Method, device, medium and equipment for determining target area in CT image

Abstract

The present disclosure relates to the field of image processing technology, and provides a method and device for determining a target area in a CT image, as well as a computer-readable storage medium and an electronic device for implementing the above method. The method includes: obtaining CT image data of a cavity surrounding a target area in an original CT image; obtaining multiple sections of the cavity according to the CT image data of the cavity, and determining the outer position of the target area based on the shape characteristics of the cavity and the multiple sections; and intercepting the target area in the original CT image according to the outer position. The technical solution can improve the recognition efficiency of the target area on the basis of ensuring the recognition accuracy of the target area, so as to remove the invalid scanning area in the original CT image and avoid labor costs.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technology, and in particular, to a method and device for determining a target area in a CT image, as well as a computer-readable storage medium and electronic device for implementing the method for determining a target area in a CT image. Background Art

[0002] When performing CT (Computed Tomography) of a target area in a medical scenario, a single scan of a single patient may, in some cases, generate a CT image containing additional scan areas, i.e., a CT image containing invalid scan areas, due to operational errors and other reasons. On the one hand, this problem hinders medical researchers from focusing on the observation of brain areas in actual scenarios. On the other hand, when constructing a brain CT image dataset, the invalid scan area will affect the overall quality of the dataset and increase the workload of data annotation. To address the above problems, the relevant technology manually crops the CT images containing invalid scan areas to extract CT image data about the target area.

[0003] It can be seen that the related art lacks a solution that can automatically extract the target area in the original CT image.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure. Summary of the invention

[0005] The purpose of the present disclosure is to provide a method and device for determining a target area in a CT image, as well as a computer-readable storage medium and an electronic device for implementing the above method, thereby improving the recognition efficiency of the target area at least to a certain extent while ensuring the recognition accuracy of the target area, and providing an efficient and robust automatic extraction solution to remove invalid scanning areas in the original CT image.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a method for determining a target area in a CT image is provided, comprising: acquiring CT image data of a cavity surrounding the target area in an original CT image; acquiring multiple sections of the cavity based on the CT image data of the cavity, and determining an envelope position of the target area based on shape features of the cavity and the multiple sections; and, intercepting the target area in the original CT image based on the envelope position.

[0008] According to one aspect of the present disclosure, a device for determining a target region in a CT image is provided, comprising: an acquisition module, an outsourcing position determination module, and a target region determination module.

[0009] Among them, the above-mentioned acquisition module is configured to: acquire CT image data of the cavity surrounding the target area in the original CT image; the above-mentioned external position determination module is configured to: acquire multiple sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, and determine the external position of the above-mentioned target area based on the shape characteristics of the above-mentioned cavity and the above-mentioned multiple sections; and the above-mentioned target area determination module is configured to: intercept the above-mentioned target area in the above-mentioned original CT image according to the above-mentioned external position.

[0010] In some embodiments of the present disclosure, based on the aforementioned scheme, the acquisition module is specifically configured to: acquire CT image data surrounding the cavity in the original CT image based on the Hounsfield unit HU data corresponding to the cavity and the Hounsfield unit HU data corresponding to the target area.

[0011] In some embodiments of the present disclosure, based on the aforementioned solution, the above-mentioned outsourcing position determination module includes: a transverse section processing unit, a coronal section processing unit and an outsourcing position determination unit.

[0012] Wherein, the above-mentioned transverse section processing unit is configured to: obtain multiple transverse sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, and based on the shape characteristics of the above-mentioned transverse sections, screen out a target transverse section from the above-mentioned multiple transverse sections as the first outer surface of the above-mentioned target area; the above-mentioned coronal section processing unit is configured to: obtain multiple coronal sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, determine the target position in each coronal section based on the shape characteristics of the coronal sections, and determine the second outer surface of the target area opposite to the first outer surface according to the target positions of the multiple coronal sections; and the above-mentioned outer surface determination unit is configured to: obtain the outer surface position of the above-mentioned target area according to the above-mentioned first outer surface and the above-mentioned second outer surface.

