Hepatobiliary CT image recognition method, device and equipment

Abstract

The present application is applicable to the field of medical image recognition, and in particular, relates to a method, device and equipment for hepatobiliary CT image recognition. The hepatobiliary CT image recognition method is applied to a hepatobiliary CT image recognition device. The hepatobiliary CT image recognition device includes a touch screen, and the hepatobiliary CT image is displayed on the touch screen. The hepatobiliary CT image recognition method includes: after receiving a signal of a touch operation of the touch screen, determining the touch area of ​​the touch operation; recognizing the hepatobiliary CT image based on the touch area to obtain a recognition area; analyzing the recognition area to obtain an enlarged area; and enlarging and displaying the enlarged area on the touch screen. The method avoids the waste of resources caused by global processing and improves the recognition speed and efficiency by conducting an in-depth analysis of the touch area specified by the user, that is, through local recognition and intelligent analysis, the speed and accuracy of hepatobiliary CT image diagnosis are improved.

Description

Technical Field

[0001] The present application belongs to the field of medical image recognition technology, and in particular, relates to a method, device and equipment for hepatobiliary CT image recognition. Background Art

[0002] With the rapid development of medical imaging technology, hepatobiliary CT (computed tomography) images play an increasingly important role in clinical diagnosis. Hepatobiliary CT images can provide detailed anatomical information, helping doctors accurately detect and evaluate the health of organs such as the liver, gallbladder and bile duct. In addition, CT images can also be used to detect tumors, inflammation, stones and other diseases, providing an important basis for formulating treatment plans.

[0003] In the prior art, a model is usually used to automatically identify the entire hepatobiliary CT image. However, since there are multiple tissues or organs in the hepatobiliary CT image, in order to cover multiple tissues and organs, the existing automatic recognition model is often designed to be very complex, which not only increases the difficulty of training, but also reduces the speed and efficiency of real-time recognition. When the entire CT image is globally processed, many normal areas are also included in the analysis scope, resulting in unnecessary waste of computing resources, affecting the system's response speed and user experience. Summary of the invention

[0004] The embodiments of the present application provide a method, device and equipment for recognizing hepatobiliary CT images, which can solve the problem of low recognition speed and efficiency when recognizing hepatobiliary CT images.

[0005] In a first aspect, an embodiment of the present application provides a hepatobiliary CT image recognition method, which is applied to a hepatobiliary CT image recognition device, wherein the hepatobiliary CT image recognition device includes a touch display screen, and the hepatobiliary CT image is displayed on the touch display screen. The method includes:

[0006] After receiving the signal of the touch operation of the touch display screen, determining the touch area of ​​the touch operation; wherein the touch area is used to reflect the position of the user's touch in the hepatobiliary CT image;

[0007] The hepatobiliary CT image is identified based on the touch area to obtain an identification area; wherein the identification area is used to reflect the area that the user needs to observe;

[0008] Analyze according to the identified area to obtain an amplified area;

[0009] The enlarged area is enlarged and displayed on the touch display screen.

[0010] The above technical solutions in the embodiments of the present application have at least the following technical effects:

[0011] The hepatobiliary CT image recognition method provided by the present application determines the touch area of ​​the touch operation used to reflect the position of the user's touch in the hepatobiliary CT image after receiving the signal of the touch operation of the touch display screen; then the hepatobiliary CT image is recognized based on the touch area to obtain the recognition area used to reflect the area that the user needs to observe; then the recognition area is analyzed to obtain the enlarged area; finally, the enlarged area is enlarged and displayed on the touch display screen. This method avoids the waste of resources caused by global processing by conducting in-depth analysis of the touch area specified by the user, improves the recognition speed and efficiency, performs pre-processing such as pixel enhancement on the image in the touch area to ensure the accuracy of subsequent recognition, and selects a more appropriate enlarged area for detailed display according to the recognition result, so as to ensure that the user can observe and analyze key details more clearly, that is, through local recognition and intelligent analysis, the speed and accuracy of hepatobiliary CT image diagnosis are significantly improved.

[0012] In a possible implementation manner of the first aspect, identifying the hepatobiliary CT image based on the touch area to obtain the identification area includes:

[0013] Preprocessing the hepatobiliary CT image based on the touch area to obtain a preprocessing area; wherein the preprocessing area is used to reflect the area after pixel enhancement is performed on the hepatobiliary CT image;

[0014] Identification is performed according to the pre-processed area to obtain an identified area.

[0015] In a possible implementation manner of the first aspect, preprocessing the hepatobiliary CT image based on the touch area to obtain a preprocessed area includes:

[0016] Acquire a seed point based on the touch area; wherein the seed point is a pixel point in the touch area;

[0017] Analyzing the seed point and the touch area to obtain a growth area; wherein the growth area is used to reflect an integrated closed area of ​​pixels in the hepatobiliary CT image whose correlation with the seed point is greater than a preset correlation;

[0018] The growth area is pretreated to obtain a pretreated area.

[0019] In a possible implementation manner of the first aspect, the analyzing according to the seed point and the touch area to obtain the growth area includes:

[0020] Performing region growth according to the seed point to obtain an initial growth region; wherein the initial growth region is used to reflect a region in which the grayscale value of a pixel point in the hepatobiliary CT image and the grayscale value of a pixel point of the seed point are in the same preset range;

[0021] Analyze the touch area to obtain a growth range; wherein the growth range is used to reflect the distance extended outward from the seed point as the center of the circle;

[0022] The initial growth region is screened based on the growth range to obtain a growth region.

