WO2025212901A1

WO2025212901A1 - Reducing tomosynthesis file sizes

Info

Publication number: WO2025212901A1
Application number: PCT/US2025/022974
Authority: WO
Inventors: Andrew P. Smith
Original assignee: Hologic Inc
Current assignee: Hologic Inc
Priority date: 2024-04-03
Filing date: 2025-04-03
Publication date: 2025-10-09
Anticipated expiration: 2026-10-03

Abstract

Systems and methods related to processing medical image data. Medical image data of a patient's breast tissue is received from a medical imaging device. The medical image data includes a plurality of X-ray projection images of the patient's breast tissue from a plurality of perspectives. The medical image data is encoded using lossy compression. The medical image data is decoded to yield a transmission image. The transmission image is encoded using lossless compression to yield a first compressed image. The first compressed image is transmitted to a first viewing device. The first viewing device is configured to decode the first compressed image to yield the transmission image and view the transmission image using the first viewing device. Viewing the transmission image includes viewing at least one of the plurality of X-ray projection images of the patient's breast or a composite image of the plurality of X-ray projection images.

Description

REDUCING TOMOSYNTHESIS FILE SIZES

CROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 63/573,688, filed on 03 April 2024, the disclosure of which is incorporated by reference in its entirety.

BACKGROUND

[0002] Medical imaging provides for visualization of internal structures of a patient’s body and is widely applied in healthcare for a number of applications. Medical imaging supports diagnosis, treatment planning, and monitoring of numerous medical conditions. For example, medical imaging plays a crucial role in breast health through early detection, diagnosis, and monitoring of breast-related conditions, particularly breast cancer, with mammography being one of the most common and effective tools for breast cancer screening and diagnosis. Digital mammography and 3D mammography techniques, such as tomosynthesis, are advanced techniques which may provide clearer images and better detection rates compared to traditional film mammography.

[0003] Along with the imaging improvements provided by more advanced techniques, the file sizes of medical images have grown substantially over time. These very large files often create issues for hospitals and other healthcare institutions. These issues include high storage costs, especially for institutions that generate a significant amount of imaging data, as extensive storage infrastructure, backup systems, and longterm data retention can strain budgets. Transmitting large medical image files between healthcare facilities or from imaging equipment to healthcare providers can be slow and cumbersome, leading to delays in diagnosis and treatment decisions. Transmitting large image files over networks consumes significant bandwidth, affecting the performance of other critical healthcare systems and potentially causing network congestion. Downloading or transmitting large data files can be time-consuming and may require specialized equipment and software. Long-term archiving and retrieval of large medical image datasets present logistical challenges. Healthcare organizations must have robust archiving solutions to ensure data availability when needed.

[0004] To offset these problems, various data compression methods are used to improve at least the transmissibility and storage options associated with medical image files. Generally, data compression methods can be divided into two groups, lossless and lossy compression. Lossless compression is a method that reduces the file size of an image while preserving all data from an original image. When you decompress a file that has undergone lossless compression, it is restored to the original, uncompressed image. Lossy compression reduces the file size of an image by selectively discarding some image data that is considered less essential. This results in a smaller file but may be characterized as potentially leading to a loss of some image data. Choosing between the two depends on the specific requirements and constraints of the medical application.

SUMMARY

[0005] Examples presented herein relate to a method of processing medical image data, the method including (a) receiving medical image data (A) of a patient’s breast tissue from a medical imaging device, the medical image data (A) including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspectives; (b) encoding the medical image data using lossy compression (B); (c) decoding the medical image data to yield a transmission image (C); (d) encoding the transmission image using lossless compression to yield a first compressed image (D); and (e) transmitting the first compressed image (D) to a first viewing device, wherein the first viewing device is configured to decode the first compressed image (D) to yield the transmission image (C) and view the transmission image (C) using the first viewing device, wherein viewing the transmission image includes viewing at least one of the plurality of X-ray projection images of the patient’s breast or a composite image of the plurality of X-ray projection images.

[0006] In other examples presented herein, the projection images are one of an Mp image and a Tp image. In other examples presented herein, the projection images of the medical image data are processed to produce a reconstructed image which is subject to steps (b) through (e). In further examples presented herein, the reconstructed image is one of a Tp image and a Ms image. In other further examples presented herein, the transmission image (C) is the reconstructed image.

[0007] In other examples presented herein, encoding the medical image data (A) using lossy compression yields a second compressed image (B) and the method further includes (f) transmitting the second compressed image (B) to a second viewing device, wherein the second viewing device is configured to decode the second compressed image (B) to yield the transmission image (C) and view the transmission image (C) using the second viewing device. In further examples presented herein, each of the first (D) and second (B) compressed images are decoded to yield a visually identical transmission image (C). In still further examples presented herein, each of the first (D) and second (B) compressed images are decoded to yield an identical transmission image (C). In other further examples presented herein, the visually identical transmission images (C) are defined by appearing to be identical to a plurality of users. In yet other examples presented herein, step (f) is performed in parallel with any of steps (b) - (e). In further examples presented herein, steps (e) and (f) are performed in parallel. In other examples presented herein, steps (a) - (e) are performed in order.

[0008] In still other examples presented herein, the method further includes identifying the first viewing device as a target viewing device; determining the first viewing device does not support lossy compression; and in response to determining the first viewing device does not support lossy compression, decoding the medical image data to yield the transmission image (C) and encoding the transmission image using lossless compression to yield the first compressed image (D). In yet other examples presented herein, the method further includes (g) processing the medical image data (A) into an output format (Al). In further examples presented herein, the transmission image (C) has reduced noise as compared to the output format (Al). In still further examples presented herein, processing the medical image data (A) into the output format (Al) includes encoding the medical image data using lossy compression. In other further examples presented herein, step (g) is performed prior to step (b).

[0009] In other examples presented herein, the method further includes storing the transmission image (C). In yet other examples presented herein, the medical imaging device is a mammography imaging device. In further examples presented herein, the medical imaging device is a tomosynthesis imaging device.

[0010] Other examples presented herein relate to a system for processing medical image data, the system including a processor; and a non-transitory memory in communication with the processor and storing instructions that, when executed, cause the processor to: receive medical image data of a patient’s breast tissue from a medical imaging device, the medical image data including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspective; encode the medical image data using lossy compression; decode the medical image data to yield a transmission image; encode the transmission image using lossless compression to yield a compressed image; and transmit the compressed image to a first viewing device, wherein the first viewing device is configured to decode the compressed image to yield the transmission image and view the transmission image using the first viewing device.

[0011] In other examples presented herein, the projection images are one of an Mp image and a Tp image. In other examples presented herein, the projection images of the medical image data are processed to produce a reconstructed image which is subject to steps (b) through (e). In further examples presented herein, the reconstructed image is one of a Tp image and a Ms image. In other further examples presented herein, the transmission image (C) is the reconstructed image.

[0012] In other examples presented herein, encoding the medical image data using lossy compression yields a second compressed image and the instructions further cause the processor to transmit the second compressed image to a second viewing device, wherein the second viewing device is configured to decode the second compressed image to yield the transmission image and view the transmission image using the second viewing device. In yet other examples presented herein, the instructions further cause the processor to identify the first viewing device as a target viewing device; determine the first viewing device does not support lossy compression; and in response to determining the first viewing device does not support lossy compression, decode the medical image data to yield the transmission image and encode the transmission image using lossless compression to yield the compressed image. In still other examples presented herein, the instructions further cause the processor to reconstruct the medical image data into an output format to yield a reconstructed image, wherein the transmission image has reduced noise as compared with the reconstructed image.

