A CT image-assisted reading method for the reexamination stage after chemotherapy

Abstract

The present invention relates to the technical field of image enhancement, and particularly relates to a method for assisting in reading CT images during the follow-up examination stage after chemotherapy. The method includes: acquiring CT images before and after chemotherapy; dividing regions of a first image to be enhanced and a second image to be enhanced; determining the matching degree between each first region and each second region; performing region matching screening according to the matching degree between the first region and the second region; determining the tumor manifestation degree and blood vessel manifestation degree corresponding to each region in each target matching pair; determining the true recovery manifestation degree under each target matching pair according to the difference between the tumor manifestation degrees corresponding to the two regions in each target matching pair and the difference between the blood vessel manifestation degrees; performing histogram equalization on the first image to be enhanced and the second image to be enhanced according to the true recovery manifestation degrees under all target matching pairs. The present invention realizes the enhancement of CT images and improves the effect of enhancing CT images.

Description

Technical Field

[0001] The present invention relates to the technical field of image enhancement, and particularly relates to a method for assisting in reading CT images during the postoperative review stage of chemotherapy. Background Art

[0002] With the development of technology, the application of image enhancement technology is becoming more and more extensive. For example, it can be used to enhance the CT images required during the postoperative review stage of chemotherapy to assist doctors in reading the images. Currently, when performing image enhancement, the commonly used method is: according to the grayscale histogram of the image, perform histogram equalization on the image to achieve image enhancement. Among them, histogram equalization is also known as grayscale histogram equalization.

[0003] However, when performing histogram equalization on a CT image according to its grayscale histogram to achieve image enhancement, the following technical problems often exist:

[0004] Since grayscale histogram equalization often performs statistical image enhancement according to the grayscale value distribution of the image, when directly performing histogram equalization on a CT image according to its grayscale histogram, it may cause the loss of detailed information with fewer pixel points, resulting in a poor effect of enhancing the CT image. Summary of the Invention

[0005] In order to solve the technical problem of poor effect in enhancing CT images, the present invention proposes a method for assisting in reading CT images during the postoperative review stage of chemotherapy.

[0006] In a first aspect, the present invention provides a method for assisting in reading CT images during the postoperative review stage of chemotherapy, the method comprising:

[0007] Obtain the CT images before and after chemotherapy as the first image to be enhanced and the second image to be enhanced respectively;

[0008] Perform region division on the first image to be enhanced to obtain a first region, and perform region division on the second image to be enhanced to obtain a second region;

[0009] Determine the matching degree between each first region and each second region according to the distance and grayscale distribution difference between each first region and each second region;

[0010] Perform region matching screening according to the matching degree between the first region and the second region to obtain target matching pairs representing changes before and after surgery;

[0011] According to the grayscale distribution of the pre-extracted connected domains in each region of each target matching pair, obtain the tumor manifestation degree corresponding to each region of each target matching pair;

[0012] According to the characteristics of the pre-extracted skeletons in the connected regions within each region of each target matching pair, determine the vascular manifestation degree corresponding to each region in each target matching pair;

[0013] According to the difference between the tumor manifestation degrees corresponding to the two regions in each target matching pair, and the difference between the corresponding vascular manifestation degrees, determine the true recovery manifestation degree under each target matching pair;

[0014] Perform histogram equalization on the first image to be enhanced and the second image to be enhanced according to the true recovery manifestation degrees under all target matching pairs.

[0015] Combined with the above first aspect, in a possible implementation manner, the determining the matching degree between each first region and each second region according to the distance and gray-scale distribution difference between each first region and each second region includes:

[0016] Determine any one of the first regions as the marked region and any one of the second regions as the reference region;

[0017] Determine the region in the second image to be enhanced with the same position as the marked region as the position representative region;

[0018] Determine the distance between the center point of the reference region and the center point of the position representative region as the target distance between the marked region and the reference region;

[0019] Determine the absolute value of the difference between the gray-scale values of the pixel points corresponding to the same positions within the reference region and within the position representative region as the target gray-scale difference, and obtain the set of target gray-scale differences between the reference region and the position representative region;

[0020] According to the set of target gray-scale differences between the reference region and the position representative region, determine the target gray-scale distribution difference between the reference region and the position representative region, where the target gray-scale differences in the set of target gray-scale differences are positively correlated with the target gray-scale distribution difference;

[0021] According to the target gray-scale distribution difference and the target distance between the reference region and the position representative region, determine the matching degree between the reference region and the position representative region, where both the target gray-scale distribution difference and the target distance are negatively correlated with the matching degree.

[0022] Combined with the above first aspect, in a possible implementation manner, the determining the target gray-scale distribution difference between the reference region and the position representative region according to the set of target gray-scale differences between the reference region and the position representative region includes:

[0023] Determine the mean of all target gray-scale differences in the set of target gray-scale differences between the reference region and the position representative region as the target gray-scale distribution difference between the reference region and the position representative region.

[0024] Combined with the first aspect above, in a possible implementation manner, the performing region matching screening according to the matching degree between the first region and the second region to obtain a target matching pair representing the change before and after surgery includes:

[0025] Determine any one of the first regions as a marked region, and screen out the second regions with the same position as the marked region from all the second regions as the matching reference regions corresponding to the marked region;

[0026] Constitute the reference matching pair corresponding to the marked region by the marked region and its corresponding matching reference region, and determine the matching degree between the two regions in the reference matching pair as the target matching index of the reference matching pair;

[0027] Screen out the reference matching pairs with the target matching index less than the preset matching change threshold from the reference matching pairs corresponding to all the first regions as the target matching pairs.

[0028] Combined with the first aspect above, in a possible implementation manner, the obtaining the tumor manifestation degree corresponding to each region in each target matching pair according to the gray-scale distribution of the connected regions pre-extracted in each region in each target matching pair includes:

[0029] Determine any one of the regions in any one of the target matching pairs as a candidate region, and perform connected region extraction on the candidate region;

[0030] Determine any one of the connected regions in the candidate region as a marked connected region, and determine the mean of the gray-scale values corresponding to all the pixel points in the marked connected region as the gray-scale representative factor corresponding to the marked connected region;

[0031] Determine the chain code corresponding to each pixel point on the edge of the marked connected region through the eight-chain code algorithm to obtain the chain code sequence corresponding to the marked connected region;

[0032] Determine the difference between every two adjacent chain codes in the chain code sequence corresponding to the marked connected region as the target difference to obtain the target difference sequence corresponding to the marked connected region;

[0033] Determine the variance of all the target differences in the target difference sequence corresponding to the marked connected region as the edge clutter degree corresponding to the marked connected region;

[0034] Normalize the product of the grayscale representative factor and the edge clutter degree corresponding to the labeled connected region to obtain the tumor suspicion index corresponding to the labeled connected region;

[0035] Determine the mean value of the tumor suspicion indices corresponding to all connected regions within the candidate region as the tumor manifestation degree corresponding to the candidate region.