[0023] In a possible implementation manner of the first aspect, analyzing according to the touch area to obtain a growth range includes:

[0024] When the touch area is a ring area, the area of ​​the ring area is obtained; wherein the ring area is the enveloping range when the track of the touch operation is a ring;

[0025] Obtaining a first preset loading range;

[0026] Expanding the annular region based on the first preset loading range to obtain a growth range;

[0027] And / or, analyzing the touch area to obtain the growth range further includes:

[0028] When the touch area is a point area, a second preset loading range is acquired, and the second preset loading range is used as the growth range.

[0029] In a possible implementation manner of the first aspect, the identifying according to the preprocessed area to obtain the identified area includes:

[0030] Analyze the pre-treated area to obtain identification features; wherein the identification features are used to reflect the density and texture of the liver, gallbladder and bile duct tissues reflected in the pre-treated area;

[0031] An analysis is performed based on the identification features to obtain an identification area.

[0032] In a possible implementation manner of the first aspect, the analyzing according to the identification feature to obtain the identification area includes:

[0033] When the identification features do not contain abnormal features, the pre-processed area is determined as the identification area; wherein the abnormal features are used to reflect the density and texture of the liver, gallbladder and bile duct tissues in the pre-processed area when lesions occur;

[0034] The step of analyzing the identified area to obtain the enlarged area includes:

[0035] The identified area is determined as the enlarged area.

[0036] In a possible implementation manner of the first aspect, the performing analysis according to the identification feature to obtain the identification area further includes:

[0037] When the identification feature contains the abnormal feature, obtaining the abnormal feature range, and determining the abnormal feature range as the identification area; wherein the abnormal feature range is used to reflect the range of the abnormal feature in the pre-processing area;

[0038] The step of analyzing the identified area to obtain the enlarged area includes:

[0039] Acquire the type information and position information of the abnormal feature reflected in the identification area; wherein the type information is used to reflect the type of lesion where the abnormal feature appears, and the position information is used to reflect the distance between the position where the abnormal feature appears in the organ tissue and other organ tissues;

[0040] Analyze the type information to obtain the lesion correlation; wherein the lesion correlation is used to reflect the degree of complication between an organ tissue and other organ tissues when the organ tissue has the current abnormal feature;

[0041] Analyze according to the lesion correlation to obtain a first magnification range, and obtain a first magnification weight of the first magnification range;

[0042] Analyze according to the position information to obtain a second magnification range, and obtain a second magnification weight of the second magnification range;

[0043] The first amplification weight is compared with the second amplification weight, and the first amplification range or the second amplification range with a larger weight value is used as the amplification area. When the first amplification weight is the same as the second amplification weight, the first amplification range is used as the amplification area.

[0044] In a second aspect, an embodiment of the present application provides a hepatobiliary CT image recognition device, comprising:

[0045] An acquisition module, configured to determine a touch area of ​​the touch operation after receiving a signal of a touch operation of the touch display screen; wherein the touch area is used to reflect a position touched by the user in the hepatobiliary CT image;

[0046] an identification module, used to identify the hepatobiliary CT image based on the touch area to obtain an identification area; wherein the identification area is used to reflect the area that the user needs to observe;

[0047] An analysis module, used for analyzing the identified area to obtain an amplified area;

[0048] The display module is used to display the enlarged area in the touch display screen in an enlarged manner.

[0049] In a third aspect, an embodiment of the present application provides a hepatobiliary CT image recognition device, comprising a touch display screen and a control device, wherein the control device is electrically connected to the touch display screen, the control device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the methods described in the first aspect when executing the computer program.

[0050] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above-mentioned first aspects is implemented.

[0051] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a hepatobiliary CT image recognition device, the hepatobiliary CT image recognition device executes the hepatobiliary CT image recognition method described in any one of the above-mentioned first aspects.

[0052] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 It is a flowchart of the hepatobiliary CT image recognition method provided in the embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of the implementation process of the hepatobiliary CT image recognition method provided in the embodiment of the present application;

[0056] Figure 3 It is a structural schematic diagram of a hepatobiliary CT image recognition device provided in an embodiment of the present application;

[0057] Figure 4 It is a structural schematic diagram of the control device of the hepatobiliary CT image recognition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0059] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0060] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0061] As used in the specification of this application and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if the described condition or event is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce the described condition or event is detected" or "in response to detecting the described condition or event" depending on the context.

[0062] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0063] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0064] With the rapid development of medical imaging technology, hepatobiliary CT (computed tomography) images play an increasingly important role in clinical diagnosis. Hepatobiliary CT images can provide detailed anatomical information, helping doctors accurately detect and evaluate the health of organs such as the liver, gallbladder and bile duct. In addition, CT images can also be used to detect tumors, inflammation, stones and other diseases, providing an important basis for formulating treatment plans.