[0013] In other examples presented herein, the system further includes the medical imaging device. In further examples presented herein, the medical imaging device is a mammography imaging device. In still further examples presented herein, the medical imaging device is a tomosynthesis imaging device. In other examples presented herein, the instructions further cause the processor to store the transmission image.

[0014] Still other examples presented herein relate to a non-transitory computer- readable medium having stored thereon sequences of instructions, the sequences of instructions including instructions that when executed by a computer system causes the computer system to perform: receiving medical image data from a medical imaging device, the medical image data including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspective; encoding the medical image data using lossy compression; decoding the medical image data to yield a transmission image; encoding the transmission image using lossless compression to yield a first compressed image; transmitting the first compressed image to a first viewing device; decoding the first compressed image to yield the transmission image; and viewing the transmission image using the first viewing device.

[0015] In other examples presented herein, the projection images of the medical image data are processed to produce a reconstructed image. In further examples presented herein, the transmission image is the reconstructed image.

[0016] In other examples presented herein, encoding the medical image data using lossy compression yields a second compressed image and the instructions further include: identifying a second viewing device as a target viewing device; determining the second viewing device supports lossy compression; in response to determining the second viewing device supports lossy compression: transmitting the second compressed image to a second viewing device; decoding the second compressed image to yield the transmission image; and viewing the transmission image using the second viewing device.

[0017] A variety of additional inventive aspects will be set forth in the description that follows. The inventive aspects can relate to individual features and to combinations of features. It is to be understood that both the forgoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the broad inventive concepts upon which the embodiments disclosed herein are based.

BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of the description, illustrate several aspects of the present disclosure. A brief description of the drawings is as follows:

[0019] FIG. 1 is a perspective view of an example imaging system.

[0020] FIG. 2A is a partial enlarged view of the imaging system of FIG. 1.

[0021] FIG. 2B is a partial front view of the imaging system of FIG. 1.

[0022] FIG. 3 is an example block diagram of an image processor for processing and generating breast X-ray images.

[0023] FIG. 4 is a processing diagram of processing pathways used by the medical image data.

[0024] FIG. 5 is a flowchart of a method for processing medical image data. [0025] FIG. 6 depicts an example of a suitable operating environment in which one or more of the present examples can be implemented.

DETAILED DESCRIPTION

[0026] For the following defined terms and abbreviations, these definitions shall be applied throughout this patent specification and the accompanying claims, unless a different definition is given in the claims or elsewhere in this specification:

[0027] An “acquired image” refers to an image generated while visualizing a patient's tissue. Acquired images can be generated by radiation from a radiation source impacting on a radiation detector disposed on opposite sides of a patient's tissue, as in a conventional mammogram.

[0028] A “reconstructed image” refers to an image generated from data derived from a plurality of acquired images. A reconstructed image simulates an acquired image not included in the plurality of acquired images.

[0029] A “synthesized image” refers to an artificial image generated from data derived from a plurality of acquired and/or reconstructed images. A synthesized image includes elements (e.g., objects and regions) from the acquired and/or reconstructed images, but does not necessarily correspond to an image that can be acquired during visualization. Synthesized images are constructed analysis tools.

[0030] An “Mp” image is a conventional mammogram or contrast enhanced mammogram, which are two-dimensional (2D) projection images of a breast, and encompasses both a digital image as acquired by a flat panel detector or another imaging device, and the image after conventional processing to prepare it for display (e.g., to a health professional), storage (e.g., in the PACS system of a hospital), and/or other use.

[0031] A “Tp” image is an image that is similarly two-dimensional (2D), but is acquired at a respective tomosynthesis angle between the breast and the origin of the imaging x rays (typically the focal spot of an x-ray tube), and encompasses the image as acquired, as well as the image data after being processed for display, storage, and/or other use.

[0032] A “Tr” image is type (or subset) of a reconstructed image that is reconstructed from tomosynthesis projection images Tp, for example, in the manner described in one or more of U.S. Pat. Nos. 7,577,282, 7,606,801, 7,760,924, and 8,571,289, the disclosures of which are fully incorporated by reference herein in their entirety, wherein a Tr image represents a slice of the breast as it would appear in a projection x ray image of that slice at any desired angle, not only at an angle used for acquiring Tp or Mp images.

[0033] An “Ms” image is a type (or subset) of a synthesized image, in particular, a synthesized 2D projection image that simulates mammography images, such as a craniocaudal (CC) or mediolateral oblique (MLO) images, and is constructed using tomosynthesis projection images Tp, tomosynthesis reconstructed images Tr, or a combination thereof. Ms images may be provided for display to a health professional or for storage in the PACS system of a hospital or another institution. Examples of methods that may be used to generate Ms images are described in the above-incorporated U.S. Pat. Nos. 7,760,924 and 8,571,289.

[0034] It should be appreciated that Tp, Tr, Ms and Mp image data encompasses information, in whatever form, that is sufficient to describe the respective image for display, further processing, or storage. The respective Mp, Ms. Tp and Tr images are typically provided in digital form prior to being displayed, with each image being defined by information that identifies the properties of each pixel in a two-dimensional array of pixels. The pixel values typically relate to respective measured, estimated, or computed responses to X-rays of corresponding volumes in the breast, i.e., voxels or columns of tissue. In a preferred embodiment, the geometry of the tomosynthesis images (Tr and Tp) and mammography images (Ms and Mp) are matched to a common coordinate system, as described in U.S. Pat. No. 7,702,142. Unless otherwise specified, such coordinate system matching is assumed to be implemented with respect to the embodiments described in the ensuing detailed description of this patent specification.

[0035] The terms “generating an image” and “transmitting an image” respectively refer to generating and transmitting information that is sufficient to describe the image for display. The generated and transmitted information is typically digital information.

[0036] Embodiments of the present disclosure relate to systems and method for processing tomosynthesis and other mammography image files, including reducing the file size of the image data and ensuring consistency between images decoded by both lossless and lossy supporting devices. Following image reconstruction, the image is compressed to provide additional viewing improvement while substantially reducing the file size for storage and transmission, while providing an image that is substantially visually identical to the original reconstructed image.

[0037] Mammographic exam image files, and tomosynthesis files in particular, can be very large, creating issues in hospital systems with transmitting and storing the files. These files are quite large, even in comparison with other medical image data files, because they contain numerous high-resolution images used, for example, to create a detailed three-dimensional reconstruction image of the breast tissue. While most forms of medical imaging generally capture only a few images, tomosynthesis may take a hundred or more images from different angles, resulting in much more data. Each image is captured at a high pixel resolution to ensure small abnormalities, such as tumors or microcalcifications, are clearly visible. The images may then be combined into a three- dimensional model, which requires significant computational processing. These high- resolution files are often necessary for accurate diagnosis, as they allow radiologists to detect even the smallest changes in tissue structure, improving the chances of early detection of conditions like breast cancer.

[0038] To accommodate these large files within the limited storage space and transmission bandwidth of hospital information networks, the files are compressed, but generally using only non-lossy (lossless) algorithms. Lossless compression is characterized by complete preservation of all original data. The primary objective of lossless compression is to ensure the original object can be fully reconstructed in its original state when the data is decompressed. This significantly limits the amount of compression that lossless compression can achieve. While it reduces file size somewhat, the files remain large enough to noticeably slow transmission and require extensive and costly storage infrastructure.

[0039] Lossy compression achieves higher compression ratios than lossless due to selectively discarding some portions of the original data, and the algorithms can be tuned to balance preservation of essential data with the desired degree of compression. Lossy compression of files is known to significantly reduce file sizes, but the use of lossy compression is not utilized in mammography because of regulatory concerns of the images varying from the original image captured depending upon whether or not a lossy compression was used.

