A CT image enhancement method based on pneumonia image diagnosis

Abstract

The present application provides a CT image enhancement method based on pneumonia image diagnosis, which belongs to the field of image processing technology. First, a total of m CT tomographic images are obtained. The superposition process retains the pixels with higher brightness in the first target image or the third target image. Finally, j fourth target images are obtained and displayed based on the m CT tomographic images. The present application proposes a CT image enhancement method based on pneumonia image diagnosis. By performing interval extraction and superposition on a group of CT tomographic images, the superimposed image makes the diffusion pattern clearer and the medical staff can observe more clearly. The present application also provides a CT image enhancement system based on pneumonia image diagnosis.

Description

Technical Field

[0001] The present application relates to the field of medical images, and in particular to a CT image enhancement method based on pneumonia image diagnosis. Background Art

[0002] CT (Computed Tomography) is a medical imaging technology. It uses X-ray beams to scan the human body and uses computer processing to produce detailed images of the body's internal structures. CT scanning is widely used in the diagnosis of various diseases due to its fast and clear imaging capabilities.

[0003] Pneumonia often presents as areas of increased density in the lungs that may be blurred and contrast with the surrounding normal lung tissue. This increased density may be due to inflammation causing the alveoli to fill with fluid or cells, or due to tissue damage caused by the infection. In some cases, CT images may also show features such as cavitation, lobar consolidation, or pleural effusion, which can help doctors determine the severity and type of infection.

[0004] In the process of observing pneumonia images, the observation of diffuse shadow areas is a very important step. However, in cases such as the early stage of the disease, the diffuse area may not be obvious in a single directly taken CT image, which may cause medical staff to ignore it. Summary of the invention

[0005] The embodiment of the present application provides a CT image enhancement method based on pneumonia image diagnosis to improve the above-mentioned problems.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] In the first aspect, the present application proposes a CT image enhancement method based on pneumonia image diagnosis, the method comprising:

[0008] A total of m CT scan images are obtained, where m is a natural number greater than or equal to 3;

[0009] Determine from m CT tomographic images that the n-1th CT tomographic image is the first target image, the nth CT tomographic image is the second target image, and the n+1th CT tomographic image is the third target image, wherein n is a natural number greater than or equal to 1 and mn≥1;

[0010] Superimposing the first target image and the third target image to obtain a fourth target image, wherein the superimposition process retains pixels with higher brightness in the first target image or the third target image;

[0011] Based on m CT tomography images, j fourth target images are acquired and displayed, wherein j is a natural number and j=m-2.

[0012] In combination with the first aspect, in some feasible implementations, acquiring and displaying j fourth target images based on m CT tomography images, where j is a natural number and j=m-2, includes:

[0013] Obtaining the average grayscale value of the entire second target image;

[0014] Image calibration is performed on the fourth target image based on the average grayscale value of the entire second target image, so that the average grayscale value of the entire fourth target image is the same as the average grayscale value of the entire second target image.

[0015] In combination with the first aspect, in some feasible implementations, acquiring and displaying j fourth target images based on m CT tomography images, where j is a natural number and j=m-2, further includes:

[0016] Obtaining an average contrast value of the entire second target image;

[0017] Image calibration is performed on the fourth target image based on the average contrast value of the entire second target image, so that the average contrast value of the entire fourth target image is the same as the average contrast value of the entire second target image.

[0018] In combination with the first aspect, in some feasible implementations, after acquiring and displaying j fourth target images based on m CT tomography images, where j is a natural number and j=m-2, the method further includes:

[0019] In response to the user's operation and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2.

[0020] In combination with the first aspect, in some feasible implementations, in response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including:

[0021] Determine from the j fourth target images that the k-1th CT tomography image is the sixth target image, the kth fourth target image is the seventh target image, and the k+1th fourth target image is the eighth target image;

[0022] The sixth target image is superimposed on the eighth target image to obtain a fifth target image, wherein the superimposition process retains pixels with higher brightness in the sixth target image or the eighth target image.