[0065] In the prior art, a model is usually used to automatically identify the entire hepatobiliary CT image. However, since there are multiple tissues or organs in the hepatobiliary CT image, in order to cover multiple tissues and organs, the existing automatic recognition model is often designed to be very complex, which not only increases the difficulty of training, but also reduces the speed and efficiency of real-time recognition. When the entire CT image is globally processed, many normal areas are also included in the analysis scope, resulting in unnecessary waste of computing resources, affecting the system's response speed and user experience.

[0066] To solve the above problems, the embodiments of the present application provide a method, device and equipment for recognizing hepatobiliary CT images. In the method, after receiving the signal of the touch operation of the touch display screen, the touch area of ​​the touch operation used to reflect the position of the user's touch in the hepatobiliary CT image is determined; then the hepatobiliary CT image is recognized based on the touch area to obtain the recognition area used to reflect the area that the user needs to observe; then the analysis is performed based on the recognition area to obtain the magnified area; finally, the magnified area is magnified and displayed on the touch display screen. The method avoids the waste of resources caused by global processing by conducting in-depth analysis of the touch area specified by the user, improves the recognition speed and efficiency, performs pre-processing such as pixel enhancement on the image in the touch area to ensure the accuracy of subsequent recognition, and selects a more appropriate magnified area for detailed display according to the recognition result, so as to ensure that the user can observe and analyze key details more clearly, that is, through local recognition and intelligent analysis, the speed and accuracy of hepatobiliary CT image diagnosis are significantly improved.

[0067] The hepatobiliary CT image recognition method provided in the embodiment of the present application can be applied to a hepatobiliary CT image recognition device. In this case, the hepatobiliary CT image recognition device is the executor of the hepatobiliary CT image recognition method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the hepatobiliary CT image recognition device.

[0068] For example, a hepatobiliary CT image recognition device may include a touch screen and a control device, wherein the control device is electrically connected to the touch screen. The touch screen is used to receive touch operations and display hepatobiliary CT images. The control device monitors and controls the entire recognition process.

[0069] For example, the control device can be a device with wireless communication function on terminal devices such as a mobile phone, a tablet computer, a wearable device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a smart screen, a smart TV, etc., a computing device or other processing device connected to a wireless modem, an Internet of Things terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a TV set-top box (STB), a customer premises equipment (CPE) and / or other devices used to communicate on a wireless system and a next-generation communication system, such as a mobile terminal in a 5G network or a mobile terminal in a future evolved public land mobile network (PLMN).

[0070] In order to better understand the hepatobiliary CT image recognition method provided in the embodiment of the present application, the specific implementation process of the hepatobiliary CT image recognition method provided in the embodiment of the present application is exemplarily introduced below.

[0071] Figure 1 and Figure 2 A schematic flow chart of a hepatobiliary CT image recognition method provided in an embodiment of the present application is shown. The hepatobiliary CT image recognition method includes:

[0072] S100, after receiving a signal of a touch operation on the touch display screen, determine a touch area of ​​the touch operation; wherein the touch area is used to reflect a position touched by the user in the hepatobiliary CT image.

[0073] It can be understood that the hepatobiliary CT image shows the liver, gallbladder, and the connection between the liver and gallbladder (such as bile duct) and other related organ tissues. The user can touch the touch display screen with a hand or other touch device.

[0074] S200, identifying the hepatobiliary CT image based on the touch area to obtain an identification area; wherein the identification area is used to reflect the area that the user needs to observe.

[0075] Exemplarily, after acquiring the touch area, the range to be identified can be determined by the shape of the touch area, that is, when the user only clicks on the touch display screen, the area that the user needs to observe can be further determined based on the location of the click and then based on the tissue characteristics within the touch area (that is, whether it is a lesion); analysis can also be performed based on the size of the touch area, and the size of the touch area can be used to determine whether only the tissue within the touch area is to be identified, or whether the touch area needs to be expanded. For example, when the touch area is smaller than a preset range, the touch area may need to be expanded, and the range of expansion may be determined based on the tissue characteristics within the touch area to obtain the identification area; when the touch area is larger than the preset range, only the tissue characteristics within the touch area may need to be identified, and the obtained identification area is within the touch area, and the same method is not limited thereto.

[0076] In a possible implementation, in step S200, the hepatobiliary CT image is identified based on the touch area to obtain the identification area, including:

[0077] S210, preprocessing the hepatobiliary CT image based on the touch area to obtain a preprocessing area; wherein the preprocessing area is used to reflect the area after pixel enhancement in the hepatobiliary CT image.

[0078] It can be understood that the preprocessing area is a partial area in the hepatobiliary CT image. Exemplarily, regional growth can be performed based on a pixel point in the touch area to obtain an initial area of ​​the same pixel point as the pixel point, and then the obtained initial area is expanded according to the shape of the touch area to obtain the growth range, and the initial area is selected based on the growth range to obtain the preprocessing area; the touch area and the hepatobiliary CT image can also be input into the learning model, and the learning model then outputs the corresponding preprocessing area, etc., but is not limited to this. The learning model is trained with multiple sets of training data, and each set of training data in the multiple sets of training data includes a touch area, a hepatobiliary CT image, and a preprocessing area.

[0079] In a possible implementation, in step S210, the hepatobiliary CT image is preprocessed based on the touch area to obtain a preprocessed area, including:

[0080] S211, obtaining a seed point based on the touch area; wherein the seed point is a pixel point in the touch area.

