CN102429679A - Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image - Google Patents
Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image Download PDFInfo
- Publication number
- CN102429679A CN102429679A CN2011102671651A CN201110267165A CN102429679A CN 102429679 A CN102429679 A CN 102429679A CN 2011102671651 A CN2011102671651 A CN 2011102671651A CN 201110267165 A CN201110267165 A CN 201110267165A CN 102429679 A CN102429679 A CN 102429679A
- Authority
- CN
- China
- Prior art keywords
- lung
- emphysema
- chest
- area
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
本发明公开了一种基于胸部CT图像的肺区自动分割与肺气肿计算机辅助诊断系统。首先给系统输入一组胸部CT断层系列图像，然后，对肺区进行自动分割，共分为三步：（1）利用自动阈值法分离躯干与背景；（2）应用轮廓跟踪法提取肺区轮廓；（3）利用边界扫描与区域填充法提取肺区。最后，应用基于密度分布与体积分数的肺气肿量化诊断标准，对肺区进行统计分析，将统计特征值根据需要显示给放射科医师，确定并重点显示病变区域，对病变程度进行分级，从而实现肺气肿的量化分析与准确诊断。本发明能提高放射科医师对肺气肿诊断的准确性与效率，更客观有效地辅助放射科医师进行临床诊断与制定治疗方案。
The invention discloses a system for automatically segmenting lung regions and emphysema computer-aided diagnosis based on chest CT images. First, a set of chest CT tomographic series images are input to the system, and then the lung area is automatically segmented, which is divided into three steps: (1) using the automatic threshold method to separate the trunk from the background; (2) applying the contour tracking method to extract the outline of the lung area ; (3) Using boundary scan and region filling method to extract the lung area. Finally, apply the quantitative diagnostic criteria of emphysema based on density distribution and volume fraction, carry out statistical analysis on the lung area, display the statistical characteristic values to radiologists as needed, determine and focus on displaying the lesion area, and grade the lesion degree, thus Realize quantitative analysis and accurate diagnosis of emphysema. The invention can improve the accuracy and efficiency of radiologists in diagnosing emphysema, and more objectively and effectively assist radiologists in clinical diagnosis and formulation of treatment plans.
Description
Technical Field
The invention belongs to the field of application of computer analysis technology based on medical images, and particularly relates to a computer-aided emphysema diagnosis system based on chest CT images.
Background
Chronic obstructive pulmonary disease is a disease characterized by a restricted expiratory airflow, including chronic bronchitis and emphysema. Chronic obstructive pulmonary disease can lead to pulmonary dysfunction, pulmonary hypertension, to the extent that hypoxemia develops, followed by hypercapnia and respiratory failure, leading to death of the patient. According to statistics, the prevalence rate of chronic obstructive pulmonary disease in recent years in China is 9%, the number of the existing chronic obstructive pulmonary disease is up to 5000 ten thousand, the number of deaths per year is 130 ten thousand, and chronic obstructive pulmonary disease becomes the fourth leading cause of death due to diseases.
The imaging characteristics and scope of many lesions in the patient's lungs are complex and even experienced radiologists have difficulty in objectively and accurately analyzing and diagnosing them. At present, many studies on CT image signs of chronic obstructive pulmonary disease are reported at home and abroad, but the studies are mainly focused on the qualitative aspect of lesions, and the studies on the degree of lesions, namely the quantitative aspect are less. The method for diagnosing by means of visual perception and experience widely adopted at present mainly takes the symptoms of low-density areas with different sizes, sparse pulmonary vascular texture, twisted blood vessel branches and the like in the lung as a basis, and carries out scoring or diagnosis according to the range and the severity of emphysema. This qualitative diagnostic method suffers from the following disadvantages:
depending on the individual's perception, experience and expertise, diagnostic results may vary from person to person;
the work intensity of reading the film by a radiologist is high, the film is easy to fatigue, and the work efficiency and the quality are influenced;
quantitative analysis and accurate disease grading cannot be performed;
is not favorable for the accurate evaluation and tracking of the treatment or postoperative curative effect.
Aiming at the problems in the clinical qualitative diagnosis, the imaging processing method is applied to carry out quantitative analysis on the lung area, so as to assist a doctor to make a diagnosis, and the respective advantages of qualitative diagnosis and quantitative diagnosis can be fully utilized, so that on one hand, the diagnosis workload and the labor intensity of a radiologist can be reduced, and on the other hand, the accuracy, the reliability and the efficiency of diagnosis can be improved. The calculation-aided diagnosis of emphysema can be divided into two steps, firstly, the left lung area and the right lung area are accurately extracted, and then, the lung areas are subjected to quantitative analysis according to the clinical quantitative diagnosis standard of emphysema to obtain a diagnosis conclusion.
The current automatic lung segmentation method in the chest CT image mainly comprises the following steps:
(1) method of thresholding
Osman, S.Sahin, "Lung Segmentation Algorithm for CAD System in CTA Images", World academic of Science, Engineering and technology, 77, 306-criterion segmentation of pulmonary nondudeles on pharmaceutical CT images ", medical Physics, 26 (6): 889-895(1999), etc.). The method is characterized by being simple and rapid, but cannot effectively remove the outer part of the trunk and the areas such as the trachea, the bronchus and the like, and the threshold is difficult to determine and is often determined according to experience.
(2) The region grows. Although the region growing method can keep the region with diffuse boundary, the structure surrounded by the boundary with strong gradient is usually excluded, and it is sensitive to the selection of seed point and growing combination rule. Since the region growing method is a semi-automatic segmentation method requiring manual participation, the application thereof is greatly limited (Yangka, Wu pray, Tianjie, etc. 'implementation and comparison of several image segmentation algorithms on CT image segmentation,' university of Beijing university, 20 (6): 720-.
(3) Statistical prior Model Based methods (S.Sun, G.McLennan, E.A.Hoffman, et. "Model-Based Segmentation of medical channels in volume CT Data," the third International work on Pulmonary Image Analysis, 31-40, (2010)). The method comprises the steps of collecting a large number of samples, establishing a prior model, and extracting a lung area outline by adopting a point matching and deformation method. The method has the advantages that the shape and density information of the sample can be utilized, but the model is difficult to establish, the time spent in the point matching and deformation process is long, and the real-time requirement of clinical application is difficult to meet.