[0023] In combination with the first aspect, in some feasible implementations, in response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including:

[0024] Obtaining the average grayscale value of the entire seventh target image;

[0025] Image calibration is performed on the fifth target image based on the average grayscale value of the seventh target image, so that the average grayscale value of the entire fifth target image is the same as the average grayscale value of the entire seventh target image.

[0026] In combination with the first aspect, in some feasible implementations, the first target image and the third target image are superimposed to obtain a fourth target image, wherein the superposition process retains pixels with higher brightness in the first target image or the third target image, including:

[0027] Segmenting the first target image to form a plurality of first sub-images, wherein the sizes of the first sub-images are preset sizes;

[0028] Acquire a first non-target image in the first target image, where the first non-target image is an image composed of a plurality of first sub-images in a non-discrete state in the first target image;

[0029] Segmenting the third target image to form a plurality of second sub-images, wherein the second sub-images correspond one-to-one to the first sub-images;

[0030] Acquire a second non-target image in the second target image, where the second non-target image is an image composed of a plurality of second sub-images in a non-discrete state in the first target image;

[0031] The first non-target image is compared with the second non-target image, and according to the comparison result, the first non-target image or the second non-target image is retained in the fourth target image.

[0032] In combination with the first aspect, in some feasible implementations, comparing the first non-target image with the second non-target image, and retaining the first non-target image or the second non-target image in the fourth target image according to a result of the comparison, includes:

[0033] Based on a first number of first sub-images constituting the first non-target image and a second number of second sub-images constituting the second non-target image, it is determined whether to retain the first non-target image or the second non-target image in the fourth target image, wherein:

[0034] When the first number is greater than the second number, determining to retain the first non-target image in the fourth target image;

[0035] When the second number is greater than the first number, determining to retain the second non-target image in the fourth target image;

[0036] When the first number is the same as the second number, the first non-target image and the second non-target image are retained at the same time.

[0037] In a second aspect, the present application embodiment further proposes a CT image enhancement system based on pneumonia image diagnosis, which is configured as follows:

[0038] A total of m CT scan images are obtained, where m is a natural number greater than or equal to 3;

[0039] Determine from m CT tomographic images that the n-1th CT tomographic image is the first target image, the nth CT tomographic image is the second target image, and the n+1th CT tomographic image is the third target image, wherein n is a natural number greater than or equal to 1 and mn≥1;

[0040] Superimposing the first target image and the third target image to obtain a fourth target image, wherein the superimposition process retains pixels with higher brightness in the first target image or the third target image;

[0041] Based on m CT tomography images, j fourth target images are acquired and displayed, wherein j is a natural number and j=m-2.

[0042] In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0043] Acquiring and displaying j fourth target images based on m CT scan images, wherein j is a natural number and j=m-2, comprises:

[0044] Obtaining the average grayscale value of the entire second target image;

[0045] Image calibration is performed on the fourth target image based on the average grayscale value of the entire second target image, so that the average grayscale value of the entire fourth target image is the same as the average grayscale value of the entire second target image.

[0046] In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0047] Acquiring and displaying j fourth target images based on m CT tomography images, wherein j is a natural number and j=m-2, further comprising:

[0048] Obtaining an average contrast value of the entire second target image;

[0049] Image calibration is performed on the fourth target image based on the average contrast value of the entire second target image, so that the average contrast value of the entire fourth target image is the same as the average contrast value of the entire second target image.

[0050] In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0051] Acquiring and displaying j fourth target images based on m CT tomography images, wherein j is a natural number and j=m-2, further comprising:

[0052] In response to the user's operation and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2.

[0053] In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0054] In response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including:

[0055] Determine from the j fourth target images that the k-1th CT tomography image is the sixth target image, the kth fourth target image is the seventh target image, and the k+1th fourth target image is the eighth target image;

[0056] The sixth target image is superimposed on the eighth target image to obtain a fifth target image, wherein the superimposition process retains pixels with higher brightness in the sixth target image or the eighth target image.