[0081] For example, the center point of the touch area can be used as the seed point, or the average pixel value of each pixel in the touch area can be calculated and the pixel point closest to the average pixel value in the touch area can be used as the seed point, etc., but not limited to this.

[0082] S212, analyzing the seed point and the touch area to obtain a growth area; wherein the growth area is used to reflect the integrated closed area of ​​pixel points in the hepatobiliary CT image whose correlation with the seed point is greater than a preset correlation.

[0083] It can be understood that the growth area can be a partial area in the touch area, or it can be an area including the touch area, which depends on the set area of ​​other pixels with the same pixel point as the seed point and the shape of the touch area. Correlation refers to the degree of correlation between the gray value of the pixel and the distance. The preset correlation is a value that is set manually, or it can be obtained from an image database, etc., but is not limited to this. The image database refers to a database including preset correlations. These data can be obtained through laboratory experiments, on-site measurements and monitoring, and past experience. After obtaining, the collected data is sorted, classified and archived, useful information and rules are extracted, and the relevant data is saved in the database to form an image database. Exemplarily, regional growth can be performed through the pixel points of the seed point, and the growth range is determined according to the shape of the touch area to obtain the growth area; it can also be obtained by inputting the seed point, the touch area and the hepatobiliary CT image into the learning model, and the learning model outputs the corresponding growth area, etc., but is not limited to this.

[0084] In a possible implementation, in step S212, analyzing the seed point and the touch area to obtain a growth area includes:

[0085] S2121, performing region growing according to the seed point to obtain an initial growing region; wherein the initial growing region is used to reflect the region where the grayscale value of the pixel point in the hepatobiliary CT image and the grayscale value of the pixel point of the seed point are in the same preset range.

[0086] It can be understood that the preset range is a pre-set range value, which includes a distance range and a grayscale value range. After determining the seed point, the region is gradually grown based on the grayscale value of the seed point and the preset range with the adjacent pixel points, that is, if the pixel value and distance of the adjacent pixel point are within the preset range, the pixel point is marked, and then the pixel value and distance of another pixel point adjacent to the pixel point are calculated to see whether they are within the same preset range as the pixel point. If so, the other pixel point is marked, and if not, the other pixel point is excluded. By identifying and expanding outward, the marked pixels are finally integrated, which is the initial growth area.

[0087] S2122, analyzing the touch area to obtain a growth range; wherein the growth range is used to reflect the distance extending outward from the seed point as the center of the circle.

[0088] It can be understood that when the user performs a touch operation, it is basically divided into point touch and area selection. Point touch means that the user only clicks on a certain place in the hepatobiliary CT image on the touch display screen, while area selection selects a certain area in the hepatobiliary CT image to understand the situation of the tissues and organs in the area. For example, the shape of the touch area can be analyzed to determine the range that needs to be loaded, and the size of the touch area can be analyzed to determine the growth ratio according to the size to obtain the growth range, etc., but it is not limited to this.

[0089] In a possible implementation, in step S2122, analyzing the touch area to obtain a growth range includes:

[0090] S21221, when the touch area is a ring area, obtain the area of ​​the ring area; wherein the ring area is the enclosing range when the track of the touch operation is a ring.

[0091] It can be understood that whether the touch area is an annular area is determined by tracking the continuous touch points on the touch screen and calculating their geometric features (such as closure, curvature, etc.), that is, if the pixel points formed by the touch action are continuous and closed rings, then the area surrounded by the ring is the annular area; if the pixel points formed by the touch action are continuous but unclosed open rings, then the curvature of the ring can be calculated, that is, for each pair of adjacent touch points, the curvature change trend is calculated, and the curvature of the unclosed part is predicted by interpolation, so as to add corresponding pixel points to complete the closure to form a new annular area.

[0092] S21222, obtain a first preset loading range.

[0093] It can be understood that the first preset loading range is a preset loading range. The first preset loading range can be manually input by humans, or can be obtained from an image database, etc., but is not limited to this. Different annular area areas correspond to a first preset loading range. Exemplarily, the annular area area can be matched in the image database to obtain a first preset loading range corresponding to the annular area area; the annular area area can also be input into a learning model, and the learning model outputs the corresponding first preset loading range, etc., but is not limited to this. The first preset loading range may be smaller than the annular area area, or it may be larger than the annular area area, depending on the size of the annular area area.

[0094] S21223, expanding the annular area based on the first preset loading range to obtain a growth range.

[0095] It can be understood that the center point of the annular area is first obtained through the annular area, and then the center point is expanded outward within the first preset loading range to obtain the growth range.

[0096] With such a setting, the corresponding first preset loading range is obtained based on the area of ​​the annular region, and then expanded outward according to the first preset loading range based on the center point of the annular region to obtain an accurate growth range. Such a setting not only improves the accuracy and robustness of annular region recognition, ensuring that annular regions of different sizes and shapes can be effectively processed, but also enhances the flexibility and diagnostic accuracy of the system through intelligent and adaptive loading range adjustment, while providing real-time feedback and user interactive adjustment functions, thereby improving user experience and the efficiency of medical image analysis.

[0097] In a possible implementation, in step S2122, analyzing the touch area to obtain a growth range further includes:

[0098] S21224: When the touch area is a point area, obtain a second preset loading range, and use the second preset loading range as a growth range.