(4) Pattern classification Based methods (H.Wang, J.Zhang, L.Wang, "Segmentation in cognitive CT image Based on FCM Clustering," IEEE 20103 rd International Conference on Advanced Computer Theory and Engineering (ICACTE), V3, 405-. The method extracts effective image features, some methods also need a large number of training samples, the dependence of segmentation results on the samples and the features is strong, and the processing time is long.
In summary, the conventional method for segmenting the lung region in the chest CT image, or the model and operation, is complex and has a slow segmentation speed; or the control parameters are difficult to determine, the segmentation stability and reliability are low, and the segmentation result is inaccurate. Namely, it is difficult to extract the lung region contour and the lung parenchyma rapidly and accurately, and the requirement of the computer-aided diagnosis system cannot be satisfied.
Disclosure of Invention
The invention aims to overcome the defects and shortcomings of the prior art and provide a chest CT image-based lung area automatic segmentation and emphysema computer-aided diagnosis system.
The purpose of the invention is realized by the following technical scheme: a computer-aided diagnosis system for emphysema based on CT images of the chest, comprising:
the system comprises an input module (100) for inputting a chest CT image to be diagnosed and transmitting the chest CT image to a lung region extracting module (200);
the lung region extracting module (200) is used for automatically segmenting the left and right lung regions and transmitting the lung region information to the quantitative parameter calculating module (300);
a quantization parameter calculation module (300) for calculating statistical distribution information of pixel density of the lung region or the designated region and geometric information, and transmitting the quantization parameter to the classification diagnosis module (400) and the output module (500);
the classification diagnosis module (400) is used for analyzing the data transmitted by the quantitative parameter calculation module (300) and sending the analysis result to the output module (500);
and the output module (500) positions the analysis result of the classification diagnosis module (400) in the CT image of the breast to be diagnosed input by the user, marks suspicious places with a specific color and displays the analysis result to the user.
The lung region extraction module (200) performs processing according to the following steps:
and (2.1) separating the trunk from the background in the chest CT image by adopting a global adaptive threshold method: firstly, an initial threshold value is given, and the threshold value is applied to divide the images into two types; then, calculating the mean value of the two average densities and taking the mean value as a new threshold value, classifying the images, gradually enabling the threshold value to approach an optimal value through an iterative algorithm, finally calculating an accurate threshold value, and separating the background from the trunk;
and (2.2) extracting the lung area contour by adopting a contour tracking method: firstly, detecting a pixel point of a lung contour according to a certain detection criterion, and then finding out other pixel points of a target contour by using a certain tracking criterion until all pixel points of the whole lung contour are found; then all pixel points of another lung contour are found;
and (2.3) acquiring pixels in the left and right lung regions by adopting a background marking scanning line method based on 4 neighborhoods.
And (3) selecting the average value of the density of the whole image by the initial threshold value in the step (2.1).
The step (2.3) comprises the following steps:
step (2.3.1) solving a circumscribed rectangle of the region of interest to generate a minimum rectangular region capable of covering the selected region;
marking outline points of the lung in the rectangular area as '1', and marking other outline points as '0';
step (2.3.3) scanning a rectangular area from top to bottom and from left to right, if the current pixel is marked as '0', scanning from left to right from the current pixel on the current line, and juxtaposing the passed pixels as '-1' until the contour point or the line end;
step (2.3.4) searching 4 neighborhoods of the current pixel, finding a point marked as '0', taking the point as a new starting point, scanning from left to right, juxtaposing the passing pixel and marking as '-1' until the contour point or the end of the row is reached;
and (5) after the rectangular area scanning is finished, removing the pixels marked as "-1".
The quantization parameters in the quantization parameter calculation module (300) comprise gray scale statistical parameters and geometric parameters, wherein the gray scale statistical parameters comprise average density, density variance and pixel percentage of which the density is less than, greater than or equal to a given threshold value of a left lung region and a right lung region or a user-specified region; the geometric parameters include: lung volume, area of area, perimeter, distance and angle.
The classification diagnosis module (400) comprises a judgment unit, the judgment unit judges whether the emphysema exists according to the quantitative diagnosis standard of the emphysema, and if the emphysema exists, the classification diagnosis module classifies the emphysema.
The classification diagnosis module (400) scans a lung region in each CT sectional image by using a volume fraction method according to the quantitative diagnosis standard of emphysema, compares each pixel in the lung region with a specified density threshold, counts pixels which are respectively greater than, less than or equal to the specified threshold, and calculates the percentage of the pixels which respectively occupy the whole lung region; and determining whether the lung area is normal or not according to the classification diagnosis standard of the emphysema, and if the lung area is abnormal, classifying.
The working principle and the process of the invention are as follows: firstly, inputting a group of chest CT images to be diagnosed into a system, then automatically segmenting lung regions, extracting left and right lung parenchyma, finally, identifying and diagnosing according to quantitative diagnosis standards of emphysema, marking key regions with special colors, providing a series of related density and geometric statistical parameters according to needs, and prompting a radiologist of the regions and related parameters needing key attention, thereby improving the accuracy, reliability and efficiency of the radiologist in diagnosing the emphysema.
Compared with the prior art, the invention has the following advantages:
(1) automatic, fast and accurate lung region extraction
The existing lung region segmentation methods, such as a traditional threshold segmentation method, a region growing method, a method based on a deformation model (Snake, Level set), a method based on a statistical model and a method based on pattern classification, are difficult to rapidly and accurately segment the lung region. The method divides the lung extraction into three steps, and adopts an automatic threshold value, contour tracking, boundary scanning and area filling marking method, so that the lung area can be quickly and effectively extracted.
(2) Accurately quantifying and grading emphysema
After the left lung area and the right lung area are extracted, the volume fraction can be rapidly calculated according to the emphysema quantitative diagnosis standard, and the emphysema quantitative classification can be realized.
(3) Counting lung area quantization parameters and marking lesion areas
The average density, the density variance, the maximum density, the minimum density and the like of the lung area or the designated area are conveniently and quickly calculated, and quantitative parameters such as the area, the volume, the distance, the angle and the like can be further used for marking the lesion area by specific colors.