[0057] In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0058] In response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including:

[0059] Obtaining the average grayscale value of the entire seventh target image;

[0060] Image calibration is performed on the fifth target image based on the average grayscale value of the seventh target image, so that the average grayscale value of the entire fifth target image is the same as the average grayscale value of the entire seventh target image.

[0061] In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0062] The first target image and the third target image are superimposed to obtain a fourth target image, wherein the superimposition process retains pixels with higher brightness in the first target image or the third target image, including:

[0063] Segmenting the first target image to form a plurality of first sub-images, wherein the sizes of the first sub-images are preset sizes;

[0064] Acquire a first non-target image in the first target image, where the first non-target image is an image composed of a plurality of first sub-images in a non-discrete state in the first target image;

[0065] Segmenting the third target image to form a plurality of second sub-images, wherein the second sub-images correspond one-to-one to the first sub-images;

[0066] Acquire a second non-target image in the second target image, where the second non-target image is an image composed of a plurality of second sub-images in a non-discrete state in the first target image;

[0067] The first non-target image is compared with the second non-target image, and according to the comparison result, the first non-target image or the second non-target image is retained in the fourth target image.

[0068] In conjunction with the second aspect, in some embodiments, the system is configured as follows:

[0069] Comparing the first non-target image with the second non-target image, and retaining the first non-target image or the second non-target image in the fourth target image according to a result of the comparison, comprises:

[0070] Based on a first number of first sub-images constituting the first non-target image and a second number of second sub-images constituting the second non-target image, it is determined whether to retain the first non-target image or the second non-target image in the fourth target image, wherein:

[0071] When the first number is greater than the second number, determining to retain the first non-target image in the fourth target image;

[0072] When the second number is greater than the first number, determining to retain the second non-target image in the fourth target image;

[0073] When the first number is the same as the second number, the first non-target image and the second non-target image are retained at the same time.

[0074] A third aspect of an embodiment of the present invention provides an electronic device, the electronic device comprising:

[0075] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method proposed in the first aspect of the embodiment of the present invention.

[0076] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in the first aspect of the embodiment of the present invention.

[0077] In summary, the above method and device have the following technical effects:

[0078] A CT image enhancement method based on pneumonia image diagnosis proposed in an embodiment of the present application first obtains a total of m CT tomographic images, determines the n-1th CT tomographic image as the first target image, the nth CT tomographic image as the second target image, and the n+1th CT tomographic image as the third target image from the m CT tomographic images, and then superimposes the first target image with the third target image to obtain the fourth target image, wherein the superposition process retains pixels with higher brightness in the first target image or the third target image, and finally obtains j fourth target images based on the m CT tomographic images and displays them. A CT image enhancement method based on pneumonia image diagnosis proposed in the present application performs interval extraction and superposition on a group of CT tomographic images, so that the superimposed image has clearer diffusion patterns and medical staff can observe more clearly. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 A flowchart of a CT image enhancement method based on pneumonia image diagnosis proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0080] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0081] This application proposes a CT image enhancement method based on pneumonia image diagnosis, please refer to Figure 1 , including the following steps:

[0082] S101: Acquire a total of m CT scan images, where m is a natural number greater than or equal to 3.

[0083] It is understandable that during the CT image scanning of a patient, an X-ray beam is used to perform a layered scan of the human body, and a detailed image of the internal structure of the body is generated by computer processing. Generally speaking, the number of tomographic scans of a CT image is greater than 10 layers or more. In this embodiment, the tomographic scan images directly obtained by the X-ray device and acquired by the computer or processing device have a total of m images, that is, multiple tomographic scan images numbered 1, 2, 3, ...m.

[0084] S102: Determine from m CT scan images that the n-1th CT scan image is the first target image, the nth CT scan image is the second target image, and the n+1th CT scan image is the third target image, where n is a natural number greater than or equal to 1 and mn≥1.