[0036] Combined with the above first aspect, in a possible implementation manner, the determining the blood vessel manifestation degree corresponding to each region in each target matching pair according to the characteristics of the pre-extracted skeletons in the connected regions within each region in each target matching pair includes:

[0037] Determine any region in any target matching pair as a candidate region, and perform skeleton extraction on all connected regions within the candidate region;

[0038] Using the intersection points of all skeletons within the candidate region as segmentation points, segment all skeletons within the candidate region to obtain skeleton branches;

[0039] Using the normal lines at the two end points of each skeleton branch as cutting lines, segment the connected region to which each skeleton branch belongs to obtain sub-regions corresponding to each skeleton branch;

[0040] Construct the intersection point set corresponding to each pixel point on each skeleton branch by using all intersection points between the normal line of each pixel point on each skeleton branch and the edge of its corresponding sub-region;

[0041] Determine the mean value of the distances between all intersection points in the intersection point set corresponding to each pixel point on each skeleton branch as the representative distance factor corresponding to each pixel point on each skeleton branch;

[0042] Determine the extensibility factor corresponding to each skeleton branch according to the grayscale values and the representative distance factors corresponding to all pixel points on each skeleton branch;

[0043] Perform threshold segmentation on each region in each target matching pair to obtain the foreground region and the background region corresponding to each region in each target matching pair;

[0044] Determine the blood vessel manifestation degree corresponding to each region in each target matching pair according to the grayscale difference between the foreground region and the background region corresponding to each region in each target matching pair, and the extensibility factors corresponding to all skeleton branches within each region in each target matching pair.

[0045] Combined with the above first aspect, in a possible implementation manner, the determining the extensibility factor corresponding to each skeleton branch according to the grayscale values and the representative distance factors corresponding to all pixel points on each skeleton branch includes:

[0046] Multiply the gray value corresponding to each pixel on each skeleton branch by the distance factor, and determine it as the width gray factor corresponding to each pixel on each skeleton branch;

[0047] Take the difference between the width gray factors corresponding to every two adjacent pixels on each skeleton branch as the width gray difference, and obtain the width gray difference set corresponding to each skeleton branch;

[0048] Take the absolute value of the cumulative value of all width gray differences in the width gray difference set corresponding to each skeleton branch as the width gray representative difference corresponding to each skeleton branch;

[0049] Take the variance of all width gray differences in the width gray difference set corresponding to each skeleton branch as the width gray change factor corresponding to each skeleton branch;

[0050] Determine the extensibility factor corresponding to each skeleton branch according to the width gray representative difference and the width gray change factor corresponding to each skeleton branch, where the width gray representative difference is positively correlated with the extensibility factor, and the width gray change factor is negatively correlated with the extensibility factor.

[0051] Combined with the above first aspect, in a possible implementation manner, the formula for the blood vessel manifestation degree corresponding to the region in the target matching pair is:

[0052] ;

[0053] ; where is the blood vessel manifestation degree corresponding to the th region in the th target matching pair; is the serial number of the target matching pair; is the serial number of the region in the th target matching pair; is the normalization function; is the th target matching pair, and is the cumulative value of the extensibility factors corresponding to all skeleton branches in the th region; characterizes the disorder situation of the th region in the th target matching pair; is the absolute value function; is the th target matching pair, and is the mean value of the gray values corresponding to all pixels in the foreground region of the th region in the The average of the gray values corresponding to all pixel points in the background area of the th area in a target matching pair; is the number of skeleton branches in the th area in the th target matching pair; is the serial number of the skeleton branch in the th area in the th target matching pair; is the variance of the chain codes corresponding to all pixel points on the th skeleton branch in the th area in the th target matching pair; the chain codes corresponding to the pixel points are obtained by the eight-chain code algorithm.

[0054] Combined with the first aspect above, in a possible implementation, the formula for the true recovery performance corresponding to a target matching pair is:

[0055] ;

[0056] ;

[0057] ; where is the true recovery performance under the th target matching pair; is the serial number of the target matching pair; is the normalization function; represents the tumor elimination situation under the th target matching pair; represents the local recovery situation under the th target matching pair; is the tumor performance corresponding to the first area in the th target matching pair; is the tumor performance corresponding to the second area in the th target matching pair; is the blood vessel performance corresponding to the second area in the th target matching pair; is the blood vessel performance corresponding to the first area in the th target matching pair.

[0058] Combined with the first aspect above, in a possible implementation, the histogram equalization of the first image to be enhanced and the second image to be enhanced according to the true recovery performance under all target matching pairs includes:

[0059] Determine the true recovery performance factor corresponding to each first area by using the true recovery performance under the target matching pair to which each first area belongs;

[0060] Adjust the grayscale histogram of the first image to be enhanced according to the true recovery performance factors corresponding to all the first regions to obtain a first target histogram;

[0061] Determine the true recovery performance degree under each target matching pair to which each second region belongs as the true recovery performance factor corresponding to each second region;

[0062] Adjust the grayscale histogram of the second image to be enhanced according to the true recovery performance factors corresponding to all the second regions to obtain a second target histogram;

[0063] Perform histogram equalization on the first image to be enhanced and the second image to be enhanced respectively according to the first target histogram and the second target histogram.

