Tissue image processing method and device, computer device, storage medium and product

Abstract

The application relates to a tissue image processing method and device, computer equipment, a storage medium and a product. The method comprises the following steps: acquiring image data of a patient examination, obtaining a tissue image by intercepting the image data based on a preset area; processing the tissue image by using a target area extraction function to obtain a first processing image; after a preset time interval, processing the tissue image again by using the target area extraction function to obtain a second processing image; detecting whether the second processing image includes a lesion area, and if yes, saving the second processing image; acquiring the similarity between the first processing image and the second processing image; and verifying the target area extraction function according to the similarity. The method can accurately verify the lesion area extraction function, and if the lesion area extraction function passes the verification, the first processing image successfully extracting the lesion area can be accurately obtained.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an image processing method, apparatus, computer equipment, storage medium, and product. Background Technology

[0002] With the development of image processing technology, tissue image processing technology can be used to automatically extract lesion tissue from the test object, thereby obtaining an image of the extracted lesion tissue. Therefore, in order to ensure the accuracy of the lesion tissue obtained by doctors, it is necessary to ensure the accuracy of the lesion tissue extracted by tissue image processing technology.

[0003] However, current tissue image processing methods suffer from low accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a tissue image processing method, apparatus, computer equipment, storage medium, and product to address the aforementioned technical problems, which can improve the accuracy of extracting lesions from tissue images.

[0005] In a first aspect, this application provides an image processing method for tissue analysis, comprising:

[0006] A tissue image processing method, characterized in that the method is applied to verify a target region extraction function, wherein the target region extraction function is used to extract target regions in a tissue image, the target regions including lesion regions; the method includes:

[0007] Acquire image data from the patient's examination, and obtain tissue images by cropping the image data based on a preset region;

[0008] The tissue image is processed using the target region extraction function to obtain a first processed image;

[0009] At preset time intervals, the tissue image is processed again using the target region extraction function to obtain a second processed image;

[0010] Detect whether the second processed image includes a lesion area; if so, save the second processed image.

[0011] Obtain the similarity between the first processed image and the second processed image;

[0012] The target region extraction function is verified based on the similarity.

[0013] In one embodiment, detecting whether the second processed image includes a lesion region, and if so, saving the second processed image, includes:

[0014] Detect whether the biological tissue in the second processed image includes lesion tissue;

[0015] If it is determined that the biological tissue in the second processed image includes the lesion tissue, then the second processed image is saved.

[0016] In one embodiment, detecting whether the biological tissue in the second processed image includes lesion tissue includes:

[0017] A portion of the processed image containing tissue is extracted to obtain a target image of the portion of the image.

[0018] Based on whether the average pixel value of each pixel in the target image is within a preset pixel range, it is determined whether the biological tissue in the second processed image includes the lesion tissue.

[0019] In one embodiment, obtaining the similarity between the first processed image and the second processed image includes:

[0020] Using the second processed image as the original image and the first processed image as the template image, the number of all pixels in the first processed image is obtained.

[0021] The template matching algorithm is used to match the first processed image and the second processed image to obtain the target pixels that are successfully matched;

[0022] The similarity between the first processed image and the second processed image is calculated based on the number of target pixels and the total number of pixels in the first processed image.

[0023] In one embodiment, the method further includes:

[0024] Determine the similarity between the tissue image and the first processed image;

[0025] The function of verifying the target region extraction based on the similarity includes:

[0026] The target region extraction function is verified based on the similarity between the tissue image and the first processed image, and the similarity between the first processed image and the second processed image.

[0027] In one embodiment, verifying the target region extraction function based on the similarity between the tissue image and the first processed image, and the similarity between the first processed image and the second processed image, includes:

[0028] If the similarity between the first processed image and the second processed image is greater than a first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than a second preset similarity threshold, then the lesion region extraction function is determined to have passed verification.

[0029] Secondly, this application also provides an image processing apparatus for tissue analysis, comprising:

[0030] The tissue image acquisition module is used to acquire image data from a patient's examination and to obtain a tissue image by cropping the image data based on a preset region.

[0031] The first image processing module is used to process the tissue image using the target region extraction function to obtain a first processed image;

[0032] The second image processing module is used to process the tissue image again using the target region extraction function at preset intervals to obtain a second processed image.

[0033] The detection module is used to detect whether the second processed image includes a lesion area; if so, the second processed image is saved.

[0034] A similarity acquisition module is used to acquire the similarity between the first processed image and the second processed image;

[0035] The verification module is used to verify the target region extraction function based on the similarity.