[0085] It is understandable that in the lung images of pneumonia patients, diffuse lobar edema, lung abscesses, etc. are generally nodular and patchy shadows of different sizes in X-rays, and ground-glass, reticular, and honeycomb high-density shadows can be seen in the subpleural area of ​​both lungs. This is caused by diffuse edema. However, in the early stages of the disease, these parts may be easily overlooked in a single CT tomographic image due to their low density. Therefore, in this embodiment, multiple CT tomographic images are combined to enhance the diffuse area image to achieve a more obvious observation purpose.

[0086] Exemplarily, in this embodiment, the n-1th CT tomography image is determined as the first target image, the nth CT tomography image is determined as the second target image, and the n+1th CT tomography image is determined as the third target image from m CT tomography images, wherein n is a natural number greater than or equal to 1 and mn≥1, that is, n can be any one of the CT tomography images numbered 2, 3, 4, 5...m-1. For example, in this embodiment, the first target image is a CT tomography image before the selected slice, and the third target image is an image after the selected slice image.

[0087] S103: Superimposing the first target image and the third target image to obtain a fourth target image, wherein the superimposing process retains pixels with higher brightness in the first target image or the third target image.

[0088] Specifically, in this embodiment, a tomographic image is first selected, and then the previous image and the next image of the CT tomographic image are superimposed, so that the diffuse image in the superimposed image is more eye-catching. As an implementation method, in this application, pixels with higher brightness can be directly selected, and discrete pixels with higher brightness can be superimposed together to make the final result more eye-catching.

[0089] Specifically, in this embodiment, when n=2, the first target image is the first one, the second target image is the second one, and the third target image is the third one, that is, the first one and the third one are superimposed. When n is equal to 3, the second one and the fourth one are superimposed.... and so on. In this way, when there are m tomographic images in total, m-2 superimposed images can be obtained, that is, m-2 fourth target images.

[0090] Since the pixel superposition process will inevitably result in the superimposed image having a lower grayscale value and a higher contrast value than the original image, in order to enable the superimposed image to retain the grayscale value or contrast value corresponding to the original image, or to be closer to the contrast value or grayscale value in the original image, in some embodiments, the superimposed image can also be calibrated by the grayscale value and contrast value of the second target image.

[0091] Specifically, step S103 may further include the following steps:

[0092] S1031: Obtain the average grayscale value of the entire second target image.

[0093] S1032: Obtain an average contrast value of the entire second target image.

[0094] S1033: Perform image calibration on the fourth target image based on the average grayscale value of the entire second target image, so that the average grayscale value of the entire fourth target image is the same as the average grayscale value of the entire second target image.

[0095] S1034: Perform image calibration on the fourth target image based on the average contrast value of the entire second target image, so that the average contrast value of the entire fourth target image is the same as the average contrast value of the entire second target image.

[0096] It can be understood that since the second target image is actually the image between the two tomographic images of the first target image and the third target image, its structure must be not much different from the first target image and the third target image, and its image change also tends to be between the two images. Therefore, in this embodiment, the grayscale value and contrast value of the second target image can be used to calibrate the grayscale value of the fourth target image.

[0097] The superposition process can make diffuse image points clearer, but for some more concentrated areas in the structure, such as branched structures, the superposition process will cause the superimposed image to have a larger range, affecting the judgment of medical staff. Therefore, the superposition process should try to avoid superimposing larger concentrated areas.

[0098] Exemplarily, as an implementation mode, step S103 may include the following steps:

[0099] S201: Segment a first target image to form a plurality of first sub-images, where the sizes of the first sub-images are preset sizes.

[0100] It is understandable that in the process of image recognition, image segmentation is a basic step. In this embodiment, the size of the first sub-image should be as small as possible to make the image recognition more accurate. Of course, the size of the first sub-image is limited by the processing power of the processing device in actual situations, and the specific parameters are not limited in this application.