[0040] Lossy compressed images can be unstable across different system networks due to variations in how the compression and decompression processes are handled. If different systems or networks use different versions of the compression algorithm or settings, this can lead to inconsistencies when the image is decompressed, causing, for example, artifacts, color shifts, or blurriness. Lossy compression methods often rely on specific parameters, such as compression ratio or quantization tables, that may not be universally supported across different platforms or software. For example, one system may apply a higher compression rate, leading to greater loss of detail, while another may apply a lower rate, preserving more of the image quality. These differences can result in variations in the image when viewed on different systems, especially when the file is transferred across networks that may alter the image during transmission, such as due to differences in bandwidth or data handling.

[0041] In environments where precise image quality is critical, such as medical imaging, this instability can be concerning. Even minor variations in quality can affect interpretation or visual consistency. This has led to lossy compression being outright discarded as an option for processing medical image data.

[0042] The solution disclosed herein reduces the compressed file size of the mammography image to be substantially similar to that of a file compressed using a lossy algorithm. Potential concerns related to the image quality of a mammography image following lossy compression are avoided because the images that are viewed and stored by the hospital are visually identical regardless of whether lossy or non-lossy (lossless) compression algorithm are employed.

[0043] Facilities typically follow guidelines and recommendations from professional organizations, such as the American College of Radiology (ACR) and the Food and Drug Administration (FDA), regarding the appropriate use of compression and image quality standards. The FDA regulates mammographic images and equipment under the Mammography Quality Standards Act (MQSA). The MQSA and its associated regulations do not specifically address image compression techniques or requirements, but provide guidelines and regulations related to image quality and standards for mammography. Facilities need to consider the impact of any compression techniques they use on the quality and diagnostic value of mammographic images. Compression should be applied in a manner that does not compromise the visibility of important details, such as microcalcifications or small lesions, which are critical for breast cancer detection.

[0044] Mammography facilities are required to have quality assurance programs in place to monitor and maintain the quality of mammographic images. MQSA mandates that mammograms be interpreted by qualified radiologists with specific training and experience in mammography. The accuracy of the interpretation depends on the quality of the images. Based on these standards, the quality of the images can be judged based on a radiologist’s ability to make clinical determinations according to the image. Mammography facilities are also expected to adhere to professional guidelines and best practices when implementing image compression techniques to ensure that they do not compromise the diagnostic value of mammograms.

[0045] Historically, this has been taken as excluding lossy compression of mammographic images. However, studies conducted over the last several years have demonstrated clinical suitability of images decoded following lossy compression, in some case up to an 80: 1 lossy compression ratio. Images processed and compressed as described herein present a number of advantages over current method of image compression for mammography images. In a typical compression method, lossy and lossless algorithms will produce different images when the compressed file is decoded. An image compressed and stored according to the principles of the present disclosure can be stored and transmitted using either of a lossy or a lossless process and, when decoded for viewing, will present the same image regardless of whether it was encoded and then decoded using a lossy or a lossless method.

[0046] In addition to providing a consistent image regardless of the encoding method used for transmission, the file that is stored is smaller than a typical compressed mammography image and much smaller than the final image, while still supporting accurate decoding into the final image. Despite providing a smaller overall file for storage and transfers, the final image provided by the present disclosure is visually identical to the original reconstructed image. To the extent the final image does vary from the original reconstructed image, the differences are not clinically significant and, further, the additional processing to reduce the storage file size provides advantages including reducing the noise in the final image as compared with the original reconstructed image. As discussed herein, the visually identical transmission images, once decoded, are not distinguished from one another based on inspection by a plurality of users or other human observers. The image therefore appears identical to the plurality of users. Further, no clinically significant differences are identifiable between two or more visually identical transmission images.

[0047] FIG. 1 is a perspective view of an example imaging system 100. Imaging system 100 may be used to capture the medical images to be processed using the methods and principles of the present disclosure. In the example, the imaging system 100 may include a gantry 102 and a data acquisition workstation 104. The gantry 102 includes a housing 106 supporting a tube arm assembly 108 that includes a rotatable compression arm assembly 110 and a rotatable x-ray tube assembly 112. The compression arm assembly 110 enables a patient’s breast to be immobilized for x-ray imagining, such as either, or both, of mammography and tomosynthesis. The compression arm assembly 110 includes a compression paddle 114 and a receptor housing 116 disposed opposite the compression paddle 114. The receptor housing 116 has a compression surface 118 that directly contacts the breast during compression and immobilization. The receptor housing 116 encloses a detector subsystem 120 that includes an image receptor 122 and may include an anti-scatter grid 124 (both shown in FIGS. 2A and 2B). The grid may optionally be retractable or otherwise removable from the imaging field of view. The compression arm assembly 110 is in a path of an imaging beam that emanates from an x-ray source 126 housed in the x-ray tube assembly 112, such that the beam impinges in the image receptor 122.

[0048] The housing 106 may also house and enclose a vertical travel assembly for moving the tube arm assembly 108 up and down to accommodate a particular patient or imaging position. An x-ray tube arm position mechanism can be used to rotate and/or position the x-ray tube assembly 112 for different imaging positions. A compression arm position mechanism is used to rotate and/or position the compression paddle 114, image receptor 122, and the grid 124. Generally, the housing 106 includes any suitable motors and electrical and mechanical components and connections to implement these functions as discussed herein.

[0049] The workstation 104 may include a display screen (typically a flat panel display that may include touch-screen functionality), user interface devices such as a keyboard, a mouse or trackball, and various switches and indicator lights and/or displays. The workstation 104 also includes computing facilities (e.g., hardware, firmware, and software) for controlling the gantry 102 and for processing, storing, and displaying data and images received from the gantry 102 during imaging operations. The gantry 102 and the workstation 104 may exchange data and controls of a schematically illustrated connection 136. In other examples, the gantry 102 and the workstation 104 may be integrated in a single unit. A power source 138 may power the imaging system 100.

[0050] FIG. 2A is a partial enlarged view of the imaging system 100 of FIG. 1. FIG. 2B is a partial front view of the imaging system 100. Referring concurrently to FIGS. 2A and 2B, certain components of the imaging system of FIG. 1 are described above, and as such, are not necessarily described further. In operation, the imaging system 100 immobilizes a patient’s breast for x-ray imaging (either or both of mammography and tomosynthesis) via the compression arm assembly 110 that includes the static receptor housing 116 and the moveable compression paddle 114, both which are coupled to a support arm 140. The compression paddle 114 is configured to move M along the support arm 140 and toward the receptor housing 116 to compress and immobilize the breast. The compression paddle 114 is positionable and supported by a compression arm device 142 that is disposed at least partially within the support arm 140 and at least partially outside of the support arm 140. In some examples, the compression paddle 114 may also be configured to linearly translate T in relation to the compression arm device 142. The compression arm device 142 includes an external compression device assembly 144 that the compression paddle 114 can removably couple thereto. The compression device assembly 144 includes at least one control, such as rotatable knob 146 or a button, etc., which can be utilized to move the compression paddle 114 as described herein. In the example, the compression arm device 142 may be a component of a compression arm position mechanism that drives motion of the compression paddle 114.

[0051] For mammography, the compression arm assembly 110 and the x-ray tube assembly 112 can rotate as a unit about an axis 148 (shown in FIG. 2A) between different imaging orientations such as CC and MLO, so that the imaging system 100 can take a mammogram projection image at each orientation. In mammography imaging operations, the image receptor 122 remains in place relative to the receptor housing 116 while an image is taken. The compression arm assembly 110 can release the breast for movement of one or more of the compression arm assembly 110 and the x-ray tube assembly 112 to a different imaging orientation. For tomosynthesis, the compression arm assembly 110 stays in place, with the breast immobilized and remaining in place, while at least the x-ray tube assembly 112 rotates the x-ray source 126 relative to the compression arm assembly 110 and the compressed breast about the axis 148. The imaging system 100 takes plural tomosynthesis projection images of the breast at respective angles of the x-ray beam relative to the breast.