[0036] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method in any of the embodiments of the first aspect described above.

[0037] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0038] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0039] The aforementioned tissue image processing method, apparatus, computer equipment, storage medium, and product acquire image data from a patient's examination, crop the image data based on a preset region to obtain a tissue image; process the tissue image using a target region extraction function to obtain a first processed image; process the tissue image again using the target region extraction function at a preset time interval to obtain a second processed image; detect whether the second processed image includes a lesion region; if so, save the second processed image; obtain the similarity between the first processed image and the second processed image; and verify the target region extraction function based on the similarity. Since this application can use the target region extraction function to process tissue images to obtain a first processed image and a second processed image, and the first processed image refers to the image obtained by extracting lesion tissue from the tissue image within a specified time period, the embodiments of this application can accurately verify the lesion region extraction function based on the similarity between the first processed image and the second processed image that accurately extracts the lesion tissue. If the lesion region extraction function passes the verification, it indicates that the first processed image is an image that successfully extracts the lesion region, that is, the first processed image with successfully extracted lesion region can be accurately obtained. Furthermore, it can accurately and automatically test whether the lesion area can be extracted from the tissue image within a specified time period, solving the misjudgment problem caused by various factors in neurosurgical software in related technologies, and improving the accuracy of automated testing of lesion tissue extraction performance. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is an application environment diagram of an organization image processing method in one embodiment;

[0042] Figure 2 This is a flowchart illustrating an image processing method in one embodiment;

[0043] Figure 3 This is a schematic diagram of an organized image in one exemplary embodiment;

[0044] Figure 4 This is a schematic diagram of a first processed image in an exemplary embodiment;

[0045] Figure 5 This is a schematic diagram of the second processed image in one exemplary embodiment;

[0046] Figure 6This is a flowchart illustrating the detection steps in one embodiment;

[0047] Figure 7 This is a schematic diagram of the target image in one exemplary embodiment;

[0048] Figure 8 This is a flowchart illustrating the similarity determination steps in one embodiment;

[0049] Figure 9 This is a flowchart illustrating an image processing method in another embodiment;

[0050] Figure 10 This is a flowchart illustrating an image processing method in one optional embodiment;

[0051] Figure 11 This is a structural block diagram of an image processing apparatus in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0054] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0055] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0056] With the development of image processing technology, tissue image processing techniques can be used to automatically extract lesions from the subject, thereby obtaining images of the extracted lesions. For example, neurosurgical software can be used to automatically extract various lesions from patients, such as hematomas, blood vessels, and brain parenchyma. Therefore, to ensure the accuracy of the lesion tissue obtained by doctors, it is necessary to ensure the accuracy of lesion tissue extraction using tissue image processing techniques.

[0057] However, current tissue image processing methods may not be able to extract images of lesion tissue within a preset time period, thus resulting in low accuracy.

[0058] The process of extracting lesion tissue has specific performance indicators, and these indicators may change with the version of neurosurgical software or functional upgrades. If the performance indicators change, it may affect the stability of the lesion tissue extraction performance. Therefore, in order to ensure the stability of the lesion tissue extraction performance, it is necessary to conduct automated testing of the lesion tissue extraction performance.

[0059] Current methods for automating the testing of lesion tissue extraction performance involve taking screenshots of the extraction process. However, this method is prone to inconsistencies due to various factors in neurosurgical software, such as loading, interface refresh, and mouse cursor movements, leading to misjudgments. Therefore, current methods for automating lesion tissue extraction performance suffer from low accuracy.

[0060] After introducing the background technology of the tissue image processing method provided in the embodiments of this application, the implementation environment involved in the tissue image processing method provided in the embodiments of this application will be briefly described below. The tissue image processing method provided in the embodiments of this application can be applied to, for example... Figure 1The computer device shown can be a terminal or a server. It includes a processor, memory, input / output interfaces, a communication interface, a display unit, and input devices. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input devices are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements an image processing method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0061] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. A specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0062] In one embodiment, such as Figure 2 As shown, a tissue image processing method is provided, which is applied to the verification of a target region extraction function. The target region extraction function is used to extract target regions from a tissue image, including lesion regions. This method is then applied to… Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0063] S201: Acquire the patient's examination image data, and extract tissue images by cropping the image data based on a preset region.