[0101] S202: Acquire a first non-target image in the first target image, where the first non-target image is an image composed of a plurality of first sub-images in a non-discrete state in the first target image.

[0102] It can be understood that for the parts that do not need to be observed in the first target image, that is, non-target images, these images may be structures such as fat, bones, and chest wall. The common feature of these structures is that the sub-images that form these structures are all in a non-discrete state in the image, that is, they are connected together. Therefore, in the first target image, the sub-images that form these highlighted parts can be marked by image recognition, and then combined to obtain all non-target images, that is, the first non-target image.

[0103] S203: Segment the third target image to form a plurality of second sub-images, where the second sub-images correspond to the first sub-images one by one.

[0104] S204: Acquire a second non-target image in the second target image, where the second non-target image is an image composed of a plurality of second sub-images in non-discrete states in the first target image.

[0105] It can be understood that the processing method for the third target image is the same as that for the first target image, and will not be described in detail here.

[0106] S205: Compare the first non-target image with the second non-target image, and retain the first non-target image or the second non-target image in the fourth target image according to the comparison result.

[0107] In this step, the first non-target image in the first target image and the second non-target image in the third target image may be compared, and the smaller one may be displayed in the final display result to reduce the interference of superposition.

[0108] Specifically, as an implementation method, first, based on the first number of first sub-images constituting the first non-target image and the second number of second sub-images constituting the second non-target image, it can be determined whether to retain the first non-target image or the second non-target image in the fourth target image. Exemplarily, when the first number is greater than the second number, it is determined to retain the first non-target image in the fourth target image. Of course, when the second number is greater than the first number, it is determined to retain the second non-target image in the fourth target image. Of course, when the first number is the same as the second number, both the first non-target image and the second non-target image are retained, and one of the two can be selected.

[0109] S104: Based on the m CT scan images, j fourth target images are acquired and displayed, where j is a natural number and j=m-2.

[0110] It can be understood that after the m images are superimposed, m-2 images, that is, j images, can be finally obtained.

[0111] In some embodiments, after one superposition, the problem of unclear diffusion area may still occur. Therefore, as an embodiment, after the image after one superposition is displayed to the medical staff for observation, it is selected whether to continue the superposition according to the instructions fed back by the medical staff. A second superposition or a third superposition can also be performed. The second superposition is taken as an example in this application, that is, in response to the user's operation and based on j fourth target images, k fifth target images are obtained and displayed, where k is a natural number and k=j-2.

[0112] Exemplarily, the method further comprises the following steps:

[0113] S105: Determine from the j fourth target images that the k-1th CT tomography image is the sixth target image, the kth fourth target image is the seventh target image, and the k+1th fourth target image is the eighth target image.

[0114] S106: Superimposing the sixth target image and the eighth target image to obtain a fifth target image, wherein the superimposing process retains pixels with higher brightness in the sixth target image or the eighth target image.

[0115] It can be understood that the j images extracted in the above steps can be superimposed into k images in this way, and the specific method is the same as the above steps, or the average grayscale value of the entire image of the seventh target image is obtained, and then the image calibration is performed on the fifth target image based on the average grayscale value of the seventh target image, so that the average grayscale value of the entire image of the fifth target image is the same as the average grayscale value of the entire image of the seventh target image. The specific process is not repeated here.

[0116] A CT image enhancement method based on pneumonia image diagnosis proposed in an embodiment of the present application first obtains a total of m CT tomographic images, determines the n-1th CT tomographic image as the first target image, the nth CT tomographic image as the second target image, and the n+1th CT tomographic image as the third target image from the m CT tomographic images, and then superimposes the first target image with the third target image to obtain the fourth target image, wherein the superposition process retains pixels with higher brightness in the first target image or the third target image, and finally obtains j fourth target images based on the m CT tomographic images and displays them. A CT image enhancement method based on pneumonia image diagnosis proposed in the present application performs interval extraction and superposition on a group of CT tomographic images, so that the superimposed image has clearer diffusion patterns and medical staff can observe more clearly.