[0099] It can be understood that the second preset loading range is a preset area range, which can be manually input by a person or obtained from an image database.

[0100] In this way, the system not only simplifies the operation process for single-point touch by processing the point area through the second preset loading range, but also ensures that each point area can be reasonably expanded to cover the potential area of ​​interest. This method enhances the flexibility of the system, adapts to different types of user interaction modes (ring area and point area), and further improves the accuracy of diagnosis and user experience through the intelligent selection of preset loading ranges.

[0101] S2123, screening the initial growth region based on the growth range to obtain a growth region.

[0102] It can be understood that the growth area is the area within the initial growth area, and the regional range of the growth area is the growth range.

[0103] With this setting, the initial growth area is obtained by regional growth based on the seed point, and the growth range with the seed point as the center is determined by combining the touch area analysis. The initial growth area is then screened based on the growth range to finally obtain an accurate growth area. This method not only ensures the accuracy of the recognition area, but also removes irrelevant pixels through intelligent screening, improves the reliability and efficiency of diagnosis, and enhances the flexibility and adaptability of the system, significantly improving the user experience and the accuracy and intuitiveness of medical image analysis.

[0104] S213, preprocessing the growth area to obtain a preprocessed area.

[0105] It can be understood that the purpose of preprocessing is to improve the image quality, enhance key features, and improve the consistency and standardization of data in the growth area. By performing edge enhancement and pixel grayscale enhancement on the hepatobiliary CT image of the growth area, the enhanced growth area is the preprocessing area.

[0106] S220, performing recognition according to the pre-processed area to obtain a recognition area.

[0107] Exemplarily, the judgment can be made by analyzing the characteristics of tissues and organs reflected in the pretreatment area to identify whether a lesion appears in the pretreatment area, and the pretreatment area can be further processed according to the presence or absence of the lesion to obtain the identification area; the judgment can also be made according to the size and position of the organ structure in the pretreatment area. For example, if the pretreatment area is located on the side of the liver away from the gallbladder, the pretreatment area can be processed according to the size of the liver, that is, the identification ratio is selected according to the size of the liver to obtain the identification area; if the pretreatment area is located on the side close to the gallbladder, the distance between the position and the gallbladder or bile duct is analyzed to obtain the identification range to obtain the identification area, and so on, but not limited to this.

[0108] With such a setting, after obtaining the preprocessing area through preprocessing, the preprocessing area is identified to obtain the identified area, which can reduce the steps and processes of hepatobiliary CT image recognition, reduce unnecessary global analysis, focus on potential lesions or important structures, and improve processing speed and system efficiency, that is, reduce the analysis capacity of data analysis, while improving the efficiency of hepatobiliary CT image recognition.

[0109] In a possible implementation, in step S220, identification is performed according to the preprocessed area to obtain the identified area, including:

[0110] S221, analyzing the pre-processed area to obtain identification features; wherein the identification features are used to reflect the density and texture of the liver, gallbladder and bile duct tissues reflected in the pre-processed area.

[0111] It can be understood that the density characteristics can be obtained by calculating the number of pixels or the gray value distribution in the neighborhood of each pixel in the preprocessing area, and the texture characteristics in the preprocessing area can be captured by applying a texture analysis algorithm (such as gray level co-occurrence matrix, local binary pattern, etc.).

[0112] S222, analyzing according to the recognition features to obtain a recognition area.

[0113] Exemplarily, the preprocessed area is processed according to the tissue condition reflected by the identification feature, that is, whether a lesion is present, to obtain the identification area; the identification feature and the preprocessed area can also be input into a learning model, and the learning model outputs the corresponding identification area, etc., but is not limited to this.

[0114] With this setting, the user's observation needs for hepatobiliary CT images can be reflected through identification features, and then the hepatobiliary CT images can be specifically identified, which enhances flexibility and adaptability, making hepatobiliary CT image analysis more intuitive and efficient.

[0115] In a possible implementation, in step S222, analysis is performed based on the recognition features to obtain the recognition area, including:

[0116] S2221, when the identification features do not contain abnormal features, the pre-processing area is determined as the identification area; wherein the abnormal features are used to reflect the density and texture of the liver, gallbladder and bile duct tissues in the pre-processing area when lesions appear.

[0117] It can be understood that when the identification features do not contain abnormal features, it means that no lesions or other abnormalities are detected in the pre-processed area. This means that the density and texture of the liver, gallbladder and bile duct tissues in the area are within the normal range. At this time, the pre-processed area is determined as the identification area for subsequent analysis or display.

[0118] S2222, when the recognition feature contains an abnormal feature, obtain the abnormal feature range, and determine the abnormal feature range as the recognition area; wherein the abnormal feature range is used to reflect the range of the abnormal feature in the preprocessing area.

[0119] It can be understood that the abnormal feature range is the set of distribution positions of all adjacent abnormal features in the preprocessing area.

[0120] With this setting, by analyzing the identification features of the pre-processing area, it is possible to distinguish between normal and abnormal situations: when no abnormal features are detected, the pre-processing area is directly determined as the identification area, simplifying the process and improving efficiency; and when abnormal features exist, the system accurately obtains and defines the range of abnormal features to ensure that potential lesions are accurately captured and marked. This method not only improves the accuracy and reliability of diagnosis, but also optimizes resource utilization, reduces unnecessary global analysis, and significantly improves the speed and user experience of hepatobiliary CT image analysis, allowing doctors to observe and diagnose more efficiently and intuitively.