[0064] In this embodiment, optionally, the computer device can pre-acquire patient examination image data from a database; alternatively, the computer device can also scan the patient using a preset scanning method to obtain patient examination image data. The preset scanning method may include, but is not limited to, CT (Computed Tomography), PET (Positron Emission Computed Tomography), or MR (Magnetic Resonance) scanning methods. Of course, this embodiment does not limit the implementation method for obtaining patient examination image data. Furthermore, the computer device can select a preset region from the patient examination image data. Thus, when the neurosurgical software reaches the tissue extraction interface, the computer device can extract image data from the preset region where tissue extraction of the lesion tissue has not yet been performed, obtaining a tissue image. For example, Figure 3 As shown, Figure 3 This is a schematic diagram of a tissue image in an exemplary embodiment. A tissue image refers to a medical image screenshot before tissue extraction of the lesion tissue.

[0065] S202, The tissue image is processed using the target region extraction function to obtain the first processed image.

[0066] In this embodiment, the computer device, in response to a user's triggering of a tissue extraction operation via clicking or touching the screen, processes the tissue image using a target region extraction function to obtain a first processed image. For example, in response to a user's triggering of a tissue extraction operation via clicking or touching the screen, the computer device can use the target region extraction function to extract lesion tissue from the tissue image, and, during a specified time period while the tissue extraction operation is being performed, capture the medical image from the neurosurgical software interface at that time to obtain the first processed image. Wherein, as... Figure 4 As shown, Figure 4 This is a schematic diagram of a first processed image in an exemplary embodiment. The first processed image refers to an image obtained by extracting lesion tissue from a tissue image within a specified time period.

[0067] S203, after a preset time interval, the tissue image is processed again using the target region extraction function to obtain a second processed image.

[0068] In this embodiment of the application, optionally, after a preset time interval, the computer device can again process the tissue image using the target region extraction function to obtain a second processed image. Alternatively, the computer device can directly capture the processed tissue image after a preset time interval to obtain the second processed image. For example, the computer device can pause the neurosurgical software for a preset time and then capture the medical image of the neurosurgical software interface at that time to obtain the second processed image. The preset time needs to be greater than the time for tissue extraction. Of course, the preset time can be set according to the actual time of tissue extraction; this embodiment of the application does not limit this. For example, the preset time can be 30 seconds. Figure 5 As shown, Figure 5 This is a schematic diagram of the second processed image in an exemplary embodiment. The second processed image refers to the extracted image obtained by taking a screenshot after successfully extracting lesion tissue from the tissue image. The extraction time of the second processed image is longer than that of the first processed image.

[0069] S204, Detect whether the second processed image includes the lesion area; if so, save the second processed image.

[0070] In this embodiment, since the preset time corresponding to the second processed image is greater than the time for tissue extraction, the second processed image can generally be identified as an image in which the lesion tissue has been successfully extracted. To further determine whether the second processed image accurately extracts the lesion tissue, the computer device can also detect whether the second processed image includes the lesion region. If the second processed image is detected to include the lesion region, the computer device can determine that the second processed image accurately extracts the lesion tissue and can save the second processed image.

[0071] S205, obtain the similarity between the first processed image and the second processed image.

[0072] In this embodiment of the application, the computer device can use a similarity calculation method to determine the similarity between the first processed image and the second processed image from which the lesion tissue is accurately extracted. The similarity calculation method may include, but is not limited to, any one of the following methods: hash algorithm, template matching algorithm, or Euclidean distance calculation method. Of course, this embodiment of the application does not limit the similarity calculation method.

[0073] S206, Target region extraction function verified based on similarity.

[0074] In this embodiment, the computer device can compare the similarity between the first processed image and the second processed image with a preset similarity threshold to obtain a comparison result. If the comparison result indicates that the similarity between the first processed image and the second processed image is greater than the preset similarity threshold, the computer device can determine that the lesion region extraction function has passed verification, meaning that lesion tissue can be successfully extracted within a specified time period. If the comparison result indicates that the similarity between the first processed image and the second processed image is less than or equal to the preset similarity threshold, the computer device can determine that the lesion region extraction function has failed verification, meaning that lesion tissue cannot be successfully extracted within a specified time period. Of course, this embodiment does not limit the specific value of the preset similarity threshold. It should be noted that, to avoid interference from other tissues, after each verification of a single lesion region extraction function, the image corresponding to that single lesion region needs to be deleted before verifying or testing other lesion region extraction functions.

