JP2002360521A - Image processing device - Google Patents

Abstract

(57) [Summary] To improve the image processing result by automatically determining the type of medical image to be image-processed and performing image processing according to an image processing algorithm suitable for the type of medical image. To be able to When an operator selects a processing button 404, an image processing apparatus automatically determines the type of a medical image obtained by photographing the chest, for example, and the breast processing apparatus suitable for processing the image photographed by the chest. Image processing is performed according to the algorithm. When the image processing algorithm is selected, CR
At T508, the cross-sectional image 400 of the observation target and the algorithm display 402 are displayed, and the operator can confirm the selected algorithm.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image processing apparatus, and more particularly to an image processing apparatus for analyzing and processing an image captured by an X-ray CT apparatus or the like.

[0002]

2. Description of the Related Art FIG. 6 shows an example in which an image processing apparatus is connected to various modalities. As shown in the figure, the image processing device 608 includes an X-ray CT device 600 and an X-ray device 6
02, and is connected to different modalities such as the MRI apparatus 604 and the ultrasonic apparatus 606, and processes image data acquired from each modality. The respective devices can be connected for communication via a communication line network 610, and transmission and reception can be performed between the devices.

An image processing apparatus 608 for processing image data obtained from different modalities, such as an X-ray CT apparatus 600 and an MRI apparatus 604, can apply the same image processing method by changing parameters in most cases. Although very rare, it may be better to use different image processing methods for each modality. By the way, in a conventional image processing apparatus, a modality of photographing an image is recorded separately from a photographed image, and parameters are changed and an image processing method is selected based on the modality information.

[0004]

However, in the conventional image processing apparatus, when performing image processing using a computer diagnostic apparatus or the like, the amount of noise included in the image is smaller than that of the model used for photographing, for example. In some cases, it depends on the displayed image quality, and there is a problem that the processing result is not improved even if the modality information is considered.

For example, in a lung cancer screening, X-ray C
When imaging the chest using a T device or the like, if the amount of X-rays emitted is reduced to reduce the amount of exposure, the captured image has a large amount of noise and the image quality deteriorates. In addition, if the X-ray dose radiated at the time of imaging is weakened, the accuracy in performing CAD analysis is also deteriorated. For this reason, there has been a problem that the image processing algorithm must be changed as necessary depending on the amount of noise in the captured image.

[0006] The present invention has been made in view of such circumstances, and it is intended to automatically determine the type of medical image to be processed and to perform image processing according to an image processing algorithm suitable for the type of medical image. Accordingly, an object of the present invention is to provide an image processing apparatus capable of improving an image processing result.

[0007]

SUMMARY OF THE INVENTION In order to achieve the above object, the present invention provides processing of a plurality of types of medical images such as medical images having different modalities, medical images having different image qualities, and medical images having different imaging regions. Image input means for inputting a medical image to be input, image analysis means for analyzing the medical image input to the image input means and determining the type of the medical image,
Having a plurality of image processing algorithms corresponding to the plurality of types of medical images, selecting an image processing algorithm corresponding to the type of medical image determined by the image analysis means from the plurality of image processing algorithms, and selecting the selected image Image processing means for processing the medical image input to the image input means according to a processing algorithm.

According to the present invention, a type of an image is determined by analyzing a medical image, an image processing algorithm is selected according to the determined type of the image, and the medical image is processed according to the selected algorithm. To

[0009]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the image processing apparatus according to the present invention will be described below in detail with reference to the accompanying drawings.

FIG. 1 is a flowchart showing an embodiment of the image processing apparatus according to the present invention. As shown in FIG. 1, an image processing algorithm is selected according to the magnitude of the variance (standard deviation) of the image reflected on the noise level of the medical image, and image processing is performed.