[0117] Based on the same inventive concept, the present application also proposes a CT image enhancement system based on pneumonia image diagnosis, which is configured as follows:

[0118] A total of m CT scan images are obtained, where m is a natural number greater than or equal to 3;

[0119] Determine from m CT tomographic images that the n-1th CT tomographic image is the first target image, the nth CT tomographic image is the second target image, and the n+1th CT tomographic image is the third target image, wherein n is a natural number greater than or equal to 1 and mn≥1;

[0120] Superimposing the first target image and the third target image to obtain a fourth target image, wherein the superimposition process retains pixels with higher brightness in the first target image or the third target image;

[0121] Based on m CT tomography images, j fourth target images are acquired and displayed, wherein j is a natural number and j=m-2.

[0122] In some embodiments, the system is configured to:

[0123] Acquiring and displaying j fourth target images based on m CT scan images, wherein j is a natural number and j=m-2, comprises:

[0124] Obtaining the average grayscale value of the entire second target image;

[0125] Image calibration is performed on the fourth target image based on the average grayscale value of the entire second target image, so that the average grayscale value of the entire fourth target image is the same as the average grayscale value of the entire second target image.

[0126] In some embodiments, the system is configured to:

[0127] Acquiring and displaying j fourth target images based on m CT tomography images, wherein j is a natural number and j=m-2, further comprising:

[0128] Obtaining an average contrast value of the entire second target image;

[0129] Image calibration is performed on the fourth target image based on the average contrast value of the entire second target image, so that the average contrast value of the entire fourth target image is the same as the average contrast value of the entire second target image.

[0130] In some embodiments, the system is configured to:

[0131] Acquiring and displaying j fourth target images based on m CT tomography images, wherein j is a natural number and j=m-2, further comprising:

[0132] In response to the user's operation and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2.

[0133] In some embodiments, the system is configured to:

[0134] In response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including:

[0135] Determine from the j fourth target images that the k-1th CT tomography image is the sixth target image, the kth fourth target image is the seventh target image, and the k+1th fourth target image is the eighth target image;

[0136] The sixth target image is superimposed on the eighth target image to obtain a fifth target image, wherein the superimposition process retains pixels with higher brightness in the sixth target image or the eighth target image.

[0137] In some embodiments, the system is configured to:

[0138] In response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including:

[0139] Obtaining the average grayscale value of the entire seventh target image;

[0140] Image calibration is performed on the fifth target image based on the average grayscale value of the seventh target image, so that the average grayscale value of the entire fifth target image is the same as the average grayscale value of the entire seventh target image.

[0141] In some embodiments, the system is configured to:

[0142] The first target image and the third target image are superimposed to obtain a fourth target image, wherein the superimposition process retains pixels with higher brightness in the first target image or the third target image, including:

[0143] Segmenting the first target image to form a plurality of first sub-images, wherein the sizes of the first sub-images are preset sizes;

[0144] Acquire a first non-target image in the first target image, where the first non-target image is an image composed of a plurality of first sub-images in a non-discrete state in the first target image;

[0145] Segmenting the third target image to form a plurality of second sub-images, wherein the second sub-images correspond one-to-one to the first sub-images;

[0146] Acquire a second non-target image in the second target image, where the second non-target image is an image composed of a plurality of second sub-images in a non-discrete state in the first target image;

[0147] The first non-target image is compared with the second non-target image, and according to the comparison result, the first non-target image or the second non-target image is retained in the fourth target image.

[0148] In some embodiments, the system is configured to:

[0149] Comparing the first non-target image with the second non-target image, and retaining the first non-target image or the second non-target image in the fourth target image according to a result of the comparison, comprises:

[0150] Based on a first number of first sub-images constituting the first non-target image and a second number of second sub-images constituting the second non-target image, it is determined whether to retain the first non-target image or the second non-target image in the fourth target image, wherein:

[0151] When the first number is greater than the second number, determining to retain the first non-target image in the fourth target image;

[0152] When the second number is greater than the first number, determining to retain the second non-target image in the fourth target image;

[0153] When the first number is the same as the second number, the first non-target image and the second non-target image are retained at the same time.