[0121] S300, analyzing the identified area to obtain an amplified area.

[0122] It can be understood that the scope of the enlarged area can be determined based on whether the identification area has abnormal features. That is, when the identification features do not contain abnormal features, the identification area can be determined as the enlarged area. When the identification features contain abnormal features, the cause of the abnormal features and the location of the abnormal features can be analyzed, and the correlation between the abnormal features and other organs when they appear can be analyzed. That is, when abnormal features appear in the liver, it can be determined whether the abnormal features will affect the bile duct or gallbladder, or whether the abnormal features are caused by the bile duct or gallbladder. If there is no correlation, the identification area can be indiscriminately enlarged (enlarged at the same proportion). If there is a correlation, considering the location of the abnormal features, other tissues or organs in the identification area are selectively enlarged to obtain the enlarged area. The identification area can also be input into a learning model, and the learning model outputs the corresponding enlarged area, and so on, but is not limited to this.

[0123] In a possible implementation, in step S300, analyzing the identified area to obtain the enlarged area includes:

[0124] S310a, when the recognition features do not contain abnormal features, the recognition area is determined as the enlarged area.

[0125] It can be understood that when the identification features do not contain abnormal features, it means that no lesions or other abnormalities are detected in the pre-processed area. This means that the density and texture of the liver, gallbladder and bile duct tissues in the area are within the normal range. The determination of the magnified area allows the user to observe the area more clearly on the touch screen, ensuring that the normal anatomical structure is presented in detail.

[0126] In a possible implementation, in step S300, analyzing is performed according to the identified area to obtain the enlarged area, further comprising:

[0127] S310b, when the identification features contain abnormal features, obtain the type information and position information of the abnormal features reflected in the identification area; wherein the type information is used to reflect the type of lesion where the abnormal features appear, and the position information is used to reflect the distance between the position where the abnormal features appear in the organ tissue and other organ tissues.

[0128] It is understandable that when the identification features contain abnormal features, it means that the user has a need to understand the lesion. The specific type of abnormal features, such as tumors, cysts, inflammation, etc., can be identified through image analysis technology (such as machine learning models), and the specific location of the abnormal features in the organ tissue is calculated, and the closest distance between it and other organ tissues is calculated to obtain the location information.

[0129] S320, analyzing the type information to obtain the lesion correlation; wherein the lesion correlation is used to reflect the degree of complication between an organ tissue and other organ tissues when the organ tissue has the current abnormal characteristics.

[0130] Exemplarily, different types of information correspond to a lesion correlation. The type information can be output to the hepatobiliary database for matching to obtain the corresponding lesion correlation; the type information can also be input to the learning model, and the learning model outputs the corresponding lesion correlation, etc., but is not limited thereto.

[0131] S330, analyzing according to the lesion correlation to obtain a first magnification range, and acquiring a first magnification weight of the first magnification range.

[0132] It can be understood that different lesion correlations correspond to a first magnification range, and the higher the lesion correlation, the larger the first magnification range. The lesion correlation can be output to the hepatobiliary database for matching to obtain the corresponding first magnification range; the lesion correlation can also be input into the learning model, and the learning model outputs the corresponding first magnification range, etc., but not limited to this. The first magnification weight is a pre-set value, which can be manually input by humans, or obtained from the hepatobiliary database, etc., but not limited to this.

[0133] S340, analyzing according to the position information to obtain a second magnification range, and acquiring a second magnification weight of the second magnification range.

[0134] It can be understood that different position information corresponds to a second magnification range. The position information can be output to the hepatobiliary database for matching to obtain the corresponding second magnification range; the position information can also be input to the learning model, and the learning model outputs the corresponding second magnification range, etc., but not limited to this. The second magnification weight is a preset value, which can be manually input by humans, or obtained from the hepatobiliary database, etc., but not limited to this.

[0135] S350, comparing the first magnification weight with the second magnification weight, taking the first magnification range or the second magnification range with a larger weight value as the magnification area, and when the first magnification weight is the same as the second magnification weight, taking the first magnification range as the magnification area.

[0136] It can be understood that when the first magnification range or the second magnification range with a larger weight value is used as the magnification area, the center point of the identification area can be used as the diffusion point, and then the diffusion point is diffused to the surroundings based on the first magnification range or the second magnification range to obtain the magnification area.

[0137] With this setting, the most appropriate magnification area is determined by multi-dimensional analysis of the types and location information of abnormal features. When the identification features contain abnormal features, the lesion correlation and the corresponding magnification range and weight value are obtained by obtaining the specific type of the lesion and its positional relationship with the surrounding organs and tissues. Different lesion correlations and location information determine the first magnification range and the second magnification range respectively, and assign corresponding weights. Finally, the range with a larger weight is selected as the magnification area to ensure that the focus is highlighted and the potential affected area is fully covered. This method not only improves the accuracy and reliability of diagnosis, but also optimizes resource utilization, reduces unnecessary global analysis, and significantly improves the speed of hepatobiliary CT image analysis and user experience, allowing users to observe and diagnose more efficiently and intuitively, thereby improving the overall quality of diagnosis and treatment.