[0075] In the above-described tissue image processing method, image data of a patient's examination is acquired, and a tissue image is obtained by cropping the image data based on a preset region; the tissue image is processed using a target region extraction function to obtain a first processed image; after a preset time interval, the tissue image is processed again using the target region extraction function to obtain a second processed image; it is detected whether the second processed image includes a lesion region, and if so, the second processed image is saved; the similarity between the first processed image and the second processed image is obtained; and the target region extraction function is verified based on the similarity. Since this application can use the target region extraction function to process tissue images to obtain a first processed image and a second processed image, and the first processed image refers to the image obtained by extracting lesion tissue from the tissue image within a specified time period, the embodiments of this application can accurately verify the lesion region extraction function based on the similarity between the first processed image and the second processed image that accurately extracts the lesion tissue. If the lesion region extraction function passes the verification, it indicates that the first processed image is an image that successfully extracts the lesion region, that is, the first processed image that successfully extracts the lesion region can be accurately obtained. Furthermore, it can accurately and automatically test whether the lesion area can be extracted from the tissue image within a specified time period, solving the misjudgment problem caused by various factors in neurosurgical software in related technologies, and improving the accuracy of automated testing of lesion tissue extraction performance.

[0076] In one embodiment, a method is provided for performing verification only after the detection passes, such as... Figure 6 As shown, the step S204 above, "detecting whether the second processed image includes a lesion area, and if so, saving the second processed image," includes:

[0077] S301, Detect whether the biological tissue in the second processed image includes lesion tissue.

[0078] S302, if it is determined that the biological tissue in the second processed image includes lesion tissue, then the second processed image is saved.

[0079] In this embodiment, after acquiring the second processed image, the computer device can detect whether the biological tissue in the second processed image includes lesion tissue. If lesion tissue is detected in the biological tissue of the second processed image, the computer device can determine that the second processed image accurately extracts the lesion tissue and can save the second processed image. If lesion tissue is detected not in the biological tissue of the second processed image, the computer device can determine that the second processed image does not accurately extract the lesion tissue, that is, the second processed image is an image that was not successfully loaded or not fully loaded, and can discard the second processed image. In this case, the computer device does not need to verify the lesion area extraction function, can directly consider the verification to have failed, and can reacquire a new second processed image, thereby re-verifying the lesion area extraction function based on the new second processed image.

[0080] In one embodiment, a method is provided for detecting whether the biological tissue in the second processed image includes lesion tissue, namely, "detecting whether the biological tissue in the second processed image includes lesion tissue" in S301 above, which includes:

[0081] A portion of the image containing tissue is extracted from the second processed image to obtain the target image of that portion.

[0082] Based on whether the average pixel value of each pixel in the target image is within a preset pixel range, it is determined whether the biological tissue in the second processed image includes lesion tissue.

[0083] Among them, such as Figure 7 As shown, Figure 7 This is a schematic diagram of the target image in an exemplary embodiment. The target image refers to an image obtained by cropping a portion of the second processed image containing tissue. The average pixel value of each pixel in the target image refers to the average pixel value of multiple channels corresponding to each pixel in the target image. The preset pixel range can be set according to actual image requirements; however, this embodiment does not limit the specific value of the preset pixel range.

[0084] In this embodiment, since tissue is extracted from fixed data and a fixed sequence, the location of the tissue region in the second processed image will not change. Assuming that tissue exists in the second processed image beforehand, the computer device can crop a portion of the second processed image containing tissue to obtain a target image corresponding to that portion. Then, the computer device can calculate the average pixel value of each pixel in the target image based on the pixel values ​​of multiple channels corresponding to each pixel, and can detect whether the average pixel value of each pixel in the target image is within a preset pixel range. If the average pixel value of each pixel in the target image is detected to be within the preset pixel range, it can be determined that the biological tissue in the second processed image includes lesion tissue; if the average pixel value of each pixel in the target image is detected to be outside the preset pixel range, it can be determined that the biological tissue in the second processed image does not include lesion tissue.

[0085] In this embodiment, it can be detected whether the biological tissue in the second processed image includes lesion tissue. If it is determined that the biological tissue in the second processed image includes lesion tissue, the second processed image is saved. Thus, through the above detection process, it can be ensured that the second processed image accurately extracts the lesion tissue, thereby guaranteeing the accuracy of the second processed image. Furthermore, the lesion region extraction function can only be verified if the second processed image contains lesion tissue, thereby improving the accuracy of automated verification of the lesion region extraction function.

[0086] In one embodiment, an implementation method for obtaining the similarity between a first processed image and a second processed image is provided, namely, "obtaining the similarity between the first processed image and the second processed image" in S205 above, including:

[0087] Using the second processed image as the original image and the first processed image as the template image, the number of all pixels in the first processed image is obtained.