Drawings
FIG. 1 is a schematic diagram of a computer-aided emphysema diagnosis system based on chest CT images;
FIG. 2 is a flow chart of the computer-aided emphysema diagnosis system based on chest CT images of the present invention;
FIG. 3 shows a slice image (a) and its histogram (b) of a CT image of a breast according to an embodiment of the present invention;
FIG. 4 is a lung region segmentation and contour tracking result according to an embodiment of the present invention, wherein (a) a global adaptive threshold segmentation result; (b) left and right contour tracking results; (c) the right and left lung parenchyma;
FIG. 5 is a diagram of an emphysema marker after quantitative analysis of lung regions, in accordance with an embodiment of the present invention, wherein (a) layer 4; (b) a 8 th layer; (c) a 12 th layer; (d) a 33 rd layer;
fig. 6 shows the volume fraction of emphysema calculated by quantitative analysis according to the embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but the embodiments of the present invention are not limited thereto.
As shown in fig. 1, the computer-aided emphysema diagnosis system based on the chest CT image of the present invention includes an input module 100, a lung region extracting module 200, a quantitative parameter calculating module 300, a classification diagnosis module 400, and an output module 500. Wherein,
the system comprises an input module (100) for inputting a chest CT image to be diagnosed and transmitting the chest CT image to a lung region extracting module (200);
the lung region extracting module (200) is used for automatically segmenting the left and right lung regions and transmitting the lung region information to the quantitative parameter calculating module (300);
a quantization parameter calculation module (300) for calculating statistical distribution information of pixel density of the lung region or the designated region and geometric information, and transmitting the quantization parameter to the classification diagnosis module (400) and the output module (500);
the classification diagnosis module (400) is used for analyzing the data transmitted by the quantitative parameter calculation module (300) and sending the analysis result to the output module (500);
and the output module (500) positions the analysis result of the classification diagnosis module (400) in the CT image of the breast to be diagnosed input by the user, marks suspicious places with a specific color and displays the analysis result to the user.
As shown in fig. 2, the present invention proceeds according to the following steps:
step (1) a group of breast CT tomograms to be diagnosed are input.
And (2) extracting the left lung area and the right lung area. As can be seen from the chest CT image and the histogram in fig. 3, the lung CT image mainly includes the trunk, the soft tissues of the chest wall, the lung parenchyma, the trachea, the bronchus, the mediastinum, the bed plate, the clothes, and the like. The gray level histogram has three main peaks, and is divided into three main areas: wherein the low density area is a black background with four corners; the middle density area is the lung parenchyma and the outer background of the trunk; the high density region is chest wall, mediastinum, trachea, bronchus, etc. The low density area, i.e. the black background, is typically the smallest fixed density value in the image, which can be easily removed with a simple threshold. If the boundary point between the two areas can be found, the image can be binarized by taking the boundary point as a threshold value, so that the background (the background outside the trunk of the medium-density area) is separated from the trunk.
And (2.1) separating the trunk from the background by adopting a global adaptive threshold method. Firstly, an initial threshold value is given (the density average value of the whole image can be selected according to the characteristics of the lung CT image), then the threshold value is gradually close to the optimal value through an iterative algorithm, and finally, the accurate threshold value is calculated to segment the image. The specific process is as follows:
the threshold is applied to divide the image into two types, the average density of the two types of objects is calculated respectively, the mean value of the two average densities is calculated and is used as a new threshold, then the image is classified, the difference between the threshold of two continuous times is compared, or whether the iteration number reaches the maximum value is judged, and whether the processing process is ended or not is determined. The process can be described as follows:
step (2.1.1) of selecting an initial estimated value T0Given a very small termination value t, and a maximum number of iterations Nmax；
Step (2.1.2) with T0Dividing the image into C as a threshold1And C2Two types are adopted;
step (2.1.3) for C1And C2Calculating the average density of all pixels in the image
Where f (-) is the image density,and
are respectively C1And C2The number of pixels of (a).
Step (2.1.4) calculating a new threshold
Step (2.1.5) of calculating the difference Δ T ═ T between successive quadratic thresholds1-T0If Δ T < T, or the number of iterations equals NmaxIf yes, ending; otherwise, the new threshold value T is set1Is given to T0And (5) repeating the steps (2.1.2) - (2.1.5).
Step (2.2) extracting the lung area contour by using a contour tracing method
The lung CT image is effectively divided into a trunk (white representation) and a background (black representation) through the processing of the step (2.1), so that the outer contour of the trunk is easily obtained, and the inner contour of the trunk, namely the outer contour of the lung, is required to be obtained because the lung parenchyma is positioned in the chest. The initial point may start from the middle of the trunk in the row direction, first find the first white point (trunk) from the left to the right direction, then start from this point, scan the row where this point is located from the left to the right direction until the first black point, i.e. the left lung contour point, and use this point as the starting point of contour tracing. Similarly, the right lung contours can be extracted from the outside-in, right-to-left direction.
The basic idea of the contour tracking method is to detect contour pixels in a target according to a certain 'detection criterion', and then find out other pixels of the target contour according to a certain tracking criterion based on certain characteristics of the pixels. The specific tracking process is described as follows:
step (2.1.1) finding out contour points at the lower left, and defining the initial search direction as the upper left;
step (2.1.2) if the upper left side is a black point, the boundary point is determined, otherwise, the search direction is rotated by 45 degrees clockwise until the first black point is found;
and (2.1.3) taking the black point as a new boundary point, rotating the new boundary point by 90 degrees anticlockwise in the current searching direction, and continuously searching the next black point by the same method until the initial contour point is returned.
And (2.3) acquiring the left lung area and the right lung area by using a boundary scanning and region filling method.
After the lung area boundary is determined, the extraction of the pixels in the lung area can be converted into the scanning conversion and area filling problems of polygons in computer graphics. The polygon scan conversion includes a scan line algorithm, an edge filling method, a barrier filling method, an edge mark filling algorithm, a seed filling method, and the like. Considering that it is a particular object of a chest CT image, the task is to extract and analyze pixels inside the region, and therefore, the present invention uses a 4 neighborhood based background labeling scan line method to acquire region pixels. The method mainly comprises the following steps:
and (2.1.1) solving a circumscribed rectangle of the region of interest to generate a minimum rectangular region capable of covering the selected region. Because the operation is only performed on the rectangular area, the calculation amount can be greatly reduced;
step (2.1.2) marking the boundary of the selected area in the rectangular area as '1', and marking the other areas as '0';
scanning a rectangular area from top to bottom and from left to right, if the current pixel is marked as '0', scanning from left to right from the current pixel on the current line, and juxtaposing the passed pixels as '-1' until a boundary point or the end of the line is reached;
step (2.1.4) searching 4 neighborhoods of the current pixel, finding a point marked as '0', taking the point as a new starting point, scanning from left to right, juxtaposing the passing pixel and marking as '-1' until the end of a boundary point or the line;
and (5) after the rectangular area scanning is finished, removing the pixels marked as "-1", namely the required area.