[0013] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being a circle, the above-mentioned transverse section processing unit is specifically configured to: scan the above-mentioned multiple transverse sections in sequence according to a preset direction; in response to the appearance of a hollow area in the scanning result, determine that the current transverse section is the above-mentioned target transverse section, and stop scanning the next transverse section; and, use the position of the above-mentioned target transverse section in the above-mentioned original CT image as the first outer surface of the above-mentioned target area.

[0014] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being an ellipse, wherein the above-mentioned coronal section processing unit includes a position determination subunit, and is specifically configured as: scanning N coronal sections in sequence along a preset direction, N being a positive integer; for the i-th coronal section, performing multiple cavity width calculations in a preset direction, i being a positive integer not greater than N; determining the maximum cavity width corresponding to the i-th coronal section; and when the current cavity width is less than a preset multiple of the above-mentioned maximum cavity width, determining the position corresponding to the current cavity width as the target position of the i-th coronal section.

[0015] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being an ellipse, the above-mentioned coronal section processing unit includes an outer surface determination subunit, and is configured to: calculate the distances between the above-mentioned multiple target positions and the above-mentioned first outer surface respectively; and determine the second outer surface of the above-mentioned target area according to the target position having the largest distance value from the above-mentioned first outer surface.

[0016] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being an ellipse, wherein the above-mentioned coronal section processing unit includes an outer surface determination subunit, and is configured to: determine a surface by fitting according to the target positions corresponding to the above-mentioned N coronal sections, and use the fitted determined surface as the second outer surface of the above-mentioned target area.

[0017] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area determination module is specifically configured to: intercept the original CT image at the first outer surface and the second outer surface, respectively, and take the portion between the first outer surface and the second outer surface as the target area.

[0018] In some embodiments of the present disclosure, based on the above-mentioned solution, the device for determining the target area in the CT image further includes: a sample determination module.

[0019] Among them, the above-mentioned sample determination module is configured to: use the CT image data of the above-mentioned target area as model training sample data to train the machine learning model.

[0020] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area is the brain, and the acquisition module is specifically configured as follows: based on the fact that the HU data corresponding to the brain tissue is different from the HU data corresponding to the skull surrounding the brain, the CT image data of the skull is acquired in the original CT image according to the HU data corresponding to the skull.

[0021] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area is the intrathoracic tissue, and the acquisition module is specifically configured as follows: based on the fact that the HU data corresponding to the intrathoracic tissue is different from the HU data corresponding to the sternum surrounding the intrathoracic tissue, the CT image data surrounding the sternum is acquired in the original CT image according to the HU data corresponding to the sternum.

[0022] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area is pelvic tissue, and the acquisition module is specifically configured as follows: based on the fact that the HU data corresponding to the pelvic tissue is different from the HU data corresponding to the pelvis surrounding the pelvic tissue, CT image data of the pelvis surrounding the target area is acquired in the original CT image according to the HU data corresponding to the pelvis.

[0023] According to one aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for determining a target area in a CT image described in the first aspect above is implemented.

[0024] According to one aspect of the present disclosure, an electronic device is provided, comprising: one or more processors; and a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method for determining the target area in the CT image described in the first aspect above.

[0025] According to one aspect of the present disclosure, a computer program product or a computer program is provided, the computer program product or the computer program includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method for determining the target area in the CT image provided in each of the above embodiments.

[0026] It can be seen from the above technical solutions that the method for determining a target area in a CT image, the device for determining a target area in a CT image, the computer-readable storage medium, and the electronic device in the exemplary embodiments of the present disclosure have at least the following advantages and positive effects:

[0027] In the technical solutions provided by some embodiments of the present disclosure, CT image data of the cavity surrounding the target area is obtained in the original CT image, so as to preliminarily locate the target area while ensuring the integrity of the target area. Furthermore, multiple sections of the cavity are obtained based on the CT image data of the cavity. Since the shape characteristics of the cavity belong to prior information, the outer position of the target area can be conveniently determined based on the above multiple sections. Then, the final positioning of the target area can be achieved in the original CT image based on the outer position. This solution provides an efficient and robust automatic extraction solution for the target area in the CT image, which can improve the recognition efficiency of the target area on the basis of ensuring the recognition accuracy of the target area, and quickly remove the invalid scanning area in the CT image.