[0154] The embodiment of the present application proposes a CT image enhancement system based on pneumonia image diagnosis. First, a total of m CT tomographic images are acquired. The n-1th CT tomographic image is determined as the first target image, the nth CT tomographic image is determined as the second target image, and the n+1th CT tomographic image is determined as the third target image from the m CT tomographic images. Then, the first target image and the third target image are superimposed to obtain the fourth target image, wherein the superposition process retains the pixels with higher brightness in the first target image or the third target image. Finally, j fourth target images are acquired and displayed based on the m CT tomographic images. The present application proposes a CT image enhancement system based on pneumonia image diagnosis. By performing interval extraction and superposition on a group of CT tomographic images, the superimposed image is clearer for the diffusion pattern, which makes it clearer for medical staff to observe.

[0155] Based on the same inventive concept, an embodiment of the present application further proposes an electronic device, the electronic device comprising:

[0156] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the CT image enhancement method based on pneumonia image diagnosis according to an embodiment of the present application.

[0157] In addition, to achieve the above-mentioned purpose, an embodiment of the present application also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the CT image enhancement method based on pneumonia image diagnosis of an embodiment of the present application.

[0158] The following is a detailed introduction to the various components of electronic equipment:

[0159] The processor is the control center of the electronic device, which may be a processor or a general term for multiple processing elements. For example, the processor is one or more central processing units (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (DSP), or one or more field programmable gate arrays (FPGA).

[0160] Optionally, the processor can perform various functions of the electronic device by running or executing a software program stored in the memory, and calling data stored in the memory.

[0161] The memory is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0162] Optionally, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor, or may exist independently and be coupled to the processor through an interface circuit of the electronic device, which is not specifically limited in the embodiments of the present invention.

[0163] A transceiver is used to communicate with a network device or a terminal device.

[0164] Optionally, the transceiver may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0165] Optionally, the transceiver may be integrated with the processor, or may exist independently and be coupled to the processor via an interface circuit of the router, which is not specifically limited in the embodiment of the present invention.

[0166] In addition, the technical effects of the electronic device can refer to the technical effects of the data transmission method in the above method embodiment, which will not be repeated here.

[0167] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0168] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0169] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0170] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0171] In the present invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0172] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0173] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

Claims

1. A CT image enhancement method based on pneumonia image diagnosis, characterized in that: The method comprises: A total of m CT scan images are obtained, where m is a natural number greater than or equal to 3; Determine from the m CT tomography images that the n-1th CT tomography image is the first target image, the nth CT tomography image is the second target image, and the n+1th CT tomography image is the third target image, wherein n is a natural number greater than or equal to 1 and mn≥1; superimposing the first target image and the third target image to obtain a fourth target image, wherein the superimposition process retains pixels with higher brightness in the first target image or the third target image; Segmenting the first target image to form a plurality of first sub-images, wherein the sizes of the first sub-images are preset sizes; Acquire a first non-target image in the first target image, where the first non-target image is an image composed of a plurality of the first sub-images in a non-discrete state in the first target image; Segmenting the third target image to form a plurality of second sub-images, wherein the second sub-images correspond one-to-one to the first sub-image; Acquire a second non-target image in the second target image, where the second non-target image is an image composed of a plurality of the second sub-images in a non-discrete state in the first target image; The first non-target image is compared with the second non-target image, and according to the comparison result, the first non-target image or the second non-target image is retained in the fourth target image; based on m CT tomography images, j fourth target images are acquired and displayed, where j is a natural number and j=m-2.