[0138] S400, the enlarged area is displayed in an enlarged manner on the touch display screen.

[0139] It is understandable that a suitable magnification ratio can be selected according to the size of the magnified area, for example, the ratio between the touch display screen and the magnified area is calculated and the corresponding magnification ratio is matched so that the tissue or organ in the magnified area can be more clearly seen.

[0140] With this setting, the user's touch operation can accurately capture the observation needs, obtain the area of ​​interest to the user, and ensure the accuracy of the identification area through seed point and growth area analysis; use image processing technology to detect and classify abnormal features, provide accurate lesion correlation and location information analysis; and select the optimal magnification area by comparing the weight values ​​of different magnification ranges to ensure that the focus is highlighted and the potential impact area is fully covered. This method not only improves the accuracy and efficiency of image recognition, but also optimizes resource utilization, reduces unnecessary global analysis, and improves the speed and user experience of hepatobiliary CT image analysis. The entire process is intuitive and efficient, which enhances the user's diagnostic ability and work efficiency, and significantly improves the accuracy and reliability of medical image analysis, thereby better supporting clinical decision-making and treatment plan formulation.

[0141] It should be understood that the size of the serial numbers of the steps in the above embodiments 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 application.

[0142] Corresponding to the hepatobiliary CT image recognition method described in the above embodiment, the embodiment of the present application also provides a hepatobiliary CT image recognition device, and each module of the system can implement each step of the hepatobiliary CT image recognition method. Figure 3 A structural block diagram of a hepatobiliary CT image recognition device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0143] Reference Figure 3 , the hepatobiliary CT image recognition device comprises:

[0144] The acquisition module is used to determine the touch area of ​​the touch operation after receiving the signal of the touch operation of the touch display screen; wherein the touch area is used to reflect the position of the user's touch in the hepatobiliary CT image.

[0145] The recognition module is used to recognize the hepatobiliary CT image based on the touch area to obtain the recognition area; wherein the recognition area is used to reflect the area that the user needs to observe.

[0146] The analysis module is used to analyze the identified area to obtain the enlarged area.

[0147] The display module is used to display the enlarged area in an enlarged manner on the touch display screen.

[0148] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0149] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above modules is used as an example for illustration. In practical applications, the above functions can be assigned to different modules as needed, that is, the internal structure of the device can be divided into different modules to complete all or part of the functions described above. The modules in the embodiment can be integrated into a processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the modules in the above device can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0150] The embodiment of the present application also provides a hepatobiliary CT image recognition device, including a touch display screen and a control device, wherein the control device is electrically connected to the touch display screen. Figure 4 This is a schematic diagram of the structure of a control device 6 provided in an embodiment of the present application. Figure 4 As shown, the control device 6 of this embodiment includes: at least one processor 60 ( Figure 4 Only one is shown), at least one memory 61 ( Figure 4Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the control device 6 implements the steps in any of the above-mentioned hepatobiliary CT image recognition method embodiments, or implements the functions of the modules in the above-mentioned device embodiments.

[0151] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the control device 6.

[0152] The control device 6 can be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The hepatobiliary CT image recognition device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 4 It is only an example of the control device 6 and does not constitute a limitation on the control device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0153] The processor 60 may be a central processing unit (CPU), or 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. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0154] In some embodiments, the memory 61 may be an internal storage unit of the control device 6, such as a hard disk or memory of the control device 6. In other embodiments, the memory 61 may also be an external storage device of the control device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the control device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the control device 6. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0155] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0156] An embodiment of the present application provides a computer program product. When the computer program product runs on a hepatobiliary CT image recognition device, the hepatobiliary CT image recognition device implements the steps in any of the above-mentioned method embodiments.

[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the hepatobiliary CT image recognition device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electrical carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk.

[0158] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0159] 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 this application.

[0160] In the embodiments provided in the present application, it should be understood that the disclosed hepatobiliary CT image recognition equipment and devices can be implemented in other ways. For example, the above-described hepatobiliary CT image recognition device embodiments are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0161] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0162] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for recognizing hepatobiliary CT images, characterized in that: Applied to a hepatobiliary CT image recognition device, the hepatobiliary CT image recognition device comprises a touch display screen, and the hepatobiliary CT image is displayed on the touch display screen. The method comprises: After receiving the signal of the touch operation of the touch display screen, determining the touch area of ​​the touch operation; wherein the touch area is used to reflect the position of the user's touch in the hepatobiliary CT image; The hepatobiliary CT image is identified based on the touch area to obtain an identification area; wherein the identification area is used to reflect the area that the user needs to observe; Analyze according to the identified area to obtain an amplified area; Enlarging and displaying the enlarged area on the touch display screen; The step of analyzing the identified area to obtain the enlarged area includes: Acquire the type information and position information of the abnormal feature reflected by the identified area; wherein the abnormal feature reflects the density and texture characteristics of the liver, gallbladder and bile duct tissues when lesions appear, the type information is used to reflect the type of lesions where the abnormal feature appears, and the position information is used to reflect the position distance between the position where the abnormal feature appears in the organ tissue and other organ tissues; Analyze the type information to obtain the lesion correlation; wherein the lesion correlation is used to reflect the degree of complication between an organ tissue and other organ tissues when the organ tissue has the current abnormal feature; Analyze according to the lesion correlation to obtain a first magnification range, and obtain a first magnification weight of the first magnification range; Analyze according to the position information to obtain a second magnification range, and obtain a second magnification weight of the second magnification range; The first amplification weight is compared with the second amplification weight, and the first amplification range or the second amplification range with a larger weight value is used as the amplification area. When the first amplification weight is the same as the second amplification weight, the first amplification range is used as the amplification area.