Thus, the automatic extraction process of the left and right lung regions is completed. Fig. 4 is a lung region extraction result of the image in fig. 3(a), wherein fig. 4(a) is a result after adaptive threshold segmentation, and the background and the torso are effectively separated; FIG. 4(b) is the left and right lung contours after contour tracing; fig. 4(c) shows the acquired right and left lung parenchyma.
Calculating quantitative parameters, namely calculating pixel density and geometric statistical information of the lung area or a designated arbitrary area, wherein the density parameters comprise average density, density variance and pixel percentage of which the density is greater than (less than or equal to) a given threshold value; the geometric parameters include volume, area of the region, perimeter, distance and angle, etc. Besides calculating the relevant parameters of the lung area, the invention also provides a user-defined arbitrary closed area and calculates the quantitative parameters of the area.
And (4) carrying out quantitative analysis and diagnosis, and carrying out classified diagnosis according to the quantitative diagnosis standard and the parameters obtained by calculation in the step (3).
The clinical quantitative diagnosis standard for emphysema based on CT image has been studied more at home and abroad, and the currently accepted method is lung function quantitative parameter method (H.M. John, M.D. Austin, "pulmonary imaging assessment of lung volume reduction surgery". Radiology, 212 (1): 1-3(1999), peony, "quantitative research progress of imaging emphysema", journal of practical Radiology, 22 (5): 610-. The average lung density reflects ventilation status, blood volume, extravascular fluid volume and comprehensive density of lung tissues, and research shows that the average density of emphysema is obviously lower than a normal value, the CT threshold deep inhalation phase is-953.3 HU, and the deep exhalation phase is-914.. 62 HU. There are two main quantification methods for lung volume: (1) determining the emphysema degree according to the reduction percentage of the respiratory two-phase lung volume; (2) analyzing and diagnosing according to the percentage (volume fraction) of an emphysema area in the whole lung, and in CT quantitative evaluation, respectively using-910 HU and-950 HU as threshold values to diagnose emphysema, namely classifying the emphysema according to the percentage of lung tissues with the density smaller than a specified threshold value in the whole lung, and regarding an inspiratory phase, using-950 HU as the threshold value, and using the volume fraction smaller than 5% as the emphysema level 0; [ 5%, 10%) is grade 1; [ 10%, 15%) is grade 2; volume fraction > 15% is grade 3 (threshold is-910 HU if expiratory phase). The emphysema volume fraction can also be used as an important index for disease observation, curative effect evaluation, lung volume reduction preoperative screening and postoperative evaluation. The invention realizes quantitative analysis and auxiliary diagnosis of lung CT images by counting emphysema volume fraction in a lung function quantitative parameter method.
After the left and right lung regions are obtained, the volume fraction method is applied to scan the lung region in each CT sectional image, each pixel in the lung region is compared with a specified density threshold value, the pixels which are respectively larger than, smaller than or equal to the specified threshold value are counted, and the percentage of the pixels which respectively occupy the whole lung region is calculated. And (4) determining whether the lung area is normal or not according to 5-grade diagnosis standards of the emphysema, and if the lung area is abnormal, grading.
And (3) positioning the classified diagnosis result on the CT image of the chest to be diagnosed input by the user, marking suspicious places with a specific color, displaying the analysis result to the user, and displaying the related parameters obtained by calculation in the step (3).
Fig. 5 shows that after the lung region is quantitatively analyzed, the key regions of 4 sectional images, namely emphysema, are marked with red color; fig. 6 shows the volume fraction of emphysema calculated by quantitative analysis in the embodiment of the present invention. Table 1 shows the parameters of the statistical output of the examples
The computer aided emphysema diagnosis system based on chest CT image provided by the invention, fig. 3-6 and table 1 illustrate the processing and analysis results of the embodiment and the relevant parameters of statistical output. In the auxiliary diagnosis system, when the lung area is segmented, a plurality of control parameters are involved, and the parameters are comprehensively adjusted and set according to specific data characteristics so as to optimize the system performance. The parameters set for processing the data set according to the invention are as follows:
the threshold initial estimated value T0 in step (2.1) is the image average density;
the end value t in step (2.1) is 0.01;
maximum number of iterations N in step (2.1)max＝500。
The invention automatically segments the chest CT image to be diagnosed by a computer-aided emphysema diagnosis system based on the chest CT image, rapidly and accurately extracts a lung region, analyzes and processes the lung region, and provides region-related density and geometric statistical parameters according to the requirements, thereby prompting a radiologist to focus on the region-related parameters needing to be focused on, and improving the accuracy and efficiency of the radiologist in emphysema diagnosis to a certain extent.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (7)
1. Emphysema computer-aided diagnosis system based on chest CT image, characterized by comprising:
the system comprises an input module (100) for inputting a chest CT image to be diagnosed and transmitting the chest CT image to a lung region extracting module (200);
the lung region extracting module (200) is used for automatically segmenting the left and right lung regions and transmitting the lung region information to the quantitative parameter calculating module (300);
a quantization parameter calculation module (300) for calculating statistical distribution information of pixel density of the lung region or the designated region and geometric information, and transmitting the quantization parameter to the classification diagnosis module (400) and the output module (500);
the classification diagnosis module (400) is used for analyzing the data transmitted by the quantitative parameter calculation module (300) and sending the analysis result to the output module (500);
and the output module (500) positions the analysis result of the classification diagnosis module (400) in the CT image of the breast to be diagnosed input by the user, marks suspicious places with a specific color and displays the analysis result to the user.