[0088] A template matching algorithm is used to match the first processed image with the second processed image to obtain the target pixels that are successfully matched.

[0089] The similarity between the first processed image and the second processed image is calculated based on the number of target pixels and the total number of pixels in the first processed image.

[0090] In the embodiments of this application, such as Figure 8 As shown, Figure 8As a flowchart illustrating the similarity determination steps in one embodiment, in step S801, the computer device can use the second processed image as the original image and the first processed image as the template image, and can obtain the total number of pixels in the first processed image. In step S802, the computer device can use a template matching algorithm to match the first processed image and the second processed image according to a standard correlation coefficient matching method, obtaining successfully matched target pixels. Here, successfully matched target pixels refer to pixels with a similarity greater than 99%. Based on the successfully matched target pixels, the coordinates and the total number of successfully matched target pixels can be determined. In step S803, the computer device can divide the number of target pixels by the total number of pixels in the first processed image to calculate the similarity between the first processed image and the second processed image.

[0091] In this embodiment, the second processed image can be used as the original image, and the first processed image can be used as the template image. The number of all pixels in the first processed image is obtained, and then a template matching algorithm is used to match the first processed image and the second processed image to obtain the successfully matched target pixels. Thus, the similarity between the first processed image and the second processed image can be accurately calculated based on the number of target pixels and the total number of pixels in the first processed image.

[0092] In one embodiment, an implementation method is provided for determining the similarity between an tissue image and a first processed image, such as... Figure 9 As shown, the above-mentioned tissue image processing method further includes:

[0093] S207, determine the similarity between the tissue image and the first processed image.

[0094] In this embodiment of the application, the computer device can also determine the similarity between the tissue image and the first processed image based on a template matching algorithm. Optionally, the computer device can directly determine the similarity between the tissue image and the first processed image based on the template matching algorithm; or, the computer device can first use the template matching algorithm to determine the successfully matched target pixels, and then determine the similarity between the tissue image and the first processed image based on the successfully matched target pixels and all pixels of the tissue image.

[0095] S206 includes:

[0096] S208, verify the target region extraction function based on the similarity between the tissue image and the first processed image, and the similarity between the first processed image and the second processed image.

[0097] Optionally, in this embodiment, the computer device can compare the first similarity between the tissue image and the first processed image with a first preset similarity threshold to obtain a first comparison result, and compare the second similarity between the first processed image and the second processed image with a second preset similarity threshold to obtain a second comparison result. Based on the first and second comparison results, the target region extraction function is verified to obtain a verification result. Alternatively, the computer device can compare both the first and second similarities with a third preset similarity threshold to obtain a comparison result, and based on the comparison result, the target region extraction function is verified to obtain a verification result. The verification result may include verification passed or verification failed. Of course, this embodiment does not limit the specific values ​​of the first, second, and third preset similarity thresholds.

[0098] In this embodiment, based on the template matching algorithm, the similarity between the tissue image and the first processed image can be accurately determined. Thus, the target region extraction function can be verified more accurately based on the similarity between the tissue image and the first processed image, as well as the similarity between the first processed image and the second processed image.

[0099] In one embodiment, an implementation method for verifying the lesion region extraction function is provided, namely, "verifying the target region extraction function based on the similarity between the tissue image and the first processed image, and the similarity between the first processed image and the second processed image" in S208 above, including:

[0100] If the similarity between the first processed image and the second processed image is greater than the first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than the second preset similarity threshold, then the lesion region extraction function is verified.

[0101] In this embodiment, after determining the first similarity between the tissue image and the first processed image, and the second similarity between the first processed image and the second processed image, the computer device can compare the first similarity between the tissue image and the first processed image with a first preset similarity threshold to obtain a first comparison result, and compare the second similarity between the first processed image and the second processed image with a second preset similarity threshold to obtain a second comparison result. If the first comparison result indicates that the first similarity is less than the first preset similarity threshold, and the second comparison result indicates that the second similarity is greater than the second preset similarity threshold, that is, it means that the tissue image and the first processed image are largely dissimilar, and the first processed image and the second processed image are similar, then the computer device can determine that the lesion area extraction function has passed verification, that is, it means that the lesion tissue can be successfully extracted within a specified time period.