[0064] In a second aspect, the present invention provides a CT image assisted reading system for the postoperative review stage of chemotherapy, and the system includes:

[0065] A CT image acquisition module for acquiring CT images before and after chemotherapy as the first image to be enhanced and the second image to be enhanced respectively;

[0066] A region division module for dividing the first image to be enhanced to obtain first regions, and dividing the second image to be enhanced to obtain second regions;

[0067] A matching degree determination module for determining the matching degree between each first region and each second region according to the distance and grayscale distribution difference between each first region and each second region;

[0068] A region matching and screening module for performing region matching and screening according to the matching degree between the first region and the second region to obtain target matching pairs representing changes before and after surgery;

[0069] A tumor manifestation degree determination module for obtaining the tumor manifestation degree corresponding to each region in each target matching pair according to the grayscale distribution of the pre-extracted connected regions in each region of each target matching pair;

[0070] A blood vessel manifestation degree determination module for determining the blood vessel manifestation degree corresponding to each region in each target matching pair according to the characteristics of the pre-extracted skeletons in the connected regions in each region of each target matching pair;

[0071] A true recovery performance degree determination module for determining the true recovery performance degree under each target matching pair according to the difference between the tumor manifestation degrees corresponding to the two regions in each target matching pair and the difference between the corresponding blood vessel manifestation degrees;

[0072] A histogram equalization module is used to perform histogram equalization on the first image to be enhanced and the second image to be enhanced according to the true recovery performance under all target matching pairs.

[0073] In a third aspect, a server is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes the method in the above first aspect or any possible implementation manner of the first aspect.

[0074] In a fourth aspect, a computer program product is provided, which includes: computer program code. When the computer program code runs on a computer, the computer is made to execute the method in the above first aspect or any possible implementation manner of the first aspect.

[0075] In a fifth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores computer program code. When the computer program code runs on a computer, the computer is made to execute the method in the above first aspect or any possible implementation manner of the first aspect.

[0076] The present invention has the following beneficial effects:

[0077] A CT image assisted reading method in the postoperative review stage of chemotherapy of the present invention realizes the enhancement of CT images, solves the technical problem of poor enhancement effect of CT images, and thus improves the enhancement effect of CT images. Compared with directly performing histogram equalization on CT images according to the gray histogram of CT images, the present invention comprehensively considers multiple indicators related to the detailed information of the disease recovery of CT images, such as the matching degree between regions in different CT images, tumor manifestation, blood vessel manifestation, and true recovery performance, thereby improving the retention degree of detailed information and further improving the enhancement effect of CT images. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0079] Figure 1 It is a flowchart of a CT image assisted reading method in the postoperative review stage of chemotherapy of the present invention;

[0080] Figure 2Schematic diagram of regions at the same position in the first image to be enhanced and the second image to be enhanced of the present invention;

[0081] Figure 3 Schematic diagram of the composition structure of a CT image-assisted film reading system in the postoperative review stage of chemotherapy according to the present invention;

[0082] Figure 4 Schematic diagram of the structure of a computer device according to the present invention.

[0083] Among them, the reference numerals include: the first image to be enhanced 201, the second image to be enhanced 202, the marked region 203, and the square region 204. Detailed implementation manners

[0084] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following describes in detail the specific implementation manners, structures, features, and effects of the technical solutions proposed according to the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0085] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0086] Refer to Figure 1 , which shows the flow of some embodiments of a CT image-assisted film reading method in the postoperative review stage of chemotherapy according to the present invention. The CT image-assisted film reading method in the postoperative review stage of chemotherapy includes the following steps:

[0087] Step S1, obtain the CT images before and after chemotherapy, and use them as the first image to be enhanced and the second image to be enhanced respectively.

[0088] Among them, chemotherapy, also often referred to as chemical therapy, is a treatment strategy for killing tumor cells, and its working mode is to inhibit tumor growth or eliminate tumors by using chemical drugs systemically or partially. For example, chemotherapy can be used for the treatment of lung cancer. The CT image can be an image collected by a CT (Computed Tomography) machine. In the embodiments of the present invention, the patient parts photographed by the CT images before and after chemotherapy can be the same.

[0089] It should be noted that CT technology has a wide range of applications in the medical and industrial fields, mainly used for diagnostic imaging, guiding treatment, surgical planning and navigation, etc. In the review stage of chemotherapy, CT scans can help doctors evaluate the effectiveness of chemotherapy. Specifically, it can be used to compare the size, morphological changes and density changes of tumors before and after treatment. During the process of doctors reading images, since chemotherapy may cause some tumor areas to become smaller, it may be difficult for doctors to detect them, and thus may lead to poor efficiency in doctors' image reading. Therefore, in the embodiments of the present invention, by enhancing the CT images before and after chemotherapy, the clarity of the changed lesion areas is enhanced to a certain extent, thereby improving the image enhancement effect.

[0090] As an example, taking chemotherapy for lung cancer treatment as an example, the lung CT image of a patient before chemotherapy surgery can be collected by a CT machine as the first image to be enhanced, and the lung CT image of the patient after chemotherapy surgery can be collected by a CT machine as the second image to be enhanced.

[0091] Step S2: Divide the first image to be enhanced to obtain the first region, and divide the second image to be enhanced to obtain the second region.

[0092] Among them, the shapes and sizes between the first region and the second region can be the same.

[0093] As an example, the first image to be enhanced can be equally divided, and each region obtained by equal division at this time is used as the first region; similarly, the second image to be enhanced is equally divided in the same way, and each region obtained by equal division at this time is used as the second region. Among them, the size of the first region and the size of the second region can both be 21×21.

[0094] Step S3: Determine the matching degree between each first region and each second region according to the distance and gray level distribution difference between each first region and each second region.

[0095] As an example, this step may include the following steps:

[0096] The first step: Determine any one of the first regions as the marked region, and determine any one of the second regions as the reference region.

[0097] The second step: Determine the region with the same position as the marked region in the second image to be enhanced as the position representative region.

[0098] For example, as Figure 2 shown, the marked region 203 is any one of the first regions in the first image to be enhanced 201; the square region 204 can be the region with the same position as the marked region 203 in the second image to be enhanced 202, that is, the position representative region.

[0099] In the third step, the distance between the center point of the reference area and the center point of the position representative area is determined as the target distance between the marked area and the reference area.

[0100] In the fourth step, the absolute value of the difference between the grayscale values ​​corresponding to the pixel points at the same position in the reference area and the position representative area is determined as the target grayscale difference, and a target grayscale difference set between the reference area and the position representative area is obtained.

[0101] The fifth step is to determine the target grayscale distribution difference between the reference area and the position representative area according to the target grayscale difference set between the reference area and the position representative area.

[0102] Among them, the target grayscale difference in the target grayscale difference set may be positively correlated with the target grayscale distribution difference.

[0103] For example, the mean value of all target grayscale differences in the target grayscale difference set between the reference region and the position representative region may be determined as the target grayscale distribution difference between the reference region and the position representative region.