First, in order to determine the magnitude of the variance value of an image, predetermined "large" and "small" variance value levels are set in advance. Subsequently, the variance of the input medical image is calculated. If it is determined that the calculated variance value of the image is larger than the “large” level variance value (Step S1, hereinafter abbreviated as S1), a high noise algorithm is selected (S4). ), And proceed to S7. If it is determined that the calculated variance value of the image is smaller than the “large” level variance value, it is compared with the “small” level variance value (S2). If it is determined that the variance value of the calculated image is larger than the variance value of the “small” level, the algorithm for medium noise is selected (S5), and the process proceeds to S7.
If it is determined that the variance is smaller than the “small” level, a low noise algorithm is selected (S6), and S7 is selected.
Proceed to processing. At S7, the medical image is processed using an image processing algorithm according to the magnitude of the noise selected at S4, S5, S6.

As described above, by selecting an image processing algorithm according to the magnitude of noise in a medical image,
By performing noise reduction processing, it is possible to increase the reliability of a captured image.

FIG. 2 is a flowchart showing another embodiment of the image processing apparatus according to the present invention. As shown in FIG. 2, an image processing algorithm is selected according to the type of the imaging modality, and image processing is performed.

First, in order to determine the imaging modality of an image, the data structure of the input medical image is detected. If it is determined that the data structure of the detected image includes a negative pixel value (S20), an X-ray CT image algorithm is selected (S23), and the process proceeds to S26. If it is determined that the data structure of the detected image does not include a negative pixel value, it is determined whether all the data structures have positive pixel values (S21). If it is determined that all of the data structures of the detected image include positive pixel values, an MRI image algorithm is selected (S24), and the process proceeds to S26.
If it is determined that not all the data structures of the detected image include positive pixel values, it is determined whether the variance of the data structure is large (S22). If it is determined that the variance of the data structure of the detected image is large, the algorithm for ultrasonic image is selected (S25), and S26.
Proceed to processing. If it is determined that the variance of the data structure of the detected image is small, the flowchart ends. In S26, the medical image is processed using an image processing algorithm corresponding to the type of the modality selected in S23, S24, S25. As described above, by processing the medical image using each of the photographed modalities, it is possible to convert the medical image into a diagnostic image for each modality.

FIG. 3 is a flowchart showing still another embodiment of the image processing apparatus according to the present invention. As shown in FIG. 3, an image processing algorithm is selected according to the imaging region of the medical image, and image processing is performed.

First, the data structure of the input medical image is detected in order to determine the imaging region of the medical image. Subsequently, the data structure of the detected image is compared with the data structure of the master image recorded in advance, and the pattern of the image is recognized. When it is determined that the recognized image pattern matches the head pattern (S31), the head algorithm is selected (S34), and the process proceeds to S37. When it is determined that the data structure of the recognized image does not match the head pattern, it is determined whether the data structure matches the chest pattern (S32). When it is determined that the data structure of the recognized image matches the chest pattern, a chest algorithm is selected (S35), and the process proceeds to S37. If it is determined that the data structure of the recognized image does not match the chest pattern, it is determined whether or not it matches the abdomen pattern (S33). If it is determined that the data structure of the recognized image matches the abdominal pattern, an abdominal algorithm is selected (S36), and the process proceeds to S37. If it is determined that the data structure of the recognized image does not match the abdomen pattern, the flowchart ends. S37
Then, the medical image is processed using an image processing algorithm corresponding to the imaging region selected in S34, S35, and S36. As described above, by processing the medical image according to the photographed part, it is possible to obtain diagnosis support information indicating an abnormality of each part.

FIG. 4 shows a display example of the observation target displayed on the image processing apparatus when performing the image processing corresponding to the imaging site shown in FIG. As shown in FIG.
Shows a cross-sectional image 400 of the observation target showing the imaged part.
, An algorithm display 402 on which the selected image processing algorithm is displayed, a process button 404 selected when the operator performs an operation process, and an end button 406 selected when the operator ends the operation. Have been.