[0102] If the first comparison result indicates that the first similarity is greater than or equal to the first preset similarity threshold, or if the second comparison result indicates that the second similarity is less than or equal to the second preset similarity threshold, then the computer device can determine that the lesion region extraction function has failed verification, meaning that lesion tissue cannot be successfully extracted within the specified time period. Since the tissue image before extraction differs significantly from the first processed image of the extracted tissue, to avoid performance test failure due to function modification, the first preset similarity threshold can be set to 60% in this embodiment; the second preset similarity threshold can be 95%. Of course, this application embodiment does not limit the specific values ​​of the first and second preset similarity thresholds.

[0103] In this embodiment, if the similarity between the first processed image and the second processed image is greater than the first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than the second preset similarity threshold, then the lesion region extraction function can be determined to have passed the verification. That is, based on the first comparison result of the first similarity and the first preset similarity threshold, and the second comparison result of the second similarity and the second preset similarity threshold, it can accurately and automatically test whether the lesion tissue can be extracted from the tissue image within a specified time period. This solves the misjudgment problem caused by various factors in neurosurgical software in related technologies and can improve the accuracy of automated testing of lesion tissue extraction performance.

[0104] In an optional embodiment, such as Figure 10 As shown, an image processing method for organizing an image is provided, applied to a computer device, including:

[0105] S1001: Acquire the patient's examination image data, and obtain a tissue image by cropping the image data based on a preset region;

[0106] S1002, The tissue image is processed using the target region extraction function to obtain the first processed image;

[0107] S1003, after a preset time interval, the tissue image is processed again using the target region extraction function to obtain a second processed image;

[0108] S1004, Extract a portion of the tissue in the second processed image to obtain a target image of the portion of the image;

[0109] S1005, determine whether the biological tissue in the second processed image includes lesion tissue based on whether the average pixel value of each pixel in the target image is within a preset pixel range;

[0110] S1006, If it is determined that the biological tissue in the second processed image includes lesion tissue, then the second processed image is saved;

[0111] S1007 If it is determined that the biological tissue in the second processed image does not include lesion tissue, the second processed image is discarded. At this time, there is no need to verify the lesion area extraction function. It can be directly considered that the verification has failed, and a new second processed image can be obtained again. The lesion area extraction function can then be re-verified based on the new second processed image.

[0112] S1008, using the second processed image as the original image and the first processed image as the template image, obtain the number of all pixels in the first processed image;

[0113] A template matching algorithm is used to match the first processed image with the second processed image to obtain the target pixels that are successfully matched;

[0114] The second similarity between the first processed image and the second processed image is calculated based on the number of target pixels and the total number of pixels in the first processed image.

[0115] And, determine the first similarity between the tissue image and the first processed image;

[0116] S1009, if the similarity between the first processed image and the second processed image is greater than the first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than the second preset similarity threshold, then the lesion region extraction function is verified.

[0117] S1010, if the first similarity is greater than or equal to the first preset similarity threshold, or the second similarity is less than or equal to the second preset similarity threshold, then the lesion region extraction function is determined to have failed the verification.

[0118] For example, the tissue extraction time for vascular tissue is 20 seconds, the tissue extraction time for hematoma tissue is 10 seconds, and the tissue extraction time for brain parenchyma tissue is 16 seconds.

[0119] In the aforementioned tissue image processing method, since this application can utilize the target region extraction function to process the tissue image to obtain a first processed image and a second processed image, and the first processed image refers to the image obtained by extracting lesion tissue from the tissue image within a specified time period, the embodiments of this application can accurately verify the lesion region extraction function based on the similarity between the first processed image and the second processed image that accurately extracts the lesion tissue. If the lesion region extraction function passes the verification, it indicates that the first processed image is an image that successfully extracts the lesion region, that is, the first processed image that successfully extracts the lesion region can be accurately obtained. In addition, it can accurately and automatically test whether the lesion region can be extracted from the tissue image within a specified time period, solving the misjudgment problem caused by various factors of neurosurgical software in related technologies, and improving the accuracy of automated testing of lesion tissue extraction performance.

[0120] As can be seen from the above embodiments, this application uses image processing algorithms to perform image recognition on images before and after extraction of various lesion tissues, obtaining tissue images, first processed images, and second processed images. The tissue pixel values ​​are used to verify whether the second processed image contains lesion tissue. Furthermore, the first similarity between the tissue image and the first processed image can be compared with a first preset similarity threshold, and the second similarity between the first processed image and the second processed image can be compared with a second preset similarity threshold. Under the premise of ensuring that the second processed image contains lesion tissue, it can accurately test whether lesion tissue can be successfully extracted from the tissue image within a specified time period, and can ensure the scene consistency of the first processed image and the second processed image and the accuracy of the lesion area extraction function.