[0104] In the sixth step, the matching degree between the reference area and the position representative area is determined according to the target grayscale distribution difference and the target distance between the reference area and the position representative area.

[0105] Among them, the target grayscale distribution difference and the target distance can both be negatively correlated with the matching degree.

[0106] For example, the formula for determining the matching degree between the first region and the second region may be:

[0107] ;

[0108] ;in, It is The first area and the The matching degree between the second regions. Is the sequence number of the first region. Is the sequence number of the second region. is a normalization function. It is an exponential function with a natural constant as its base. It is The first area and the The target grayscale distribution difference between the second regions. It is The first area and the The target distance between the second area. is the number of pixel points in the first region or the number of pixel points in the second region, and the number of pixel points in the first region is the same as the number of pixel points in the second region. is the serial number of a pixel point in the first region or the serial number of a pixel point in the second region, and the th pixel point in the first region and the th pixel point in the second region can be pixel points at the same position in different regions. is the absolute value function. is the th gray value corresponding to the th pixel point in the first region. is the th gray value corresponding to the th pixel point in the second region. is the target gray difference.

[0109] It should be noted that when is smaller, it often indicates that the gray distribution in the th first region is more similar to the gray distribution in the th second region, and it often indicates that the difference between the th first region and the th second region is smaller. When is smaller, it often indicates that the distance between the th first region and the th second region is smaller, and it often indicates that the th first region and the th second region are more likely to represent the same part. Therefore, when is larger, it often indicates that the th first region and the th second region are more similar, and it often indicates that the th first region and the th second region are more matched.

[0110] Step S4: Perform regional matching screening according to the matching degree between the first region and the second region to obtain the target matching pairs representing the changes before and after the operation.

[0111] Among them, each target matching pair may include a first region and a second region. The target matching pair can represent the disease regions that have changed before and after the chemotherapy surgery.

[0112] As an example, this step may include the following steps:

[0113] First step, determine any one of the first regions as the marked region, and screen out the second regions with the same position as the above-mentioned marked region from all the second regions as the matching reference regions corresponding to the above-mentioned marked region.

[0114] It should be noted that since the same part is photographed before and after the operation, the matching reference regions corresponding to the marked regions are often the regions with the same position as the marked regions in the second image to be enhanced.

[0115] Second step, form the reference matching pairs corresponding to the above-mentioned marked regions by the above-mentioned marked regions and their corresponding matching reference regions, and determine the matching degree between the two regions in the reference matching pairs as the target matching index of the reference matching pairs.

[0116] Third step, screen out the reference matching pairs with the target matching index less than the preset matching change threshold from the reference matching pairs corresponding to all the first regions as the target matching pairs.

[0117] Among them, the preset matching change threshold can be a threshold preset for screening the diseased regions. For example, the preset matching change threshold can be 0.3.

[0118] It should be noted that the tumor regions with lesions often change to a certain extent before and after chemotherapy, that is, the degree of lesions in the tumor regions often decreases before and after chemotherapy. Therefore, there are often certain changes between the tumor regions before and after chemotherapy. The regions in the target matching pairs can often characterize the regions with lesions.

[0119] Step S5, obtain the tumor manifestation degree corresponding to each region in each target matching pair according to the gray distribution of the connected domains pre-extracted in each region in each target matching pair.

[0120] As an example, this step may include the following steps:

[0121] First step, determine any one of the regions in any one of the target matching pairs as the candidate region, and perform connected domain extraction on the above-mentioned candidate region through the connected domain extraction algorithm to obtain multiple connected domains.

[0122] It should be noted that for the regions without connected domains in the first image to be enhanced and the second image to be enhanced, and the regions with the same position as the regions without connected domains, the indicators regarding the tumor manifestation and blood vessel manifestation of these regions do not need to be calculated subsequently, and the number of pixels corresponding to the gray values of these regions in the gray histogram does not need to be adjusted subsequently, and histogram equalization can be directly performed through the actual number of pixels corresponding to the gray values of these regions in the gray histogram.

[0123] In the second step, any connected component within the above-mentioned candidate region is determined as the marked connected component, and the average value of the gray values corresponding to all the pixel points within the above-mentioned marked connected component is determined as the gray representative factor corresponding to the above-mentioned marked connected component.

[0124] It should be noted that in actual situations, the tumor region in CT images is often relatively bright. When the gray representative factor corresponding to the marked connected component is larger, it often indicates that the marked connected component is relatively brighter, and it often indicates that the marked connected component is more likely to be a tumor connected component.

[0125] In the third step, through the eight-chain code algorithm, the chain code corresponding to each pixel point on the edge of the above-mentioned marked connected component is determined, and the chain code sequence corresponding to the above-mentioned marked connected component is obtained.

[0126] Among them, the chain code sequence corresponding to the marked connected component can characterize the chain code situation of the edge of the marked connected component. The chain code sequence corresponding to the marked connected component can include: the chain codes corresponding to all the pixel points on the edge of the marked connected component.

[0127] In the fourth step, the difference between every two adjacent chain codes in the chain code sequence corresponding to the above-mentioned marked connected component is determined as the target difference, and the target difference sequence corresponding to the above-mentioned marked connected component is obtained.

[0128] Among them, every two adjacent chain codes in the chain code sequence corresponding to the marked connected component can characterize the chain codes corresponding to every two adjacent pixel points on the edge of the marked connected component. The difference between two adjacent chain codes can be equal to the previous chain code minus the latter chain code among these two chain codes. The target difference sequence corresponding to the marked connected component can include: the differences between all adjacent two chain codes in the chain code sequence corresponding to the marked connected component.

[0129] In the fifth step, the variance of all the target differences in the target difference sequence corresponding to the above-mentioned marked connected component is determined as the edge clutter degree corresponding to the above-mentioned marked connected component.

[0130] It should be noted that in actual situations, the shape of the tumor region is often irregular, so the edge of the tumor region is often relatively cluttered. Therefore, when the edge clutter degree corresponding to the marked connected component is larger, it often indicates that the edge of the marked connected component is more cluttered, and it often indicates that the marked connected component is more likely to be a tumor connected component.

[0131] In the sixth step, the product of the gray representative factor and the edge clutter degree corresponding to the above-mentioned marked connected component is normalized to obtain the tumor suspicion index corresponding to the above-mentioned marked connected component.