2. A CT image enhancement method based on pneumonia image diagnosis according to claim 1, characterized in that: Acquiring and displaying j fourth target images based on m CT scan images, wherein j is a natural number and j=m-2, comprises: Obtaining an average grayscale value of the entire second target image; Based on the average grayscale value of the entire second target image, image calibration is performed on the fourth target image so that the average grayscale value of the entire fourth target image is the same as the average grayscale value of the entire second target image.

3. A CT image enhancement method based on pneumonia image diagnosis according to claim 2, characterized in that: Based on m CT scan images, j fourth target images are acquired and displayed, wherein j is a natural number and j=m-2, and further includes: Obtaining an average contrast value of the entire second target image; Image calibration is performed on the fourth target image based on the average contrast value of the entire second target image, so that the average contrast value of the entire fourth target image is the same as the average contrast value of the entire second target image.

4. A CT image enhancement method based on pneumonia image diagnosis according to claim 2, characterized in that: After acquiring and displaying j fourth target images based on m CT tomography images, wherein j is a natural number and j=m-2, the method further includes: In response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, wherein k is a natural number and k=j-2.

5. A CT image enhancement method based on pneumonia image diagnosis according to claim 4, characterized in that: In response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including: Determine from the j fourth target images that the k-1th CT tomography image is the sixth target image, the kth fourth target image is the seventh target image, and the k+1th fourth target image is the eighth target image; The sixth target image is superimposed with the eighth target image to obtain a fifth target image, wherein the superimposition process retains pixels with higher brightness in the sixth target image or the eighth target image.

6. A CT image enhancement method based on pneumonia image diagnosis according to claim 5, characterized in that: In response to the operation of the user and based on the j fourth target images, k fifth target images are acquired and displayed, where k is a natural number and k=j-2, including: Obtaining an average grayscale value of the entire seventh target image; Based on the average grayscale value of the seventh target image, image calibration is performed on the fifth target image so that the average grayscale value of the entire fifth target image is the same as the average grayscale value of the entire seventh target image.

7. A CT image enhancement method based on pneumonia image diagnosis according to claim 6, characterized in that: Comparing the first non-target image with the second non-target image, and retaining the first non-target image or the second non-target image in the fourth target image according to a result of the comparison, comprises: Based on a first number of the first sub-images constituting the first non-target image and a second number of the second sub-images constituting the second non-target image, it is determined whether to retain the first non-target image or the second non-target image in the fourth target image, wherein: When the first number is greater than the second number, determining to retain the first non-target image in the fourth target image; When the second number is greater than the first number, determining to retain the second non-target image in the fourth target image; When the first number is the same as the second number, the first non-target image and the second non-target image are simultaneously retained.

8. A CT image enhancement system based on pneumonia image diagnosis, characterized in that: The system is configured to: A total of m CT scan images are obtained, where m is a natural number greater than or equal to 3; Determine from the m CT tomography images that the n-1th CT tomography image is the first target image, the nth CT tomography image is the second target image, and the n+1th CT tomography image is the third target image, wherein n is a natural number greater than or equal to 1 and mn≥1; superimposing the first target image and the third target image to obtain a fourth target image, wherein the superimposition process retains pixels with higher brightness in the first target image or the third target image; Segmenting the first target image to form a plurality of first sub-images, wherein the sizes of the first sub-images are preset sizes; Acquire a first non-target image in the first target image, where the first non-target image is an image composed of a plurality of the first sub-images in a non-discrete state in the first target image; Segmenting the third target image to form a plurality of second sub-images, wherein the second sub-images correspond one-to-one to the first sub-image; Acquire a second non-target image in the second target image, where the second non-target image is an image composed of a plurality of the second sub-images in a non-discrete state in the first target image; The first non-target image is compared with the second non-target image, and according to the comparison result, the first non-target image or the second non-target image is retained in the fourth target image; based on m CT tomography images, j fourth target images are acquired and displayed, where j is a natural number and j=m-2.

9. An electronic device, characterized in that: include: at least one processor; And, a memory communicatively connected to at least one of the processors; wherein the memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the method proposed in any one of claims 1-7.

Images