2. The computer-aided diagnosis system for emphysema based on CT images of chest as claimed in claim 1, wherein the module for extracting lung region (200) performs the following steps:
and (2.1) separating the trunk from the background in the chest CT image by adopting a global adaptive threshold method: firstly, an initial threshold value is given, and the threshold value is applied to divide the images into two types; then, calculating the mean value of the two average densities and taking the mean value as a new threshold value, classifying the images, gradually enabling the threshold value to approach an optimal value through an iterative algorithm, finally calculating an accurate threshold value, and separating the background from the trunk;
and (2.2) extracting the lung area contour by adopting a contour tracking method: firstly, detecting a pixel point of the left lung outline according to the density and the spatial position, then, sending out from the pixel point, and searching other pixel points of the target outline by using an outline tracking method until all pixel points of the left lung outline are found; similarly, all pixel points of the right lung contour can be obtained;
and (2.3) acquiring pixels in the left and right lung regions by adopting a background marking scanning line method based on 4 neighborhoods.
3. Computer-aided emphysema computer-aided diagnosis system based on CT images of chest as claimed in claim 2 wherein the initial threshold in step (2.1) selects the mean value of the density of the whole image.
4. Computer-aided diagnosis system for emphysema based on CT images of the chest according to claim 2, characterized in that said step (2.3) comprises the steps of:
step (2.3.1) solving a circumscribed rectangle of the region of interest to generate a minimum rectangular region capable of covering the selected region;
marking outline points of the lung in the rectangular area as '1', and marking other outline points as '0';
step (2.3.3) scanning a rectangular area from top to bottom and from left to right, if the current pixel is marked as '0', scanning from left to right from the current pixel on the current line, and juxtaposing the passed pixels as '-1' until the contour point or the line end;
step (2.3.4) searching 4 neighborhoods of the current pixel, finding a point marked as '0', taking the point as a new starting point, scanning from left to right, juxtaposing the passing pixel and marking as '-1' until the contour point or the end of the row is reached;
and (5) after the rectangular area scanning is finished, removing the pixels marked as "-1".
5. The computer-aided diagnosis system for emphysema based on CT images of chest of claim 4, wherein: the quantization parameters in the quantization parameter calculation module (300) comprise gray scale statistical parameters and geometric parameters, wherein the gray scale statistical parameters comprise average density, density variance and pixel percentage of which the density is less than, greater than or equal to a given threshold value of a left lung region and a right lung region or a user-specified region; the geometric parameters include: lung volume, area of area, perimeter, distance and angle.
6. The computer-aided emphysema computer-aided diagnosis system based on chest CT images as claimed in claim 5, wherein the classification diagnosis module (400) comprises a determination unit for determining whether emphysema exists or not according to quantitative diagnosis criteria for emphysema, and classifying emphysema if determined.
7. The computer-aided diagnosis system for emphysema based on CT images of chest of claim 6, wherein: a classification diagnosis module (400) which scans the lung area in each CT sectional image by using a volume fraction method according to the quantitative diagnosis standard of emphysema, compares each pixel in the lung area with a specified density threshold, counts the pixels which are respectively greater than, less than or equal to the specified threshold, and calculates the percentage of the pixels which respectively occupy the whole lung area; and determining whether the lung area is normal or not according to the classification diagnosis standard of the emphysema, and if the lung area is abnormal, classifying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102671651A CN102429679A (en) | 2011-09-09 | 2011-09-09 | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102671651A CN102429679A (en) | 2011-09-09 | 2011-09-09 | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102429679A true CN102429679A (en) | 2012-05-02 |
Family
ID=45978283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102671651A Pending CN102429679A (en) | 2011-09-09 | 2011-09-09 | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102429679A (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103892854A (en) * | 2012-12-28 | 2014-07-02 | 上海联影医疗科技有限公司 | Digital medical image processing method and device |
| CN103932727A (en) * | 2013-01-22 | 2014-07-23 | 上海理工大学 | Computer-aided diagnosis system based on CT image texture tactile sense |
| CN104573309A (en) * | 2013-10-24 | 2015-04-29 | 三星电子株式会社 | Apparatus and method for computer-aided diagnosis |
| CN105232081A (en) * | 2014-07-09 | 2016-01-13 | 无锡祥生医学影像有限责任公司 | Medical ultrasound assisted automatic diagnosis device and medical ultrasound assisted automatic diagnosis method |
| CN106384342A (en) * | 2015-07-24 | 2017-02-08 | 富士通株式会社 | Computer readable storage medium, apparatus, and method for image processing |
| JP2018151791A (en) * | 2017-03-10 | 2018-09-27 | 富士通株式会社 | Similar case image search program, similar case image search device, and similar case image search method |
| CN108742663A (en) * | 2018-04-03 | 2018-11-06 | 深圳蓝韵医学影像有限公司 | Exposure dose evaluation method, device and computer readable storage medium |
| CN108882907A (en) * | 2016-04-13 | 2018-11-23 | 日本医事物理股份有限公司 | Method, device and computer program for automatic estimation of bone region in CT image |