[0052] Concurrently and optionally, the image receptor 122 may be tilted relative to the receptor housing 116 and coordinated with the rotation of the x-ray tube assembly 112. The tilting can be through the same angle as the rotation of the x-ray source 126, but may also be through a different angle selected such that the x-ray beam remains substantially in the same position on the image receptor 122 for each of the plural images. The tilting can be about the axis 148, which can, but need not, be in the image plane of the image receptor 122. A compression arm position mechanism can drive the image receptor 122 in a tilting motion. For tomosynthesis imaging and/or CT imaging, the receptor housing 106 can be horizontal or can be at an angle to the horizontal, e.g., at an orientation similar to that for conventional MLO imaging in mammography. The imaging system 100 can be solely a mammography system, a CT system, or solely a tomosynthesis system, or a “combo” system that can perform multiple forms of imaging. [0053] When the system is operated, the image receptor 122 produces imaging information in response to irradiation by the imaging x-ray beam from the x-ray source 126, and supplies it to an image processor of the workstation 104 (shown in FIG. 1) for processing and generating breast x-ray images. The workstation 104 may control the operation of the imaging system 100 and interacts with the health professional to receive commands and deliver information including processed x-ray images. A health professional, typically an x-ray technologist, generally adjusts the breast within the compression arm assembly 110 while pulling tissue towards imaging area and moving the compression paddle 114 toward the receptor housing 116 to immobilize the breast and keep it in place, with as much of the breast tissue as practicable being between the compression paddle 114 and receptor housing 116.

[0054] As noted above, the workstation 104 also includes computing facilities (e.g., hardware, firmware, and software) for controlling the gantry 102 and for processing, storing, transmitting, and displaying data and images received from the gantry 102 during imaging operations. In embodiments, workstation 104 includes an image processor for processing and generating breast x-ray images.

[0055] FIG. 3 is an example block diagram of an image processor 300 for processing and generating breast x-ray images. Image processor 300 manipulates and enhances images captured by an imaging device 350. In embodiments, imaging device 350 may be an imaging detector such as detector subsystem 120 of FIG. 1. The specific components and functions of image processor 300 can vary among embodiments. In the example of FIG. 3, image processor 300 includes noise reduction 302, enhancement 304, compression 306, and storage 308. Data may be passed out of image processor 300 to a graphics processing unit (GPU) 310 for further processing and/or image rendering for viewing.

[0056] Noise reduction 302 includes noise reduction algorithms to reduce sensor noise, such as that introduced in low-irradiation conditions. This can involve both temporal and spatial noise reduction techniques. Noise reduction in image processing improves the quality and interpretability of digital images. Noise can be introduced during image acquisition, transmission, or processing and can manifest as random variations in pixel values, reducing image clarity and affecting the performance of subsequent image analysis tasks. Noise reduction may include, by way of example, smoothing filters to reduce high-frequency noise in an image, wavelet denoising, nonlocal means (NLM) denoising, total variation denoising, anisotropic diffusion, and adaptive or bilateral filtering.

[0057] The choice of noise reduction method depends on the specific characteristics of the noise and the quality requirements of the application. As disclosed herein, noise reduction 302 may include a lossy compression algorithm. Following lossy compression, lossy encoded medical image data has reduced noise as compared with the raw or reconstructed medical image data prior to lossy encoding. In embodiments, lossy compression, with or without other noise reduction operations, may be performed during initial image processing prior to the image data reaching workstation 104, e.g., image processing components integrated into gantry 102 may perform noise reduction operations including applying lossy compression.

[0058] Enhancement 304 performs operations such as sharpening, contrast adjustment, and other image enhancements to improve the overall image quality. A variety of techniques may be applied to, for example, boost contrast and remove imperfections. Example methods include histogram equalization for better contrast, spatial filtering for sharpening, and gamma correction to adjust brightness. Image enhancement can also include more advanced techniques for example super-resolution for increasing image resolution and deep learning and neural network approaches for overall improvement. The choice of method depends on the image's specific characteristics and the desired outcome.

[0059] Combining different techniques may often yield the best results, ensuring images look their best for various applications, from photography to medical imaging. It is noted that mammography may be particularly challenging for enhancement and image processing generally, due to the size of clinical features and the application as a screening modality. This leads to a large number of patients being imaged and the expectation that a majority will present as healthy without clinically significant disease features, meaning minimal external or other additional data is available to a clinician to guide their identification of the clinically significant disease feature other than the imaging itself. Therefore ensuring each patient’s breast image data is effectively enhanced and otherwise processed for accurate assessment of clinically significant disease features is a profound consideration. However, speedy and efficient processing of the data is also important to limit delays in diagnosis and treatment. [0060] According to the present disclosure, lossy compression may be applied during enhancement operations or prior to enhancement operations to provide improved enhancement outcomes. For example, according to the present disclosure, lossy encoding may remove features from the image (such as for example features without clinical significance), providing for easier identification of those features with clinical significance. Further, as many modem mammography procedures take a series of frames from a number of perspectives to image the full volume of the breast, the lossy encoding can provide smoothing of features between adjacent frames, leading to a smoother final reconstruction image rendered from the series of frames.

[0061] As discussed above, application of lossy compression during initial image processing is a non-obvious choice in mammography imaging and image processing, as compression is generally applied to image data once processing is complete in preparation for transmission or storage of the image data. As disclosed herein, lossy compression is instead, or in addition, applied during initial image processing of raw image data and provides the unexpected effect of introducing productive processing effects to the medical image data in addition to reducing the file size. Depending on the system configuration, once the lossy encoding is applied during initial image processing, the lossy encoded medical image data may be decoded as a further operation in the initial image processing or at a viewing device in preparation for viewing the medical image data.

[0062] Compression 306 applies image compression to reduce file sizes and storage requirements. Compression in image processing involves reducing the file size of an image, while preserving its essential visual content, for efficient storage and transmission of images. In embodiments, compression 306 may be bypassed and the lossy encoded medical image data output during initial image processing and/or reconstruction is held in storage and/or transmitted to a viewing device. In cases where the lossy encoded medical image data is decoded as part of the noise reduction or enhancement process, the decoded transmission image may then be compressed at compression 306. Compression 306 may include either lossy or lossless compression, or no compression, depending on system configuration and system settings.

[0063] Storage 308 manages the storage of captured medical images. Having storage 308 within image processor 300 may assist in managing digital image data. Temporary storage is used for capturing and processing images, which can be stored in various formats, including raw and compressed files. Efficient storage management ensures smooth and effective image processing operations.

[0064] GPU 310 accelerates graphics rendering and, in embodiments, may be further applied to perform complex mathematical operations. While GPUs are primarily applied for rendering images and videos for graphical applications, they may also be applied to execute a wide range of general-purpose computing tasks, such as machine learning and simulations. In embodiments, GPU 310 is one of one or more heterogeneous processing units, including other GPUs and/or dedicated neural processing units (NPUs), to accelerate specific image processing tasks, including Al-based features like feature recognition or image segmentation. Non-limiting examples of other components, not shown, which image processor 300 may include are an image sensor interface, color and brightness correction, exposure control, image distortion correction, image stabilization, and interface and control.