2. The hepatobiliary CT image recognition method according to claim 1, characterized in that: The identifying the hepatobiliary CT image based on the touch area to obtain the identification area includes: Preprocessing the hepatobiliary CT image based on the touch area to obtain a preprocessing area; wherein the preprocessing area is used to reflect the area after pixel enhancement is performed on the hepatobiliary CT image; Identification is performed according to the pre-processed area to obtain an identified area.

3. The hepatobiliary CT image recognition method according to claim 2, characterized in that: The preprocessing of the hepatobiliary CT image based on the touch area to obtain a preprocessing area includes: Acquire a seed point based on the touch area; wherein the seed point is a pixel point in the touch area; Analyzing the seed point and the touch area to obtain a growth area; wherein the growth area is used to reflect an integrated closed area of ​​pixels in the hepatobiliary CT image whose correlation with the seed point is greater than a preset correlation; The growth area is pretreated to obtain a pretreated area.

4. The hepatobiliary CT image recognition method according to claim 3, characterized in that: The step of analyzing the seed point and the touch area to obtain a growth area includes: Performing region growth according to the seed point to obtain an initial growth region; wherein the initial growth region is used to reflect a region in which the grayscale value of a pixel point in the hepatobiliary CT image and the grayscale value of a pixel point of the seed point are in the same preset range; Analyze the touch area to obtain a growth range; wherein the growth range is used to reflect the distance extended outward from the seed point as the center of the circle; The initial growth region is screened based on the growth range to obtain a growth region.

5. The hepatobiliary CT image recognition method according to claim 4, characterized in that: The analyzing according to the touch area to obtain the growth range includes: When the touch area is a ring area, the area of ​​the ring area is obtained; wherein the ring area is the enveloping range when the track of the touch operation is a ring; Obtaining a first preset loading range; Expanding the annular region based on the first preset loading range to obtain a growth range; And / or, analyzing the touch area to obtain the growth range further includes: When the touch area is a point area, a second preset loading range is acquired, and the second preset loading range is used as the growth range.

6. The hepatobiliary CT image recognition method according to claim 2, characterized in that: The identifying according to the pre-processed area to obtain the identified area includes: Analyze the pre-treated area to obtain identification features; wherein the identification features are used to reflect the density and texture of the liver, gallbladder and bile duct tissues reflected in the pre-treated area; An analysis is performed based on the identification features to obtain an identification area.

7. The hepatobiliary CT image recognition method according to claim 6, characterized in that: The step of analyzing the identification features to obtain the identification area includes: When the identification features do not contain abnormal features, the pre-processed area is determined as the identification area; wherein the abnormal features are used to reflect the density and texture of the liver, gallbladder and bile duct tissues in the pre-processed area when lesions occur; The step of analyzing the identified area to obtain the enlarged area includes: The identified area is determined as the enlarged area.

8. The hepatobiliary CT image recognition method according to claim 7, characterized in that: The analyzing according to the identification feature to obtain the identification area also includes: When the identification feature contains the abnormal feature, the abnormal feature range is obtained, and the abnormal feature range is determined as the identification area; wherein the abnormal feature range is used to reflect the range of the abnormal feature in the preprocessing area.

9. A hepatobiliary CT image recognition device, characterized in that: include: An acquisition module, configured to determine a touch area of ​​the touch operation after receiving a signal of a touch operation on the touch display screen; wherein the touch area is used to reflect a position touched by the user in the hepatobiliary CT image; an identification module, used to identify the hepatobiliary CT image based on the touch area to obtain an identification area; wherein the identification area is used to reflect the area that the user needs to observe; An analysis module, used for analyzing the identified area to obtain an amplified area; A display module, used to display the enlarged area in the touch display screen in an enlarged manner; Wherein, the analysis module is also used for: Acquire the type information and position information of the abnormal feature reflected by the identified area; wherein the abnormal feature reflects the density and texture characteristics of the liver, gallbladder and bile duct tissues when lesions appear, the type information is used to reflect the type of lesions where the abnormal feature appears, and the position information is used to reflect the position distance between the position where the abnormal feature appears in the organ tissue and other organ tissues; Analyze the type information to obtain the lesion correlation; wherein the lesion correlation is used to reflect the degree of complication between an organ tissue and other organ tissues when the organ tissue has the current abnormal feature; Analyze according to the lesion correlation to obtain a first magnification range, and obtain a first magnification weight of the first magnification range; Analyze according to the position information to obtain a second magnification range, and obtain a second magnification weight of the second magnification range; The first amplification weight is compared with the second amplification weight, and the first amplification range or the second amplification range with a larger weight value is used as the amplification area. When the first amplification weight is the same as the second amplification weight, the first amplification range is used as the amplification area.

10. A hepatobiliary CT image recognition device, characterized in that: It includes a touch display screen and a control device, the control device is electrically connected to the touch display screen, the control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method according to any one of claims 1 to 8 when executing the computer program.

Images