| CN109035283A (en) * | 2018-09-05 | 2018-12-18 | 中国医科大学附属盛京医院 | It is a kind of precisely to be detected and quantitative analysis method based on the pulmonary emphysema for randomly selecting subregion |
| CN109214397A (en) * | 2018-09-14 | 2019-01-15 | 郑州大学 | The dividing method of Lung neoplasm in a kind of lung CT image |
| CN109300122A (en) * | 2018-09-14 | 2019-02-01 | 沈阳东软医疗系统有限公司 | Image procossing and Threshold, device and equipment |
| CN109394268A (en) * | 2018-12-07 | 2019-03-01 | 余姚市华耀工具科技有限公司 | Polyp extent of injury Mapping Platform |
| CN109448822A (en) * | 2018-09-21 | 2019-03-08 | 沈阳医学院附属中心医院 | CT image pulmonary emphysema automatic marking method based on image report |
| CN109447969A (en) * | 2018-10-29 | 2019-03-08 | 北京青燕祥云科技有限公司 | Hepatic space occupying lesion recognition methods, device and realization device |
| CN109754394A (en) * | 2018-12-28 | 2019-05-14 | 上海联影智能医疗科技有限公司 | 3 d medical images processing unit and method |
| CN110176009A (en) * | 2019-05-23 | 2019-08-27 | 复旦大学 | A kind of segmentation of lung images and tracking and system |
| CN110211104A (en) * | 2019-05-23 | 2019-09-06 | 复旦大学 | A kind of image analysis method and system for pulmonary masses computer aided detection |
| CN110335281A (en) * | 2018-03-28 | 2019-10-15 | 北京连心医疗科技有限公司 | A kind of tumor boundaries determine method, equipment and storage medium |
| CN110349115A (en) * | 2019-07-04 | 2019-10-18 | 邃蓝智能科技(上海)有限公司 | CT image processing system |
| CN110533658A (en) * | 2019-09-02 | 2019-12-03 | 山东大学齐鲁医院 | Intelligent pulmonary emphysema diagnostic message processing system and method, information data processing terminal |
| CN110717915A (en) * | 2019-09-25 | 2020-01-21 | 武汉联影智融医疗科技有限公司 | Segmentation method, segmentation device, computer equipment and storage medium |
| CN111212591A (en) * | 2017-10-17 | 2020-05-29 | 富士胶片株式会社 | Medical image processing apparatus and endoscope apparatus |
| CN111242931A (en) * | 2020-01-15 | 2020-06-05 | 东北大学 | Method and device for judging small airway lesion of single lung lobe |
| CN111260627A (en) * | 2020-01-15 | 2020-06-09 | 东北大学 | Pulmonary lobe-based emphysema region judgment method and device |
| CN111477324A (en) * | 2020-04-03 | 2020-07-31 | 深圳前海微众银行股份有限公司 | Method, device, equipment and storage medium for emphysema disease prediction |
| CN111598853A (en) * | 2020-04-30 | 2020-08-28 | 科大讯飞股份有限公司 | Pneumonia-oriented CT image scoring method, device and equipment |
| CN111657985A (en) * | 2020-06-30 | 2020-09-15 | 杭州依图医疗技术有限公司 | Lung image information processing method, lung image information display method and readable storage medium |
| CN111739645A (en) * | 2020-05-14 | 2020-10-02 | 上海依智医疗技术有限公司 | Training method of immune-related pneumonia prediction model |
| CN111738980A (en) * | 2020-05-14 | 2020-10-02 | 上海依智医疗技术有限公司 | Medical image display method, computer equipment and storage medium |
| WO2020232998A1 (en) * | 2019-05-22 | 2020-11-26 | 平安国际智慧城市科技股份有限公司 | Medical image evaluation method and apparatus, computer device and storage medium |
| CN112150406A (en) * | 2019-06-28 | 2020-12-29 | 复旦大学 | CT image-based pneumothorax lung collapse degree accurate calculation method |
| CN112190277A (en) * | 2020-11-09 | 2021-01-08 | 华中科技大学同济医学院附属协和医院 | Data fitting method for CT reexamination of new coronary pneumonia |
| CN113096139A (en) * | 2021-04-14 | 2021-07-09 | 上海市第一人民医院 | Image segmentation processing method for lung parenchyma |
| CN113425319A (en) * | 2020-03-08 | 2021-09-24 | 广东毓秀科技有限公司 | Respiratory system disease intelligent auxiliary diagnosis decision-making method for basic medical institution |
| CN113469934A (en) * | 2020-03-31 | 2021-10-01 | 西门子医疗有限公司 | Assessment of abnormal regions associated with disease from chest CT images |
| US11341734B2 (en) | 2018-12-17 | 2022-05-24 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for image segmentation |
| CN115281695A (en) * | 2021-05-03 | 2022-11-04 | 通用电气精准医疗有限责任公司 | Method and system for robust intensity range for automated lesion volume measurement |
| CN115761034A (en) * | 2022-12-15 | 2023-03-07 | 中国科学院精密测量科学与技术创新研究院 | Method for generating lung CT density difference image |
| CN116229091A (en) * | 2022-12-12 | 2023-06-06 | 东软医疗系统股份有限公司 | CT data processing method, device, storage medium and computer equipment |
| CN116958151A (en) * | 2023-09-21 | 2023-10-27 | 中国医学科学院北京协和医院 | Method, system and equipment for distinguishing adrenal hyperplasia from fat-free adenoma based on CT image characteristics |
| CN117218150A (en) * | 2023-09-12 | 2023-12-12 | 厦门大学 | Quantitative analysis method for the degree of white spot infection in the spleen of large yellow croaker based on machine learning |
| CN119606409A (en) * | 2024-11-26 | 2025-03-14 | 北京大学第三医院（北京大学第三临床医学院） | A lung lesion analysis system based on parameter response graph and image generation system |
| CN117218150B (en) * | 2023-09-12 | 2026-02-13 | 厦门大学 | A Machine Learning-Based Method for Quantitative Analysis of White Spot Infection Degree in Spleen of Large Yellow Croaker |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101103924A (en) * | 2007-07-13 | 2008-01-16 | 华中科技大学 | Breast cancer computer-aided diagnosis method and system based on mammography |
-
2011
- 2011-09-09 CN CN2011102671651A patent/CN102429679A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101103924A (en) * | 2007-07-13 | 2008-01-16 | 华中科技大学 | Breast cancer computer-aided diagnosis method and system based on mammography |
Non-Patent Citations (4)
| Title |
|---|
| 薛以锋等: "基于CT图像的肺结节计算机辅助诊断系统", 《中国医学物理学杂志》 * |
| 郭圣文等: "胸部CT中肺实质的提取与辅助诊断", 《中国生物医学工程学报》 * |
| 郭圣文等: "胸部CT中肺实质的自动分割与计算机辅助诊断", 《华南理工大学学报（自然科学版）》 * |
| 陈坚等: "胸部CT图像中感兴趣区域的提取与量化分析", 《中国医学物理学杂志》 * |
Cited By (65)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103892854A (en) * | 2012-12-28 | 2014-07-02 | 上海联影医疗科技有限公司 | Digital medical image processing method and device |