[0132] It should be noted that when the tumor suspicion index corresponding to the marked connected component is larger, it often indicates that the marked connected component is more likely to be a tumor connected component.

[0133] Step 7: Determine the tumor manifestation degree corresponding to the above candidate region by taking the mean value of the tumor suspicion indicators corresponding to all connected components within the above candidate region.

[0134] It should be noted that when the tumor manifestation degree corresponding to the candidate region is larger, it often indicates that the candidate region is more likely to be a real tumor region.

[0135] Step S6: Determine the blood vessel manifestation degree corresponding to each region in each target matching pair according to the characteristics of the pre-extracted skeletons in the connected components within each region in each target matching pair.

[0136] As an example, this step may include the following steps:

[0137] Step 1: Determine any region in any target matching pair as a candidate region, and perform skeleton extraction on all connected components within the above candidate region through the opencv skeleton extraction algorithm to obtain multiple skeletons.

[0138] Step 2: Take the intersection points of all skeletons within the above candidate region as segmentation points, and segment all skeletons within the above candidate region to obtain skeleton branches.

[0139] Among them, the intersection point can be the intersection of at least two lines.

[0140] Step 3: Take the normal lines at the two end points of each skeleton branch as cutting lines, and segment the connected component to which each skeleton branch belongs to obtain the sub-region corresponding to each skeleton branch.

[0141] Step 4: Construct the intersection point set corresponding to each pixel point on each skeleton branch by taking all the intersection points between the normal line of each pixel point on each skeleton branch and the edge of its corresponding sub-region.

[0142] It should be noted that if the sub-region represented by the skeleton branch corresponds to a blood vessel, the number of intersection points in the intersection point set corresponding to the pixel points on this skeleton branch is often 2.

[0143] Step 5: Determine the mean value of the distances between all intersection points in the intersection point set corresponding to each pixel point on each skeleton branch as the representative distance factor corresponding to each pixel point on each skeleton branch.

[0144] It should be noted that if a certain pixel point is a blood vessel pixel point, the representative distance factor corresponding to this pixel point can represent the blood vessel width at this pixel point. If the number of intersection points in the intersection point set corresponding to a certain pixel point is 1, the representative distance factor corresponding to this pixel point can be set to 0.

[0145] Step 6. Determining the extensibility factor corresponding to each skeleton branch based on the grayscale values corresponding to all the pixel points on each skeleton branch and the representative distance factor may include the following sub-steps:

[0146] The first sub-step: determining the width grayscale factor corresponding to each pixel point on each skeleton branch as the product of the grayscale value corresponding to each pixel point on each skeleton branch and the representative distance factor.

[0147] The second sub-step: determining the difference between the width grayscale factors corresponding to every two adjacent pixel points on each skeleton branch as the width grayscale difference, and obtaining the width grayscale difference set corresponding to each skeleton branch.

[0148] The third sub-step: determining the absolute value of the cumulative value of all the width grayscale differences in the width grayscale difference set corresponding to each skeleton branch as the representative width grayscale difference corresponding to each skeleton branch.

[0149] The fourth sub-step: determining the variance of all the width grayscale differences in the width grayscale difference set corresponding to each skeleton branch as the width grayscale variation factor corresponding to each skeleton branch.

[0150] The fifth sub-step: determining the extensibility factor corresponding to each skeleton branch according to the representative width grayscale difference and the width grayscale variation factor corresponding to each skeleton branch.

[0151] Among them, the representative width grayscale difference may have a positive correlation with the extensibility factor. The width grayscale variation factor may have a negative correlation with the extensibility factor.

[0152] For example, the formula for determining the extensibility factor corresponding to the skeleton branch may be:

[0153] ;

[0154] ; where is the extensibility factor corresponding to the th skeleton branch. is the serial number of the skeleton branch. is the normalization function. is the exponential function with the natural constant as the base. is the width grayscale variation factor corresponding to the th skeleton branch, that is, the variance of all the width grayscale differences in the width grayscale difference set corresponding to the th skeleton branch. is the number of pixel points on the th skeleton branch. is the representative width grayscale difference corresponding to the th skeleton branch. is the The serial number of the pixel on a skeleton branch. is the th representative distance factor corresponding to the th pixel on the th skeleton branch. is the th representative distance factor corresponding to the th pixel on the th skeleton branch. is the absolute value function. is the width gray - level difference. and are the width gray - level factors.

[0155] It should be noted that in actual situations, blood vessels often appear as one or more tubular or tree - like structures. Along the extension direction of the blood vessels, the diameter of the blood vessels often becomes narrower, and their gray - level values often become smaller. For example, taking the pulmonary blood vessels as an example, along the extension direction of the pulmonary blood vessels, the width of the pulmonary blood vessels often becomes narrower, and the gray - level values of the pixels of the pulmonary blood vessels often become smaller. The more the extracted skeleton branches meet these characteristics, the stronger the extensibility of the extracted skeleton branches is often indicated, and the more likely the skeleton branch is to represent a blood vessel. When is larger, it often indicates that the sub - region corresponding to the th skeleton branch is more likely to conform to the characteristics of decreasing gray - level and width simultaneously in sequence, and it often indicates that the sub - region corresponding to the th skeleton branch is more likely to be a blood - vessel branch. When is smaller, it often indicates that the sub - region corresponding to the th skeleton branch is more likely to conform to the degree of decreasing gray - level and width simultaneously in sequence more evenly, and it often indicates that the sub - region corresponding to the th skeleton branch is more likely to be a blood - vessel branch. Therefore, when is larger, it often indicates that the sub - region corresponding to the th skeleton branch is more likely to be a blood - vessel branch.

[0156] Step 7: Perform threshold segmentation on each region in each target matching pair to obtain the foreground region and background region corresponding to each region in each target matching pair.

[0157] Step 8: Determine the blood - vessel manifestation degree corresponding to each region in each target matching pair according to the gray - level difference between the foreground region and the background region corresponding to each region in each target matching pair, and the extensibility factors corresponding to all skeleton branches in each region in each target matching pair.