[0065] FIG. 4 is a processing diagram 400 of processing pathways used by the medical image data. Processing diagram may represent data processing performed by image processor 300. In embodiments, some or all of processing pathways 402-414 may be used in processing a particular medical image data file.

[0066] Raw medical image data 402 is generated by imaging device 350. In embodiments, raw medical image data 402 is images of a patient’s breast tissue captured using imaging device 350. Imaging device 350 may be a mammography or tomosynthesis imaging system, as discussed above in reference to FIGS. 1 and 2, among other possible imaging devices.

[0067] Raw medical image data 402 is received by initial imaging processing 320 of image processor 300. Initial image processing 320 performs a number of operations to prepare the raw medical image data 402 for viewing. Operations may include noise filtering and image enhancement as discussed above in reference to FIG. 3. Initial image processing 320 reconstructs the medical image data into an output format to yield a reconstructed image.

[0068] The reconstructed image has been through initial image processing to achieve features such as high resolution and clarity to ensure precise diagnostics. The reconstructed image may be configured to support various formats, including DICOM (Digital Imaging and Communications in Medicine), to enable effective integration with medical systems. The reconstructed image may also contain essential metadata like patient information, study details, and imaging parameters for comprehensive record- keeping. In embodiments, security and encryption measures are put in place to safeguard patient data.

[0069] According to the present disclosure, initial image processing 320 also encodes the medical image data using lossy compression. The lossy encoding provides advantageous processing of the medical image data. In embodiments, the lossy encoding is used to generate a version of the medical image data suitable for storage and transmission using either of lossy or lossless compression, or no compression. In embodiments, the lossy encoded medical image data may be transmitted, held in storage, or decoded using the lossy algorithm to yield a transmission image. As discussed herein, the transmission image refers to the product image resulting from lossy encoding and then decoding the medical image data. The transmission image has reduced noise as compared with the reconstructed image, among other processing improvements.

[0070] Depending on the configuration of the workstation and overall imaging and viewing system, a viewing system 312 may be configured to decode lossy encoded medical image data. In embodiments, the lossy encoded medical image data is transmitted directly from initial image processing 320 to viewing system 312, at 404. Lossy encoded medical image data may also be held in storage 308 for later retrieval, at 406. Lossy encoded medical image data may be freely retrieved and return to storage 308 by viewing system 312, at 414. Some examples presented herein discuss handling, processing, display, etc. of the encoded medical image data by viewing device, which is one type of data handling device relevant to the methods disclosed herein. Those of skill in the art will understand that in some cases the encoded image data is handled, processed, etc., by a device which is not a viewing device.

[0071] In embodiments, lossy encoded medical image data is retrieved from storage 308 by compression 306, at 410. The lossy encoded medical image data may be lossy decoded by compression 306 and encoded with a compression algorithm, such as a lossless compression algorithm, and returned to storage, at 410. In embodiments, lossy encoded medical image data is decoded into a transmission image at initial image processing 320 and the transmission image is received by compression 306, at 408. The transmission image may be compressed by compression 306 using any number of lossy or lossless compression techniques, depending on the systems design and settings.

[0072] In some cases, viewing system 312 may be preferentially configured to receive lossless compressed medical image data. Following lossy encoding of the raw medical image data at initial image processing 320, the medical image data may be lossy decoded by either initial image processing 320 or compression 306, or another component or subsystem of image processor 300, to yield the transmission image. At compression 306, the transmission image is encoded using lossless compression to yield a compressed image. The compressed image may be held in in storage, at 410, and/or transmitted to a viewing system 312, at 412.

[0073] For example, a first viewing device may be configured to decode a lossless compressed image for viewing by a user. A user may request the medical image data for viewing at the first viewing device. The system may determine that the first viewing device is configured for decoding a lossless compressed image for viewing. The lossless compressed image may be held in storage and may be retrieved from storage by the first viewing device. The lossy encoded transmission image may be held in storage, and retrieved by compression 306 to be lossy decoded and lossless encoded prior to transmission to the first viewing device.

[0074] A second viewing device may be configured to the lossy encoded transmission image. In embodiments, the lossy encoded transmission image may be stored as a lossy compressed second transmission image. A user may request the medical image data for viewing at the second viewing device. The system may determine that the second viewing device is configured for decoding a lossy compressed image for viewing. The lossy compressed second compression image may be held in storage and may be retrieved from storage by the second viewing device.

[0075] In embodiments, a target viewing device may be identified by the image processor. For example, the first viewing device of the example above, configured to decode a lossless compressed image, is identified as a target viewing device. The image processor or another system component determines that the first viewing device does not support lossy compression or decoding. In response to determining the first viewing device does not support lossy decoding, the system decodes the lossy encoded medical image data into the transmission image and encodes the transmission image using lossless compression to yield the compressed image. The compressed image may then be transmitted to or retrieved by the first viewing device.

[0076] FIG. 5 is a flowchart of a method 500 for processing medical image data. The steps of the method 500 may generally be performed in any order. In some embodiments, steps of the method 500 are performed in the order shown in FIG. 5, in particular as discussed below in reference to particular steps and their relation to other steps of the method 500. Method 500 may be performed by an image processor, such as image processor 300 of FIGS. 3 and 4, or another image processing system.

[0077] At operation 502, medical image data of a patient’s breast tissue is received from a medical imaging device. In embodiments, the medical image data includes a plurality of X-ray images of the patient’s breast tissue from a plurality of perspectives. Medical image data may be received directly from an imaging device, such as imaging system 100 of FIG. 1, or other mammography or tomosynthesis imaging devices. The medical image data may be raw images such as tomosynthesis projection images, Tp, acquired by the tomosynthesis imaging devices. In some instances, the tomosynthesis projection images, Tp, may be stored to a storage device after processing and may be configured to be transmitted to a remote storage location.

[0078] At operation 504, the medical image data is reconstructed and other initial image processing of the raw medical image data is performed. In instances, tomosynthesis projection images, Tp, are processed using reconstruction algorithms to produce reconstructed tomosynthesis images, Tr. For example, other initial image processing can include performing noise reduction and enhancement processing. In embodiments, the medical image data includes image data of a patient’s breast tissue taken from multiple perspectives. Initial image processing may include generating a composite image representing a three-dimensional view of the patient’s breast tissue based on the multiple perspectives. For example, the composite image processing can include using either tomosynthesis projection, Tp, or reconstructed images, Tr, or some portion thereof to generate a synthesized 2D mammography image, Ms. The synthesized image, Ms, may simulate the appearance of 2D mammography images while retaining the clinical information contained in the plurality of tomosynthesis images. Initial image processing, according to the present disclosure, may further include applying lossy encoding to the medical image data. At operation 506, the medical image data, such as the reconstructed tomosynthesis Tr images, are encoded using lossy compression. The compressed reconstructed tomosynthesis Tr images may be stored in a number of formats, and may include additional patient and other information, such as the DICOM image format described above.

[0079] Once initial image data processing and reconstruction are completed, at operations 502-506, the remainder of the method 500 be performed in the order shown or another order depending on the system configuration and user operations, including one or more paths in the alternative or in parallel. [0080] At operation 507, in embodiments, a determination is made whether the transmission should be made encoded or unencoded. For example, a user may select whether an image is to be transmitted encoded or unencoded or the system may make the determination based on predetermined system parameters or parameters associated with the system or device receiving the transmission.