| CN103932727A (en) * | 2013-01-22 | 2014-07-23 | 上海理工大学 | Computer-aided diagnosis system based on CT image texture tactile sense |
| US10147223B2 (en) | 2013-10-24 | 2018-12-04 | Samsung Electronics Co., Ltd. | Apparatus and method for computer-aided diagnosis |
| CN104573309A (en) * | 2013-10-24 | 2015-04-29 | 三星电子株式会社 | Apparatus and method for computer-aided diagnosis |
| CN104573309B (en) * | 2013-10-24 | 2019-07-19 | 三星电子株式会社 | Device and method for computer-aided diagnosis |
| CN105232081A (en) * | 2014-07-09 | 2016-01-13 | 无锡祥生医学影像有限责任公司 | Medical ultrasound assisted automatic diagnosis device and medical ultrasound assisted automatic diagnosis method |
| CN106384342A (en) * | 2015-07-24 | 2017-02-08 | 富士通株式会社 | Computer readable storage medium, apparatus, and method for image processing |
| CN106384342B (en) * | 2015-07-24 | 2019-10-25 | 富士通株式会社 | Apparatus and method for image processing |
| CN108882907A (en) * | 2016-04-13 | 2018-11-23 | 日本医事物理股份有限公司 | Method, device and computer program for automatic estimation of bone region in CT image |
| JP2018151791A (en) * | 2017-03-10 | 2018-09-27 | 富士通株式会社 | Similar case image search program, similar case image search device, and similar case image search method |
| US11574401B2 (en) | 2017-10-17 | 2023-02-07 | Fujifilm Corporation | Medical image processing apparatus and endoscope apparatus |
| CN111212591B (en) * | 2017-10-17 | 2022-08-02 | 富士胶片株式会社 | Medical image processing apparatus and endoscope apparatus |
| CN111212591A (en) * | 2017-10-17 | 2020-05-29 | 富士胶片株式会社 | Medical image processing apparatus and endoscope apparatus |
| CN110335281A (en) * | 2018-03-28 | 2019-10-15 | 北京连心医疗科技有限公司 | A kind of tumor boundaries determine method, equipment and storage medium |
| CN108742663A (en) * | 2018-04-03 | 2018-11-06 | 深圳蓝韵医学影像有限公司 | Exposure dose evaluation method, device and computer readable storage medium |
| CN109035283B (en) * | 2018-09-05 | 2021-03-30 | 中国医科大学附属盛京医院 | A method for accurate detection and quantitative analysis of emphysema based on randomly selected partitions |
| CN109035283A (en) * | 2018-09-05 | 2018-12-18 | 中国医科大学附属盛京医院 | It is a kind of precisely to be detected and quantitative analysis method based on the pulmonary emphysema for randomly selecting subregion |
| CN109300122A (en) * | 2018-09-14 | 2019-02-01 | 沈阳东软医疗系统有限公司 | Image procossing and Threshold, device and equipment |
| CN109214397A (en) * | 2018-09-14 | 2019-01-15 | 郑州大学 | The dividing method of Lung neoplasm in a kind of lung CT image |
| CN109300122B (en) * | 2018-09-14 | 2023-04-07 | 东软医疗系统股份有限公司 | Image processing and threshold determining method, device and equipment |
| US11478163B2 (en) | 2018-09-14 | 2022-10-25 | Neusoft Medical Systems Co., Ltd. | Image processing and emphysema threshold determination |
| CN109448822A (en) * | 2018-09-21 | 2019-03-08 | 沈阳医学院附属中心医院 | CT image pulmonary emphysema automatic marking method based on image report |
| CN109447969B (en) * | 2018-10-29 | 2021-08-10 | 北京青燕祥云科技有限公司 | Liver occupation lesion identification method and device and implementation device |
| CN109447969A (en) * | 2018-10-29 | 2019-03-08 | 北京青燕祥云科技有限公司 | Hepatic space occupying lesion recognition methods, device and realization device |
| CN109394268A (en) * | 2018-12-07 | 2019-03-01 | 余姚市华耀工具科技有限公司 | Polyp extent of injury Mapping Platform |
| CN109394268B (en) * | 2018-12-07 | 2021-05-11 | 刘志红 | Polyp harm degree mapping platform |
| US11836925B2 (en) | 2018-12-17 | 2023-12-05 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for image segmentation |
| US11341734B2 (en) | 2018-12-17 | 2022-05-24 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for image segmentation |
| CN109754394A (en) * | 2018-12-28 | 2019-05-14 | 上海联影智能医疗科技有限公司 | 3 d medical images processing unit and method |
| CN109754394B (en) * | 2018-12-28 | 2021-02-23 | 上海联影智能医疗科技有限公司 | Three-dimensional medical image processing device and method |
| WO2020232998A1 (en) * | 2019-05-22 | 2020-11-26 | 平安国际智慧城市科技股份有限公司 | Medical image evaluation method and apparatus, computer device and storage medium |
| CN110211104B (en) * | 2019-05-23 | 2023-01-06 | 复旦大学 | Image analysis method and system for computer-aided detection of lung mass |
| CN110176009B (en) * | 2019-05-23 | 2023-03-07 | 复旦大学 | A lung image segmentation and tracking method and system |
| CN110176009A (en) * | 2019-05-23 | 2019-08-27 | 复旦大学 | A kind of segmentation of lung images and tracking and system |
| CN110211104A (en) * | 2019-05-23 | 2019-09-06 | 复旦大学 | A kind of image analysis method and system for pulmonary masses computer aided detection |
| CN112150406A (en) * | 2019-06-28 | 2020-12-29 | 复旦大学 | CT image-based pneumothorax lung collapse degree accurate calculation method |
| CN110349115A (en) * | 2019-07-04 | 2019-10-18 | 邃蓝智能科技(上海)有限公司 | CT image processing system |
| CN110533658A (en) * | 2019-09-02 | 2019-12-03 | 山东大学齐鲁医院 | Intelligent pulmonary emphysema diagnostic message processing system and method, information data processing terminal |
| CN110717915A (en) * | 2019-09-25 | 2020-01-21 | 武汉联影智融医疗科技有限公司 | Segmentation method, segmentation device, computer equipment and storage medium |
| CN111242931A (en) * | 2020-01-15 | 2020-06-05 | 东北大学 | Method and device for judging small airway lesion of single lung lobe |
| CN111242931B (en) * | 2020-01-15 | 2023-08-22 | 东北大学 | A single lobe small airway lesion judgment method and device |
| CN111260627A (en) * | 2020-01-15 | 2020-06-09 | 东北大学 | Pulmonary lobe-based emphysema region judgment method and device |
| CN113425319A (en) * | 2020-03-08 | 2021-09-24 | 广东毓秀科技有限公司 | Respiratory system disease intelligent auxiliary diagnosis decision-making method for basic medical institution |
| CN113469934A (en) * | 2020-03-31 | 2021-10-01 | 西门子医疗有限公司 | Assessment of abnormal regions associated with disease from chest CT images |
| CN111477324A (en) * | 2020-04-03 | 2020-07-31 | 深圳前海微众银行股份有限公司 | Method, device, equipment and storage medium for emphysema disease prediction |