[0158] For example, the formula for determining the blood vessel manifestation degree corresponding to the region in the target matching pair can be:

[0159] ;

[0160] ; where is the blood vessel manifestation degree corresponding to the th region in the th target matching pair. is the serial number of the target matching pair. is the serial number of the region in the th target matching pair. is the normalization function. is the serial number of the th region in the th target matching pair, which is the cumulative value of the extensibility factors corresponding to all skeleton branches in the region. characterizes the chaos degree of the th region in the th target matching pair. is the exponential function with the natural constant as the base. is the absolute value function. is the serial number of the th region in the th target matching pair, which is the mean value of the gray values corresponding to all pixel points in the foreground region of the region. is the serial number of the th region in the th target matching pair, which is the mean value of the gray values corresponding to all pixel points in the background region of the region. is the serial number of the th region in the th target matching pair, which is the number of skeleton branches in the region. is the serial number of the th region in the th target matching pair, which is the serial number of the skeleton branch in the region. is the serial number of the th region in the th target matching pair, which is the variance of the chain codes corresponding to all pixel points on the th skeleton branch in the region. The chain code corresponding to the pixel point can be obtained through the octal chain code algorithm.

[0161] It should be noted that when is larger, it often indicates that the skeleton branches in the th region of the th target matching pair are more likely to be blood vessel branches, and the more skeleton branches in the th region of the th target matching pair, it often indicates that In the th region of a target matching pair, the higher the likelihood of meeting the density of blood vessels, the more likely it indicates that the th region in the th target matching pair is a blood vessel region. When is larger, it often indicates that the th region in the th target matching pair has more irregular edges of the skeleton branches, which often indicates that the th region in the th target matching pair is relatively more chaotic, which often indicates that the th region in the th target matching pair is more likely to meet the density of blood vessels. When is smaller, it often indicates that the th region in the th target matching pair has a worse contrast in segmentation, which often indicates a lower clarity of segmentation, and often indicates that the th region in the th target matching pair is more likely to meet the density of blood vessels. Therefore, when is larger, it often indicates that the th region in the th target matching pair is more likely to represent a real blood vessel region.

[0162] Step S7: Determine the true recovery performance under each target matching pair according to the difference between the tumor manifestation degrees corresponding to the two regions in each target matching pair and the difference between their corresponding blood vessel manifestation degrees.

[0163] As an example, the formula for determining the true recovery performance under a target matching pair can be:

[0164] ;

[0165] ;

[0166] ; where is the true recovery performance under the th target matching pair. is the serial number of the target matching pair. is a normalization function. represents the tumor elimination situation under the th target matching pair. represents the local recovery situation under the th target matching pair. is the tumor manifestation degree corresponding to the first region in the th target matching pair. is the The tumor manifestation degree corresponding to the second region in the target matching pair. is the vascular manifestation degree corresponding to the second region in the target matching pair. is the vascular manifestation degree corresponding to the first region in the target matching pair.

[0167] It should be noted that before and after chemotherapy, the tumor manifestation degree in the lesion area often becomes lower, and the vascular manifestation degree often becomes higher. When is larger, it often indicates that the change in tumor manifestation before and after chemotherapy in the th target matching pair is more in line with the tumor change of the real lesion, and it often indicates that the th target matching pair is more likely to represent the detailed information that needs to be retained. When is larger, it often indicates that the change in vascular manifestation before and after chemotherapy in the th target matching pair is more in line with the vascular change of the real lesion, and it often indicates that the th target matching pair is more likely to represent the detailed information that needs to be retained. Therefore, when is larger, it often indicates that the th target matching pair is more likely to represent the detailed information that needs to be retained, and it often indicates that it is more necessary to increase the number of pixels of the th target matching pair in its grayscale histogram.

[0168] Step S8: Perform histogram equalization on the first image to be enhanced and the second image to be enhanced according to the true recovery manifestation degrees under all target matching pairs.

[0169] As an example, this step may include the following steps:

[0170] First step, determine the true recovery manifestation factor corresponding to each first region by using the true recovery manifestation degree under the target matching pair to which each first region belongs.

[0171] Second step, adjust the grayscale histogram of the first image to be enhanced according to the true recovery manifestation factors corresponding to all first regions to obtain the first target histogram.

[0172] Among them, the horizontal and vertical coordinates of the grayscale histogram are the grayscale value and the number of pixel points equal to this grayscale value respectively.

[0173] For example, determine each grayscale value within all the first regions as candidate grayscale values. Based on the true recovery performance factors corresponding to all the first regions to which each candidate grayscale value belongs, increase the number of pixel points in the grayscale histogram of the first image to be enhanced that are equal to the candidate grayscale value, obtain the target pixel number corresponding to each candidate grayscale value, and update the number of pixel points of each candidate grayscale value in the grayscale histogram of the first image to be enhanced to its corresponding target pixel number. Take the finally updated grayscale histogram at this time as the first target histogram.

[0174] For instance, determining the target pixel number corresponding to each candidate grayscale value may include the following sub-steps:

[0175] The first sub-step: Determine any one candidate grayscale value as the marked grayscale value, determine each first region to which the marked grayscale value belongs as a temporary region, and determine the number of pixel points within each temporary region whose corresponding grayscale value is equal to the marked grayscale value as the initial marked pixel number corresponding to each temporary region.

[0176] The second sub-step: Determine the product of the initial marked pixel number corresponding to each temporary region and the true recovery performance factor as the marked pixel increment corresponding to each temporary region.

[0177] The third sub-step: Round the accumulated value of the marked pixel increments corresponding to all the temporary regions to obtain the target pixel number corresponding to the marked grayscale value.

[0178] It should be noted that the same grayscale value may exist in different first regions, so there may be multiple first regions to which a candidate grayscale value belongs.

[0179] The third step: Determine the true recovery performance degree corresponding to each target matching pair to which each second region belongs as the true recovery performance factor corresponding to each second region.

[0180] The fourth step: Adjust the grayscale histogram of the second image to be enhanced according to the true recovery performance factors corresponding to all the second regions to obtain the second target histogram.

[0181] It should be noted that the method for obtaining the second target histogram may be the same as the method for obtaining the first target histogram, which will not be elaborated here.

[0182] The fifth step: Perform histogram equalization on the first image to be enhanced and the second image to be enhanced respectively according to the above-mentioned first target histogram and the above-mentioned second target histogram.

[0183] For example, update the grayscale histogram of the first image to be enhanced to the first target histogram, and perform histogram equalization on the first image to be enhanced according to the updated grayscale histogram at this time. Update the grayscale histogram of the second image to be enhanced to the second target histogram, and perform histogram equalization on the second image to be enhanced according to the updated grayscale histogram at this time.