When the operator selects the process button 404,
The image processing apparatus automatically determines, for example, the type of a medical image obtained by imaging the chest, and performs image processing according to a chest algorithm suitable for processing the image obtained by imaging the chest.
The CRT 508 also displays a cross-sectional image 400 of the observation target showing the image-processed chest and an algorithm display 402 for the selected chest, so that the operator can confirm the selected algorithm. If the operator desires to end the operation, the operator selects the end button 406 displayed on the CRT 508. When the end button 406 is designated, the image processing of the medical image ends.

FIG. 5 is a block diagram showing an example of a hardware configuration of an image processing apparatus used in the image processing apparatus according to the present invention. As shown in FIG. 5, the image processing device 608
Mainly include a magnetic disk 500 and a main memory 502
, Central processing unit (CPU) 504, display memory 50
6, a CRT 508, a controller 510, a mouse 512, a keyboard 514, and a common bus 516 connecting the above components.

An X-ray C
The three-dimensional original image acquired by the T device or the like and an image configuration program are stored, and the main memory 502 stores a control program of the device. First, a three-dimensional original image, an image composition program, etc., control the operation of each component.
Read by PU 504. Note that the CPU 504
Automatically determines the type of the input medical image, and performs image processing according to an image processing algorithm suitable for the type of the medical image.

Subsequently, the main memory 502 forms, for example, a cross-sectional image or a pseudo three-dimensional image from the read three-dimensional original image and the like, and image data indicating the formed image is stored in the display memory 5.
06, and an image is displayed on the CRT 508 based on the image data. Note that input devices such as a mouse 512 and a keyboard 514 controlled by the controller 510 perform input / output processing and various processing operations.

[0022]

As described above, according to the image processing apparatus of the present invention, the medical image is processed according to the selected image processing algorithm, so that the image processing result can be improved.

[Brief description of the drawings]

FIG. 1 is a flowchart illustrating an embodiment of an image processing apparatus according to the present invention.

FIG. 2 is a flowchart showing another embodiment of the image processing apparatus according to the present invention.

FIG. 3 is a flowchart showing still another embodiment of the image processing apparatus according to the present invention.

FIG. 4 is a view showing a display example of an observation target displayed on the image processing apparatus when performing image processing according to the imaging region shown in FIG. 3;

FIG. 5 is a block diagram showing an example of a hardware configuration of an image processing device used in the image processing device according to the present invention.

FIG. 6 is a diagram illustrating an example in which the image processing apparatus is connected to various modalities.

[Explanation of symbols]

400: cross-sectional image of the observation target, 402: algorithm display, 404: processing button, 406: end button, 500
... magnetic disk, 502 ... main memory, 504 ... CPU,
506: display memory, 508: CRT, 510: controller, 512: mouse, 514: keyboard, 516
... common bus, 600 ... X-ray CT apparatus, 602 ... X-ray apparatus, 604 ... MRI apparatus, 606 ... ultrasonic apparatus, 6
08: image processing device, 610: communication line network

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI theme coat ゛ (reference) // A61B 6/03 360 A61B 5/05 380 F term (reference) 4C093 AA01 AA21 AA26 CA29 FF19 FF50 4C096 AA20 AB50 AD14 DC11 DC14 DC18 DC21 DC35 DD01 DE02 4C301 DD30 EE07 EE14 EE20 JC06 JC16 JC20 KK40 LL13 LL20 5B057 AA08 AA09 CA08 CA16 CA16 CB08 CB16 CE02 CH01 CH12 CH14 CH18 DA20 DB09 DC22 5L096 AA03 MA06 FA06

Claims (1)

[Claims] An image input unit for inputting a medical image to be processed from a plurality of types of medical images, such as medical images having different modalities, medical images having different image qualities, and medical images having different imaging regions; Image analyzing means for analyzing a medical image input to the apparatus to determine the type of the medical image, and a plurality of image processing algorithms according to the plurality of types of medical images, the medical image of the medical image determined by the image analyzing means Image processing means for selecting an image processing algorithm according to the type from the plurality of image processing algorithms, and processing the medical image input to the image input means according to the selected image processing algorithm. Image processing device.