[0081] If the determination is made, at operation 507, that the image, such as the compressed tomosynthesis image Tr or the synthesized image Ms, is to be transmitted encoded, the proceeds to determine the appropriate or desired encoding. At operation 508, in embodiments, a determination is made whether a target viewing device supports lossy decoding. The viewing device may be a picture archiving and communication system (PACS) or another similar image storage, review and communication software. In some embodiments, the determination of the decoding configuration of the PACS or other viewing device may occur later in the method, for example after storage of the transmission image, or may be excluded. For example, the lossy encoded medical image data, such as the compressed tomosynthesis image Tr or the synthesized image Ms, may be held in storage for a period of time before being retrieved by or transmitted to a viewing device for viewing or to a compression module of the image processor for further processing.

[0082] If, at operation 508, a determination is made that the target PACS supports lossless decoding, the method proceeds to prepare the transmission image, such as the tomosynthesis image Tr or the synthesized image Ms, for lossless decoding. At operation 510, the lossy encoded medical image data, such as the tomosynthesis image Tr or the synthesized image Ms, is decoded to yield a transmission image. As discussed herein, the transmission image refers to the product image resulting from lossy encoding and then decoding the medical image data. The transmission image has reduced noise as compared with the reconstructed image, among other processing improvements. At 512, the transmission image is encoded using lossless compression to yield a compressed image.

[0083] At 514, the compressed image is transmitted to a viewing device, such as a mammography viewing workstation, or a PACS medical image review station. In embodiments, the viewing device is configured to decode the compressed image to yield the transmission image, as at operation 516. The transmission image can then be viewed using the viewing device, as at operation 518. Viewing the transmission image includes viewing at least one of the plurality of X-ray images of the patient’s breast or a composite image of the plurality of X-ray images.

[0084] If at operation 508, the viewing device is determined to support lossy decoding, the lossy encoded medical image data may be transmitted to the viewing device, as at operation 520. In embodiments, operation 520 is performed in parallel with any of operations 510 through 518. In other words, the lossy encoded medical image data may be transmitted to an appropriately configured viewing device, and/or held in storage, in parallel with being further processed into the transmission image and/or into a lossless compressed image. At operation 522, the lossy encoded medical image data is decoded to the transmission image by the viewing device. At operation 518, the transmission image is viewed at the viewing device.

[0085] If the determination is made, at operation 507, that the image is to be transmitted unencoded, the lossy encoded medical image data is decoded to yield a transmission image, at operation 524. As discussed herein, the transmission image refers to the product image resulting from lossy encoding and then decoding the medical image data. The transmission image has reduced noise as compared with the reconstructed image, among other processing improvements. The uncompressed transmission image may then be transmitted to a receiving system or device, at operation 526. At operation 518, the transmission image is viewed at the viewing device.

[0086] Thus, method 500 ensures consistent image quality and appearance across multiple viewing devices regardless of differing decompression or decoding capabilities among the multiple viewing devices. Regardless of whether the medical image data is ultimately decoded and viewed at a first viewing device, which may only support lossless decoding, or a second viewing device, which may support lossy decoding, a visually identical transmission image is viewed at each viewing device. As discussed herein, the visually identical transmission images are not distinguished from one another based on inspection by a plurality of users or other human observers. The image therefore appears identical to the plurality of users. Further, no clinically significant differences are identifiable between two or more visually identical transmission images.

[0087] Once image processing and reconstruction are complete, the lossy encoded medical image data can be decoded into the visually identical transmission image at multiple locations within the imaging system, with consistent results despite differences in decoding. For example, the lossy encoded medical image data may be sent to a viewing device which supports lossy decoding straight from initial image processing and decoded at the viewing device and viewed as the transmission image. The lossy encoded medical image data may be stored and subsequently retrieved or transmitted to the viewing device and decoded at the viewing device and viewed as the transmission image. The lossy encoded medical image data may be decoded into the transmission image and compressed using lossless compression into a compressed image, which is subsequently stored and/or obtained by a viewing device. The lossless compressed image is also decoded at the viewing device and viewed as a visually identical transmission image as compared with the transmission image viewed at the viewing device supporting lossy decoding.

[0088] The example method 500 may be understood to be performed by a single device, by multiple independent devices, or by one or more interconnected devices. In an example, all operations of the method 500 may be performed by a single device e.g., transmission at operation 507 moves the image data from storage to processing within a single device. In another example, the operations of method 500 may be divided among devices in series, e.g., transmission at operation 507 moves image data from a first device to one or more additional devices, each of which may perform a portion or subset of the remaining operations.

[0089] FIG. 6 depicts one example of a suitable operating environment 700 in which one or more of the present examples can be implemented. This operating environment may be incorporated directly into the controller for a breast imaging system, e.g., such as the controller depicted in FIG. 1 or the imaging device of FIG. 3, the system 300, or 400 as described above. The suitable operating environment 700 may also perform any of the steps of method 500 described above. This is only one example of a suitable operating environment and is not intended to suggest any limitation as to the scope of use or functionality. Other well- known computing systems, environments, and/or configurations that can be suitable for use include, but are not limited to, personal computers, server computers, hand-held or laptop devices, multiprocessor systems, microprocessor-based systems, programmable consumer electronics such as smart phones, network PCs, minicomputers, mainframe computers, tablets, distributed computing environments that include any of the above systems or devices, and the like. [0090] In its most basic configuration, operating environment 700 typically includes at least one processing unit 702 and memory 704. Depending on the exact configuration and type of computing device, memory 704 (storing, among other things, instructions to control the compression arm, image of the breast, or perform other methods disclosed herein) can be volatile (such as RAM), non-volatile (such as ROM, flash memory, etc.), or some combination of the two. This most basic configuration is illustrated in FIG. 6 by dashed line 706. Further, environment 700 can also include storage devices (removable, 708, and/or non-removable, 710) including, but not limited to, magnetic or optical disks or tape. Similarly, environment 700 can also have input device(s) 714 such as touch screens, keyboard, mouse, pen, voice input, etc., and/or output device(s) 716 such as a display, speakers, printer, etc. Also included in the environment can be one or more communication connections 712, such as LAN, WAN, point to point, Bluetooth, RF, etc. [0091] Operating environment 700 typically includes at least some form of computer readable media. Computer readable media can be any available media that can be accessed by processing unit 702 or other devices having the operating environment. By way of example, and not limitation, computer readable media can include computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, solid state storage, or any other tangible medium which can be used to store the desired information. Communication media embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of the any of the above should also be included within the scope of computer readable media. A computer-readable device is a hardware device incorporating computer storage media.

[0092] The operating environment 700 can be a single computer operating in a networked environment using logical connections to one or more remote computers. The remote computer can be a personal computer, a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above as well as others not so mentioned. The logical connections can include any method supported by available communications media. Such networking environments are commonplace in offices, enterprise-wide computer networks, intranets and the Internet.

[0093] In some examples, the components described herein include such modules or instructions executable by computer system 700 that can be stored on computer storage medium and other tangible mediums and transmitted in communication media. Computer storage media includes volatile and non-volatile, removable and non- removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, or other data. Combinations of any of the above should also be included within the scope of readable media. In some examples, computer system 700 is part of a network that stores data in remote storage media for use by the computer system 700.

[0094] Examples.

[0095] Example 1.

[0096] Example 1 presents an evaluation of the use of lossy encoding in the processing of tomosynthesis images. The method used for compression in Example 1 is jpeg 2000 Lossy and Lossless. This example presents the approximate compression ratio at which expert readers report a loss in image quality that may be clinically relevant.

[0097] To evaluate the compression ratios a set of 30 high resolution tomosynthesis images (reconstructed slices) were used. These images contained clinically meaningful features such as masses and calcifications. The compression amount was adjusted relative to the lossless size, e.g., “14” is reduced in size 4 times compared with jpeg20001ossless, the lossless compression control. The average file case sizes (four view mammograms) for various compression methods are given in Table 1.