[0184] Reference Figure 3 , based on the same inventive concept as the above method embodiments, the present invention provides a CT image assisted reading system for the postoperative review stage of chemotherapy. The system includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps of a CT image assisted reading method for the postoperative review stage of chemotherapy, which may specifically include:

[0185] A CT image acquisition module 301, configured to acquire CT images before and after chemotherapy as the first image to be enhanced and the second image to be enhanced respectively;

[0186] A region division module 302, configured to divide the first image to be enhanced to obtain a first region, and divide the second image to be enhanced to obtain a second region;

[0187] A matching degree determination module 303, configured to determine the matching degree between each first region and each second region according to the distance and grayscale distribution difference between each first region and each second region;

[0188] A region matching and screening module 304, configured to perform region matching and screening according to the matching degree between the first region and the second region to obtain a target matching pair indicating changes before and after surgery;

[0189] A tumor manifestation degree determination module 305, configured to obtain the tumor manifestation degree corresponding to each region in each target matching pair according to the grayscale distribution of the pre-extracted connected domains in each region of each target matching pair;

[0190] A blood vessel manifestation degree determination module 306, configured to determine the blood vessel manifestation degree corresponding to each region in each target matching pair according to the characteristics of the pre-extracted skeletons in the connected domains in each region of each target matching pair;

[0191] A true recovery manifestation degree determination module 307, configured to determine the true recovery manifestation degree under each target matching pair according to the difference between the tumor manifestation degrees corresponding to the two regions in each target matching pair and the difference between the corresponding blood vessel manifestation degrees;

[0192] A histogram equalization module 308, configured to perform histogram equalization on the first image to be enhanced and the second image to be enhanced according to the true recovery manifestation degrees under all target matching pairs.

[0193] Figure 4 This is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Exemplarily, as Figure 4 shown, the computer device 400 includes: a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any one of the CT image-assisted reading methods in the postoperative chemotherapy review stage introduced above.

[0194] Based on the same inventive concept as the above method embodiment, the present invention provides a server, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the device executes any one of the CT image-assisted reading methods in the postoperative chemotherapy review stage described above.

[0195] Based on the same inventive concept as the above method embodiment, the present invention provides a computer program product, which includes: computer program code. When the computer program code runs on a computer, the computer executes any one of the CT image-assisted reading methods in the postoperative chemotherapy review stage described above.

[0196] Based on the same inventive concept as the above method embodiment, the present invention provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the CT image-assisted reading methods in the postoperative chemotherapy review stage described above.

[0197] In summary, compared with directly performing histogram equalization on a CT image according to the gray histogram of the CT image, the present invention comprehensively considers multiple indicators related to the detailed information of the disease recovery of the CT image, such as the matching degree between regions in different CT images, the tumor manifestation degree, the blood vessel manifestation degree, and the true recovery manifestation degree, thereby improving the retention degree of the detailed information, and further improving the effect of CT image enhancement.

[0198] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A CT image-assisted reading method for the post-chemotherapy review stage, characterized in that: The following steps are involved: Acquire CT images before and after chemotherapy as the first image to be enhanced and the second image to be enhanced, respectively; Performing region division on the first image to be enhanced to obtain a first region, and performing region division on the second image to be enhanced to obtain a second region; Determine the matching degree between each first region and each second region according to the distance and grayscale distribution difference between each first region and each second region, wherein the distance and grayscale distribution difference between the first region and each second region is the distance and grayscale distribution difference between the second region and a position representative region, and the position representative region is a region in the second image to be enhanced that has the same position as the first region; Performing regional matching screening according to the matching degree between the first region and the second region to obtain a target matching pair representing changes before and after the operation; Obtaining a tumor expression degree corresponding to each region in each target matching pair according to the grayscale distribution of the pre-extracted connected domain in each region in each target matching pair, wherein the tumor expression degree is a probability that the region is a real tumor region; According to the characteristics of the pre-extracted skeleton in the connected domain in each region of each target matching pair, the vascular expression degree corresponding to each region in each target matching pair is determined. The specific formula is: ； ;in, It is Target matching pair The vascular expression corresponding to each region; is the sequence number of the target matching pair; It is The serial number of the target matching area; is the normalization function; It is Target matching pair The cumulative value of the extensibility factors corresponding to all skeleton branches in a region; Characterization Target matching pair Disorder in the region; It is an exponential function with a natural constant as base; It is the absolute value function; It is Target matching pair The mean of the gray values ​​corresponding to all pixels in the foreground area of ​​the region; It is Target matching pair The mean of the grayscale values ​​corresponding to all pixels in the background area of ​​a region; It is Target matching pair The number of skeleton branches in a region; It is Target matching pair The serial number of the skeleton branches in each region; It is Target matching pair In the region The variance of the chain codes corresponding to all pixels on the skeleton branches; the chain codes corresponding to the pixels are obtained through the eight-chain code algorithm; The skeleton is extracted from the connected domain in any region of the target matching pair to obtain multiple skeletons, and all skeletons in the region are segmented using the intersection of the skeletons as segmentation points to obtain skeleton branches; Determine the extensibility factor corresponding to each skeleton branch according to the grayscale values ​​and representative distance factors corresponding to all pixels on each skeleton branch, wherein the representative distance factor corresponding to the pixel represents the width of the blood vessel at the pixel; According to the difference between the tumor expressions corresponding to the two regions in each target matching pair and the difference between the corresponding blood vessel expressions, the true restored expression under each target matching pair is determined; According to the true restoration performance under all target matching pairs, histogram equalization is performed on the first image to be enhanced and the second image to be enhanced.

2. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 1, characterized in that: The determining the matching degree between each first region and each second region according to the distance and grayscale distribution difference between each first region and each second region includes: Determine any one of the first regions as a marking region, and determine any one of the second regions as a reference region; Determine the region in the second image to be enhanced that is at the same position as the marked region as a position representative region; Determine the distance between the center point of the reference area and the center point of the position representative area as the target distance between the marked area and the reference area; Determine the absolute value of the difference between the grayscale values ​​corresponding to the pixels at the same position in the reference area and in the position representative area as the target grayscale difference, and obtain a target grayscale difference set between the reference area and the position representative area; Determine a target grayscale distribution difference between the reference area and the position representative area according to a target grayscale difference set between the reference area and the position representative area, wherein the target grayscale difference in the target grayscale difference set is positively correlated with the target grayscale distribution difference; The matching degree between the reference area and the position representative area is determined according to the target grayscale distribution difference and the target distance between the reference area and the position representative area, wherein the target grayscale distribution difference and the target distance are negatively correlated with the matching degree.

3. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 2, characterized in that: The determining the target grayscale distribution difference between the reference area and the position representative area according to the target grayscale difference set between the reference area and the position representative area comprises: The mean value of all target grayscale differences in the target grayscale difference set between the reference region and the position representative region is determined as the target grayscale distribution difference between the reference region and the position representative region.

4. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 1, characterized in that: The region matching screening is performed according to the matching degree between the first region and the second region to obtain a target matching pair representing changes before and after the operation, including: Determine any one of the first regions as a marked region, and select a second region having the same position as the marked region from all the second regions as a matching reference region corresponding to the marked region; The marked area and its corresponding matching reference area constitute a reference matching pair corresponding to the marked area, and the matching degree between the two areas in the reference matching pair is determined as a target matching index of the reference matching pair; A reference matching pair whose target matching index is less than a preset matching change threshold is selected from all reference matching pairs corresponding to the first region as a target matching pair.

5. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 1, characterized in that: The step of obtaining the tumor expression corresponding to each region in each target matching pair according to the grayscale distribution of the pre-extracted connected domain in each region in each target matching pair includes: Determine any region in any target matching pair as a candidate region, and perform connected domain extraction on the candidate region; Determine any connected domain in the candidate region as a marked connected domain, and determine the mean of the grayscale values ​​corresponding to all pixels in the marked connected domain as a grayscale representative factor corresponding to the marked connected domain; Determine the chain code corresponding to each pixel point on the edge of the marked connected domain by using the eight-chain code algorithm to obtain the chain code sequence corresponding to the marked connected domain; The difference between each two adjacent chain codes in the chain code sequence corresponding to the marked connected domain is determined as a target difference, so as to obtain a target difference sequence corresponding to the marked connected domain; Determine the variance of all target difference values ​​in the target difference value sequence corresponding to the marked connected domain as the edge clutter corresponding to the marked connected domain; Normalizing the product of the grayscale representative factor and the edge clutter corresponding to the marked connected domain to obtain a suspected tumor indicator corresponding to the marked connected domain; The average of the suspected tumor indicators corresponding to all connected domains in the candidate region is determined as the tumor expression degree corresponding to the candidate region.

6. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 1, characterized in that: Determining the blood vessel expression corresponding to each region in each target matching pair according to the characteristics of the pre-extracted skeleton in the connected domain in each region in each target matching pair includes: Determine any region in any target matching pair as a candidate region, and perform skeleton extraction on all connected domains in the candidate region; Taking the intersection points of all skeletons in the candidate area as segmentation points, segmenting all skeletons in the candidate area to obtain skeleton branches; Using the normals at the two endpoints of each skeleton branch as cutting lines, the connected domain of each skeleton branch is segmented to obtain the sub-region corresponding to each skeleton branch; All intersection points of the normal line of each pixel point on each skeleton branch and the edge of its corresponding sub-region form a set of intersection points corresponding to each pixel point on each skeleton branch; The average value of the distances between all intersection points in the set of intersection points corresponding to each pixel point on each skeleton branch is determined as the representative distance factor corresponding to each pixel point on each skeleton branch; Determine the extensibility factor corresponding to each skeleton branch according to the grayscale values ​​and representative distance factors corresponding to all pixels on each skeleton branch; Perform threshold segmentation on each region in each target matching pair to obtain the foreground region and background region corresponding to each region in each target matching pair; The vascular expression degree corresponding to each region in each target matching pair is determined according to the grayscale difference between the foreground region and the background region corresponding to each region in each target matching pair, and the extensibility factor corresponding to all skeleton branches in each region in each target matching pair.

7. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 6, characterized in that: Determining the extensibility factor corresponding to each skeleton branch according to the grayscale values ​​corresponding to all pixels on each skeleton branch and the representative distance factor includes: The product of the grayscale value corresponding to each pixel point on each skeleton branch and the representative distance factor is determined as the width grayscale factor corresponding to each pixel point on each skeleton branch; The difference between the width grayscale factors corresponding to each adjacent pixel point on each skeleton branch is determined as the width grayscale difference, and a width grayscale difference set corresponding to each skeleton branch is obtained; The absolute value of the accumulated values ​​of all the width grayscale differences in the width grayscale difference set corresponding to each skeleton branch is determined as the width grayscale representative difference corresponding to each skeleton branch; The variance of all width grayscale differences in the width grayscale difference set corresponding to each skeleton branch is determined as the width grayscale variation factor corresponding to each skeleton branch; According to the width grayscale representative difference and the width grayscale variation factor corresponding to each skeleton branch, the extensibility factor corresponding to each skeleton branch is determined, wherein the width grayscale representative difference is positively correlated with the extensibility factor, and the width grayscale variation factor is negatively correlated with the extensibility factor.

8. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 1, characterized in that: The formula corresponding to the true recovery performance under the target matching pair is: ； ； ;in, It is The true recovery performance under target matching pairs; is the sequence number of the target matching pair; is the normalization function; Indicates Tumor elimination under target matching pairs; Indicates Local recovery under target matching pairs; It is The tumor expression corresponding to the first region in the target matching pair; It is The tumor expression corresponding to the second region in the target matching pair; It is The vascular expression corresponding to the second region in the target matching pair; It is The vascular expression corresponding to the first region in the target matching pair.

9. The CT image-assisted reading method for the post-chemotherapy review stage according to claim 1, characterized in that: The performing histogram equalization on the first image to be enhanced and the second image to be enhanced according to the true restoration performance under all target matching pairs includes: Determine the true recovery performance degree of each target matching pair to which each first region belongs as a true recovery performance factor corresponding to each first region; Adjusting the grayscale histogram of the first image to be enhanced according to the true restoration performance factors corresponding to all the first regions to obtain a first target histogram; Determine the true recovery performance degree under the target matching pair to which each second region belongs as the true recovery performance factor corresponding to each second region; According to the true restoration performance factors corresponding to all the second regions, the grayscale histogram of the second image to be enhanced is adjusted to obtain a second target histogram; Histogram equalization is performed on the first image to be enhanced and the second image to be enhanced according to the first target histogram and the second target histogram.

Images