[0121] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0122] Based on the same inventive concept, this application also provides a tissue image processing apparatus for implementing the tissue image processing method described above. The solution provided by this apparatus is similar to the implementation described in the above method; therefore, the specific limitations in one or more tissue image processing apparatus embodiments provided below can be found in the limitations of the tissue image processing method described above, and will not be repeated here.

[0123] In one exemplary embodiment, such as Figure 11 As shown, an organ image processing apparatus is provided, comprising: an organ image acquisition module 31, a first processed image acquisition module 32, a second processed image acquisition module 33, a detection module 34, a similarity acquisition module 35, and a verification module 36, wherein:

[0124] The tissue image acquisition module 31 is used to acquire image data of the patient's examination and to obtain tissue images by cropping the image data based on a preset area.

[0125] The first image processing module 32 is used to process the tissue image using the target region extraction function to obtain the first processed image.

[0126] The second image processing module 33 is used to process the tissue image again using the target region extraction function at preset intervals to obtain a second processed image.

[0127] The detection module 34 is used to detect whether the second processed image includes a lesion area. If so, the second processed image is saved.

[0128] The similarity acquisition module 35 is used to acquire the similarity between the first processed image and the second processed image.

[0129] Verification module 36 is used to verify the target region extraction function based on similarity.

[0130] In one embodiment, the detection module 34 includes:

[0131] The detection unit is used to detect whether the biological tissue in the second processed image includes lesion tissue;

[0132] A storage unit is used to save the second processed image if it is determined that the biological tissue in the second processed image includes lesion tissue.

[0133] In one embodiment, the detection unit includes:

[0134] The target image acquisition subunit is used to extract a portion of the tissue in the second processed image to obtain a target image of that portion.

[0135] The detection subunit is used to determine whether the biological tissue in the second processed image includes lesion tissue based on whether the average pixel value of each pixel in the target image is within a preset pixel range.

[0136] In one embodiment, the similarity acquisition module 35 includes:

[0137] The quantity acquisition unit is used to take the second processed image as the original image and the first processed image as the template image to acquire the quantity of all pixels in the first processed image.

[0138] The target pixel acquisition unit is used to match the first processed image and the second processed image using a template matching algorithm to obtain the successfully matched target pixels;

[0139] The similarity calculation unit is used to calculate the similarity between the first processed image and the second processed image based on the number of target pixels and the total number of pixels in the first processed image.

[0140] In one embodiment, the tissue image processing apparatus further includes:

[0141] The first similarity determination module is used to determine the similarity between the tissue image and the first processed image;

[0142] Verification module 36 includes:

[0143] The verification unit is used to verify the target region extraction function based on the similarity between the tissue image and the first processed image, and the similarity between the first processed image and the second processed image.

[0144] In one embodiment, the verification unit includes:

[0145] The verification subunit is used to determine that the lesion region extraction function has passed verification if the similarity between the first processed image and the second processed image is greater than the first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than the second preset similarity threshold.

[0146] Each module in the aforementioned tissue image processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0147] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 1 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements an image processing method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0148] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0149] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0150] Acquire patient examination imaging data, and obtain tissue images by cropping the imaging data based on a preset region;

[0151] The tissue image is processed using the target region extraction function to obtain the first processed image;

[0152] At preset time intervals, the tissue image is processed again using the target region extraction function to obtain a second processed image;

[0153] Detect whether the second processed image includes the lesion area; if so, save the second processed image.

[0154] Obtain the similarity between the first processed image and the second processed image;

[0155] The function of extracting target regions is verified based on similarity.

[0156] In one embodiment, it is detected whether the second processed image includes a lesion area; if so, the second processed image is saved. The processor, when executing the computer program, also performs the following steps:

[0157] Detect whether the biological tissue in the second processed image includes lesion tissue;

[0158] If it is determined that the biological tissue in the second processed image includes lesion tissue, then the second processed image is saved.

[0159] In one embodiment, the processor, while executing a computer program, further performs the following steps to detect whether the biological tissue in the second processed image includes lesion tissue:

[0160] A portion of the image containing tissue is extracted from the second processed image to obtain a target image of that portion.

[0161] Based on whether the average pixel value of each pixel in the target image is within a preset pixel range, it is determined whether the biological tissue in the second processed image includes lesion tissue.