[0098] Table 1: Average case size for 30 image set, using high resolution tomosynthesis

[0099] A subset of the 30 images, each subset being about 5 images each, were reviewed on a computer display workstation, for example a Picture archiving and communication system (PACS) workstation, by at least three experts, including one radiologist and two tomosynthesis technical experts, each with over 10 years’ experience with tomosynthesis. In the evaluation the images were labelled as shown in Table 2. The ‘G’ images were processed with no lossy encoding. The evaluations were made with respect to the ‘G’ images.

[0100] Table 2: Images for Evaluation

[0101] Each evaluator’s assessment is shown in Table 3.

[0102] Table 3: Evaluator’s Assessment

[0103] Remarks were found to be consistent across all evaluators and all images that were reviewed. All evaluators preferred the images in the order of: (1) Cl, (2) C3, and (3) C2 (ranked from best to worst). All evaluators noted that Cl and C3 were not clinically different than G. Radiologist 1 also remarked separately that they would have no objection to using lossy encoded images in their practice if the image quality was like Cl or C3. Based on this sample of high resolution tomosynthesis images a compression ratio of at least 8: 1 (relative to lossless compression) is achievable using jpeg2000 lossy compression without any significant loss of clinical image quality.

[0104] Illustrative examples of the systems and methods described herein are provided below. An embodiment of the system or method described herein may include any one or more, and any combination of, the clauses described below.

[0105] Clause 1. A method of processing medical image data, the method including: (a) receiving medical image data (A) of a patient’s breast tissue from a medical imaging device, the medical image data (A) including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspectives; (b) encoding the medical image data using lossy compression (B); (c) decoding the medical image data to yield a transmission image (C); (d) encoding the transmission image using lossless compression to yield a first compressed image (D); and (e) transmitting the first compressed image (D) to a first viewing device, wherein the first viewing device is configured to decode the first compressed image (D) to yield the transmission image (C) and view the transmission image (C) using the first viewing device, wherein viewing the transmission image includes viewing at least one of the plurality of X-ray projection images of the patient’s breast or a composite image of the plurality of X-ray projection images.

[0106] Clause 2. The method clause 1, wherein the projection images are one of an Mp image and a Tp image.

[0107] Clause 3. The method of clause 1 or 2, wherein the projection images of the medical image data are processed to produce a reconstructed image which is subject to steps (b) through (e).

[0108] Clause 4. The method of clause 3, wherein the reconstructed image is one of a Tp image and a Ms image.

[0109] Clause 5. The method of clause 4, wherein the transmission image (C) is the reconstructed image.

[0110] Clause 6. The method of any one of clauses 1-5, wherein encoding the medical image data (A) using lossy compression yields a second compressed image (B) and the method further includes: (f) transmitting the second compressed image (B) to a second viewing device, wherein the second viewing device is configured to decode the second compressed image (B) to yield the transmission image (C) and view the transmission image (C) using the second viewing device.

[0111] Clause 7. The method of clause 6, wherein each of the first (D) and second (B) compressed images are decoded to yield a visually identical transmission image (C). [0112] Clause 8. The method of clause 7, wherein each of the first (D) and second (B) compressed images are decoded to yield an identical transmission image (C).

[0113] Clause 9. The method of clause 6 or 7, wherein the visually identical transmission images (C) are defined by appearing to be identical to a plurality of users.

[0114] Clause 10. The method of any one of clauses 6-9, wherein step (f) is performed in parallel with any of steps (b) - (e).

[0115] Clause 11. The method of clause 10, wherein steps (e) and (f) are performed in parallel.

[0116] Clause 12. The method of any one of clauses 1-11, wherein steps (a) - (e) are performed in order.

[0117] Clause 13. The method of any one of clauses 1-12, further including: identifying the first viewing device as a target viewing device; determining the first viewing device does not support lossy compression; and in response to determining the first viewing device does not support lossy compression, decoding the medical image data to yield the transmission image (C) and encoding the transmission image using lossless compression to yield the first compressed image (D).

[0118] Clause 14. The method of any one of clauses 1-13, further comprising (g) processing the medical image data (A) into an output format (Al).

[0119] Clause 15. The method of clause 14, wherein the transmission image (C) has reduced noise as compared to the output format (Al).

[0120] Clause 16. The method of clause 14 or 15, wherein processing the medical image data (A) into the output format (Al) includes encoding the medical image data using lossy compression.

[0121] Clause 17. The method of any one of clauses 14-16, wherein step (g) is performed prior to step (b).

[0122] Clause 18. The method of any one of clauses 1-17, further comprising storing the transmission image (C).

[0123] Clause 19. The method of any one of clauses 1-18, wherein the medical imaging device is a mammography imaging device. [0124] Clause 20. The method of clause 19, wherein the medical imaging device is a tomosynthesis imaging device.

[0125] Clause 21. A system for processing medical image data, the system including: a processor; a non-transitory memory in communication with the processor and storing instructions that, when executed, cause the processor to: receive medical image data of a patient’s breast tissue from a medical imaging device, the medical image data including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspectives; encode the medical image data using lossy compression; decode the medical image data to yield a transmission image; encode the transmission image using lossless compression to yield a compressed image; and transmit the compressed image to a first viewing device, wherein the first viewing device is configured to decode the compressed image to yield the transmission image and view the transmission image using the first viewing device.

[0126] Clause 22. The system clause 21, wherein the projection images are one of an Mp image and a Tp image.

[0127] Clause 23. The system of clause 21 or 22, wherein the projection images of the medical image data are processed to produce a reconstructed image which is subject to steps (b) through (e).

[0128] Clause 24. The system of clause 23, wherein the reconstructed image is one of a Tp image and a Ms image.

[0129] Clause 25. The system of clause 24, wherein the transmission image (C) is the reconstructed image.

[0130] Clause 26. The system of any one of clauses 21-25, wherein encoding the medical image data using lossy compression yields a second compressed image and the instructions further cause the processor to transmit the second compressed image to a second viewing device, wherein the second viewing device is configured to decode the second compressed image to yield the transmission image and view the transmission image using the second viewing device.

[0131] Clause 27. The system of any one of clauses 21-26, wherein the instructions further cause the processor to: identify the first viewing device as a target viewing device; determine the first viewing device does not support lossy compression; and in response to determining the first viewing device does not support lossy compression, decode the medical image data to yield the transmission image and encode the transmission image using lossless compression to yield the compressed image. [0132] Clause 28. The system of any one of clauses 21-27, further comprising reconstructing the medical image data into an output format to yield a reconstructed image, wherein the transmission image has reduced noise as compared with the reconstructed image.

[0133] Clause 29. The system of any one of clauses 21-28, wherein the system further includes the medical imaging device.

[0134] Clause 30. The system of clause 29, wherein the medical imaging device is a mammography imaging device.

[0135] Clause 31. The system of claim 30, wherein the medical imaging device is a tomosynthesis imaging device.

[0136] Clause 32. The system of any one of clauses 21-31, wherein the instructions further cause the processor to store the transmission image.

[0137] Clause 33. A non-transitory computer-readable medium having stored thereon sequences of instructions, the sequences of instructions including instructions that when executed by a computer system causes the computer system to perform: receiving medical image data from a medical imaging device, the medical image data including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspective; encoding the medical image data using lossy compression; decoding the medical image data to yield a transmission image; encoding the transmission image using lossless compression to yield a first compressed image; transmitting the first compressed image to a first viewing device; decoding the first compressed image to yield the transmission image; and viewing the transmission image using the first viewing device.

[0138] Clause 34. The non-transitory computer-readable medium of clause 33, wherein the projection images of the medical image data are processed to produce a reconstructed image.