| CN111477324B (en) * | 2020-04-03 | 2025-05-27 | 深圳前海微众银行股份有限公司 | Emphysema disease prediction method, device, equipment and storage medium |
| CN111598853A (en) * | 2020-04-30 | 2020-08-28 | 科大讯飞股份有限公司 | Pneumonia-oriented CT image scoring method, device and equipment |
| CN111598853B (en) * | 2020-04-30 | 2024-02-13 | 讯飞医疗科技股份有限公司 | CT image scoring methods, devices and equipment for pneumonia |
| CN111738980A (en) * | 2020-05-14 | 2020-10-02 | 上海依智医疗技术有限公司 | Medical image display method, computer equipment and storage medium |
| CN111739645B (en) * | 2020-05-14 | 2024-01-30 | 北京深睿博联科技有限责任公司 | Training method of immune-related pneumonia prediction model |
| CN111739645A (en) * | 2020-05-14 | 2020-10-02 | 上海依智医疗技术有限公司 | Training method of immune-related pneumonia prediction model |
| CN111738980B (en) * | 2020-05-14 | 2023-08-04 | 北京深睿博联科技有限责任公司 | Medical image display method, computer equipment and storage medium |
| CN111657985A (en) * | 2020-06-30 | 2020-09-15 | 杭州依图医疗技术有限公司 | Lung image information processing method, lung image information display method and readable storage medium |
| CN112190277A (en) * | 2020-11-09 | 2021-01-08 | 华中科技大学同济医学院附属协和医院 | Data fitting method for CT reexamination of new coronary pneumonia |
| CN113096139B (en) * | 2021-04-14 | 2022-09-06 | 上海市第一人民医院 | Image segmentation processing method for lung parenchyma |
| CN113096139A (en) * | 2021-04-14 | 2021-07-09 | 上海市第一人民医院 | Image segmentation processing method for lung parenchyma |
| CN115281695A (en) * | 2021-05-03 | 2022-11-04 | 通用电气精准医疗有限责任公司 | Method and system for robust intensity range for automated lesion volume measurement |
| CN116229091A (en) * | 2022-12-12 | 2023-06-06 | 东软医疗系统股份有限公司 | CT data processing method, device, storage medium and computer equipment |
| CN115761034A (en) * | 2022-12-15 | 2023-03-07 | 中国科学院精密测量科学与技术创新研究院 | Method for generating lung CT density difference image |
| CN115761034B (en) * | 2022-12-15 | 2025-05-09 | 中国科学院精密测量科学与技术创新研究院 | A method for generating lung CT density difference map |
| CN117218150A (en) * | 2023-09-12 | 2023-12-12 | 厦门大学 | Quantitative analysis method for the degree of white spot infection in the spleen of large yellow croaker based on machine learning |
| CN117218150B (en) * | 2023-09-12 | 2026-02-13 | 厦门大学 | A Machine Learning-Based Method for Quantitative Analysis of White Spot Infection Degree in Spleen of Large Yellow Croaker |
| CN116958151A (en) * | 2023-09-21 | 2023-10-27 | 中国医学科学院北京协和医院 | Method, system and equipment for distinguishing adrenal hyperplasia from fat-free adenoma based on CT image characteristics |
| CN116958151B (en) * | 2023-09-21 | 2023-12-12 | 中国医学科学院北京协和医院 | Method, system and equipment for distinguishing adrenal hyperplasia from fat-free adenoma based on CT image characteristics |
| CN119606409A (en) * | 2024-11-26 | 2025-03-14 | 北京大学第三医院（北京大学第三临床医学院） | A lung lesion analysis system based on parameter response graph and image generation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102429679A (en) | Computer-assisted emphysema analysis system based on chest CT (Computerized Tomography) image | |
| CN109583440B (en) | Medical image auxiliary diagnosis method and system combining image recognition and report editing | |
| CN109035283B (en) | A method for accurate detection and quantitative analysis of emphysema based on randomly selected partitions | |
| Campadelli et al. | A fully automated method for lung nodule detection from postero-anterior chest radiographs | |
| CN101763644B (en) | Pulmonary nodule three-dimensional segmentation and feature extraction method and system thereof | |
| CN112819747B (en) | A method for automatically diagnosing benign and malignant nodules based on lung tomography images | |
| Mesanovic et al. | Automatic CT image segmentation of the lungs with region growing algorithm | |
| Abd-Elaziz et al. | Liver tumors segmentation from abdominal CT images using region growing and morphological processing | |
| CN111374712B (en) | A kind of ultrasonic imaging method and ultrasonic imaging equipment | |
| Pulagam et al. | Automated lung segmentation from HRCT scans with diffuse parenchymal lung diseases | |
| CN113706435A (en) | Chest enhanced CT image processing method based on traditional image omics | |
| CN108062749B (en) | Recognition method, device and electronic device for levator hiatus | |
| CN104182755A (en) | Mammary gland molybdenum target X-ray image block feature extraction method based on tower-shaped principal component analysis (PCA) | |
| Gao et al. | Accurate lung segmentation for X-ray CT images | |
| US20150065868A1 (en) | System, method, and computer accessible medium for volumetric texture analysis for computer aided detection and diagnosis of polyps | |
| CN116403211A (en) | Segmentation and clustering method and system based on single-cell pathology image cell nuclei | |
| CN113838020B (en) | Lesion area quantification method based on molybdenum target image | |
| Maitra et al. | Automated digital mammogram segmentation for detection of abnormal masses using binary homogeneity enhancement algorithm | |
| CN117876833A (en) | A lung CT image feature extraction method for machine learning | |
| Maitra et al. | Detection of abnormal masses using divide and conquer algorithmin digital mammogram | |
| CN118941812B (en) | Automatic knee joint lesion feature interpretation method and system based on medical image | |
| CN118154975B (en) | Tumor pathological diagnosis image classification method based on big data | |
| Junior et al. | Evaluating margin sharpness analysis on similar pulmonary nodule retrieval | |
| Devaki et al. | A novel approach to detect fissures in lung CT images using marker-based watershed transformation | |
| Devaki et al. | Study of computed tomography images of the lungs: A survey |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120502 |
|
| RJ01 | Rejection of invention patent application after publication |