[0162] In one embodiment, the similarity between the first processed image and the second processed image is obtained, and the processor, when executing the computer program, further implements the following steps:

[0163] Using the second processed image as the original image and the first processed image as the template image, the number of all pixels in the first processed image is obtained.

[0164] A template matching algorithm is used to match the first processed image with the second processed image to obtain the target pixels that are successfully matched;

[0165] The similarity between the first processed image and the second processed image is calculated based on the number of target pixels and the total number of pixels in the first processed image.

[0166] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0167] Determine the similarity between the tissue image and the first processed image;

[0168] In addition to verifying the target region extraction function based on similarity, the processor also performs the following steps when executing the computer program:

[0169] The target region extraction function is verified based on the similarity between the tissue image and the first processed image, and the similarity between the first processed image and the second processed image.

[0170] In one embodiment, if the similarity meets a preset condition, the target region extraction function is verified based on the similarity between the tissue image and the first processed image, and the similarity between the first processed image and the second processed image. When the processor executes the computer program, it also performs the following steps:

[0171] If the similarity between the first processed image and the second processed image is greater than the first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than the second preset similarity threshold, then the lesion region extraction function is verified.

[0172] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0173] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0174] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0175] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0176] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A tissue image processing method, characterized in that, The method is applied to the verification of a target region extraction function, wherein the target region extraction function is used to extract target regions in tissue images, the target regions including lesion regions; the method includes: Acquire image data from the patient's examination, and obtain tissue images by cropping the image data based on a preset region; The tissue image is processed using the target region extraction function to obtain a first processed image; the first processed image refers to the image obtained by extracting lesion tissue from the tissue image within a specified time period; At a preset time interval, the tissue image is processed again using the target region extraction function to obtain a second processed image; the second processed image refers to the extracted image obtained by taking a screenshot after successfully extracting lesion tissue from the tissue image, and the extraction time of the second processed image is greater than the extraction time of the first processed image; the preset time is greater than the time for tissue extraction. Detect whether the second processed image includes a lesion area; if so, save the second processed image. Obtain the similarity between the first processed image and the second processed image; Determine the similarity between the tissue image and the first processed image; If the similarity between the first processed image and the second processed image is greater than a first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than a second preset similarity threshold, then the lesion region extraction function is determined to have passed verification.

2. The method according to claim 1, characterized in that, The step of detecting whether the second processed image includes a lesion area, and if so, saving the second processed image, includes: Detect whether the biological tissue in the second processed image includes lesion tissue; If it is determined that the biological tissue in the second processed image includes the lesion tissue, then the second processed image is saved.

3. The method according to claim 2, characterized in that, The detection of whether the biological tissue in the second processed image includes lesion tissue includes: A portion of the processed image containing tissue is extracted to obtain a target image of the portion of the image. Based on whether the average pixel value of each pixel in the target image is within a preset pixel range, it is determined whether the biological tissue in the second processed image includes the lesion tissue.

4. The method according to any one of claims 1-3, characterized in that, The step of obtaining the similarity between the first processed image and the second processed image includes: Using the second processed image as the original image and the first processed image as the template image, the number of all pixels in the first processed image is obtained. A template matching algorithm is used to match the first processed image and the second processed image to obtain the target pixels that are successfully matched; The similarity between the first processed image and the second processed image is calculated based on the number of target pixels and the total number of pixels in the first processed image.

5. A tissue image processing apparatus, characterized in that, The device includes: The tissue image acquisition module is used to acquire image data from a patient's examination and to obtain a tissue image by cropping the image data based on a preset region. The first image processing module is used to process the tissue image using the target region extraction function to obtain a first processed image; the first processed image refers to the image obtained by extracting lesion tissue from the tissue image within a specified time period; The second image processing module is used to process the tissue image again using the target region extraction function at preset intervals to obtain a second processed image. The second processed image refers to the extracted image obtained by taking a screenshot after successfully extracting lesion tissue from the tissue image. The extraction time of the second processed image is longer than the extraction time of the first processed image. The preset time is longer than the time for tissue extraction. The detection module is used to detect whether the second processed image includes a lesion area; if so, the second processed image is saved. A similarity acquisition module is used to acquire the similarity between the first processed image and the second processed image; The first similarity determination module is used to determine the similarity between the tissue image and the first processed image; The verification module is used to determine that the lesion region extraction function passes verification if the similarity between the first processed image and the second processed image is greater than a first preset similarity threshold, and the similarity between the tissue image and the first processed image is less than a second preset similarity threshold.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images