[0139] Clause 35. The non-transitory computer-readable medium of clause 34, wherein the transmission image is the reconstructed image.

[0140] Clause 36. The non-transitory computer-readable medium of any one of clauses 33-35, wherein encoding the medical image data using lossy compression yields a second compressed image and the instructions further include: identifying a second viewing device as a target viewing device; determining the second viewing device supports lossy compression; in response to determining the second viewing device supports lossy compression: transmitting the second compressed image to a second viewing device; decoding the second compressed image to yield the transmission image; and viewing the transmission image using the second viewing device.

[0141] This disclosure described some examples of the present technology with reference to the accompanying drawings, in which only some of the possible examples were shown. Other aspects can, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein. Rather, these examples were provided so that this disclosure was thorough and complete and fully conveyed the scope of the possible examples to those skilled in the art.

[0142] Although specific examples were described herein, the scope of the technology is not limited to those specific examples. One skilled in the art will recognize other examples or improvements that are within the scope of the present technology. Therefore, the specific structure, acts, or media are disclosed only as illustrative examples. Examples according to the technology may also combine elements or components of those that are disclosed in general but not expressly exemplified in combination, unless otherwise stated herein. The scope of the technology is defined by the following claims and any equivalents therein.

Claims

CLAIMS What is claimed is:

1. A method of processing medical image data, the method comprising:

(a) receiving medical image data (A) of a patient’s breast tissue from a medical imaging device, the medical image data (A) including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspectives;

(b) encoding the medical image data using lossy compression (B);

(c) decoding the medical image data to yield a transmission image (C);

(d) encoding the transmission image using lossless compression to yield a first compressed image (D); and

(e) transmitting the first compressed image (D) to a first viewing device, wherein the first viewing device is configured to decode the first compressed image (D) to yield the transmission image (C) and view the transmission image (C) using the first viewing device, wherein viewing the transmission image includes viewing at least one of the plurality of X-ray projection images of the patient’s breast or a composite image of the plurality of X-ray projection images.

2. The method claim 1, wherein the projection images are one of an Mp image and a Tp image.

3. The method of claim 1 or 2, wherein the projection images of the medical image data are processed to produce a reconstructed image which is subject to steps (b) through (e).

4. The method of claim 3 , wherein the reconstructed image is one of a Tp image and a Ms image.

5. The method of claim 4, wherein the transmission image (C) is the reconstructed image.

6. The method of any one of claims 1-5, wherein encoding the medical image data (A) using lossy compression yields a second compressed image (B) and the method further comprises: (f) transmitting the second compressed image (B) to a second viewing device, wherein the second viewing device is configured to decode the second compressed image

(B) to yield the transmission image (C) and view the transmission image (C) using the second viewing device.

7. The method of claim 6, wherein each of the first (D) and second (B) compressed images are decoded to yield a visually identical transmission image (C).

8. The method of claim 7, wherein each of the first (D) and second (B) compressed images are decoded to yield an identical transmission image (C).

9. The method of claim 6 or 7, wherein the visually identical transmission images

(C) are defined by appearing to be identical to a plurality of users.

10. The method of any one of claims 6-9, wherein step (f) is performed in parallel with any of steps (b) - (e).

11. The method of claim 10, wherein steps (e) and (f) are performed in parallel.

12. The method of any one of claims 1-11, wherein steps (a) - (e) are performed in order.

13. The method of any one of claims 1-12, further comprising: identifying the first viewing device as a target viewing device; determining the first viewing device does not support lossy compression; and in response to determining the first viewing device does not support lossy compression, decoding the medical image data to yield the transmission image (C) and encoding the transmission image using lossless compression to yield the first compressed image (D).

14. The method of any one of claims 1-13, further comprising (g) processing the medical image data (A) into an output format (Al).

15. The method of claim 14, wherein the transmission image (C) has reduced noise as compared to the output format (Al).

16. The method of claim 14 or 15, wherein processing the medical image data (A) into the output format (Al) includes encoding the medical image data using lossy compression.

17. The method of any one of claims 14-16, wherein step (g) is performed prior to step (b).

18. The method of any one of claims 1-17, further comprising storing the transmission image (C).

19. The method of any one of claims 1-18, wherein the medical imaging device is a mammography imaging device.

20. The method of claim 19, wherein the medical imaging device is a tomosynthesis imaging device.

21. A system for processing medical image data, the system comprising: a processor; a non-transitory memory in communication with the processor and storing instructions that, when executed, cause the processor to:

(a) receive medical image data of a patient’s breast tissue from a medical imaging device, the medical image data including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspectives;

(b) encode the medical image data using lossy compression;

(c) decode the medical image data to yield a transmission image;

(d) encode the transmission image using lossless compression to yield a compressed image; and

(e) transmit the compressed image to a first viewing device, wherein the first viewing device is configured to decode the compressed image to yield the transmission image and view the transmission image using the first viewing device.

22. The system claim 21 , wherein the projection images are one of an Mp image and a Tp image.

23. The system of claim 21 or 22, wherein the proj ection images of the medical image data are processed to produce a reconstructed image which is subject to steps (b) through (e).

24. The system of claim 23, wherein the reconstructed image is one of a Tp image and a Ms image.

25. The system of claim 24, wherein the transmission image (C) is the reconstructed image.

26. The system of any one of claims 21-25, wherein encoding the medical image data using lossy compression yields a second compressed image and the instructions further cause the processor to transmit the second compressed image to a second viewing device, wherein the second viewing device is configured to decode the second compressed image to yield the transmission image and view the transmission image using the second viewing device.

27. The system of any one of claims 21-26, wherein the instructions further cause the processor to: identify the first viewing device as a target viewing device; determine the first viewing device does not support lossy compression; and in response to determining the first viewing device does not support lossy compression, decode the medical image data to yield the transmission image and encode the transmission image using lossless compression to yield the compressed image.

28. The system of any one of claims 21-27, wherein the instructions further cause the processor to reconstruct the medical image data into an output format to yield a reconstructed image, wherein the transmission image has reduced noise as compared with the reconstructed image.

29. The system of any one of claims 21 -28, wherein the system further comprises the medical imaging device.

30. The system of claim 29, wherein the medical imaging device is a mammography imaging device.

31. The system of claim 30, wherein the medical imaging device is a tomosynthesis imaging device.

32. The system of any one of claims 21-31, wherein the instructions further cause the processor to store the transmission image.

33. A non-transitory computer-readable medium having stored thereon sequences of instructions, the sequences of instructions including instructions that when executed by a computer system causes the computer system to perform: receiving medical image data from a medical imaging device, the medical image data including a plurality of X-ray projection images of the patient’s breast tissue from a plurality of perspectives; encoding the medical image data using lossy compression; decoding the medical image data to yield a transmission image; encoding the transmission image using lossless compression to yield a first compressed image; transmitting the first compressed image to a first viewing device; decoding the first compressed image to yield the transmission image; and viewing the transmission image using the first viewing device.

34. The non-transitory computer-readable medium of claim 33, wherein the projection images of the medical image data are processed to produce a reconstructed image.

35. The non-transitory computer-readable medium of claim 34, wherein the transmission image is the reconstructed image.

36. The non-transitory computer-readable medium of any one of claims 33-35, wherein encoding the medical image data using lossy compression yields a second compressed image and the instructions further include: identifying a second viewing device as a target viewing device; determining the second viewing device supports lossy compression; in response to determining the second viewing device supports lossy compression: transmitting the second compressed image to a second viewing device; decoding the second compressed image to yield the transmission image; and viewing the transmission image using the second viewing device.