[0028] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0030] Figure 1a An original CT image including an invalid scanning area in an exemplary embodiment of the present disclosure is shown.

[0031] Figure 1b An original CT image including an invalid scanning area in another exemplary embodiment of the present disclosure is shown.

[0032] Figure 2 A schematic diagram showing an exemplary system architecture to which the technical solution of the embodiments of the present disclosure can be applied is shown.

[0033] Figure 3 A schematic flow chart showing a method for determining a target area in a CT image in an exemplary embodiment of the present disclosure.

[0034] Figure 4 A schematic flow chart of a method for determining a target area in a CT image in another exemplary embodiment of the present disclosure is shown.

[0035] Figure 5 A schematic flow chart of a method for determining an outsourcing location in an exemplary embodiment of the present disclosure is shown.

[0036] Figure 6 A schematic diagram showing a skull CT in an exemplary embodiment of the present disclosure.

[0037] Figure 7 A schematic flow chart of a method for determining a first outer envelope in an exemplary embodiment of the present disclosure is shown.

[0038] Figure 8 A schematic flow chart of a method for determining a second outer envelope in an exemplary embodiment of the present disclosure is shown.

[0039] Figure 9a A schematic diagram of a target area determination scenario in an exemplary embodiment of the present disclosure is shown.

[0040] Figure 9b A schematic diagram of a target area determination scenario in another exemplary embodiment of the present disclosure is shown.

[0041] Fig.10 A schematic diagram showing the structure of a device for determining a target area in a CT image in an exemplary embodiment of the present disclosure is shown.

[0042] Fig.11 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0043] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete and will fully convey the concept of the example embodiments to those skilled in the art.

[0044] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0045] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0046] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0047] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0048] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0049] Natural language processing (NLP) is an important direction in the fields of computer science and artificial intelligence. It studies various theories and methods that can achieve effective communication between people and computers using natural language. Natural language processing is a science that integrates linguistics, computer science, and mathematics. Therefore, research in this field will involve natural language, that is, the language people use in daily life, so it is closely related to the study of linguistics. Natural language processing technology usually includes text processing, semantic understanding, machine translation, robot question answering, knowledge graph and other technologies.

[0050] Machine Learning (ML) is a multi-disciplinary subject that involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and self-learning.

[0051] The solution provided by the embodiments of the present disclosure involves technologies such as machine learning and natural language processing of artificial intelligence, which are specifically described by the following embodiments:

[0052] For example, Figure 1a and Figure 1b The original CT images containing invalid scanning areas are shown respectively. Figure 1a It is a CT image of the target area brain 10, but it also includes CT images of other organs 20 such as the neck. Figure 1b It is also a CT image of the target area brain 10, but it contains repeated CT images of the brain 10'. The part of the original CT image except the target area (the brain in this embodiment) is the invalid scanning area, such as other organs 20 and the repeated scanning area (such as Figure 1b 10').

[0053] For invalid scan areas contained in CT images, related technologies generally remove invalid scan areas by manually checking and processing CT image data one by one and performing manual cropping. However, the manual processing method is slow and will be affected by the working state of the staff, and the accuracy and robustness are difficult to guarantee.

[0054] In view of the above problems existing in the related art, the present technical solution provides a method, device, medium and equipment for determining the target area in a CT image. First, Figure 2 A schematic diagram showing an exemplary system architecture to which the technical solution of the embodiments of the present disclosure can be applied is shown.

[0055] like Figure 2 As shown, the system architecture 200 may include one or more of terminal devices 201, 202, 203, a network 204, and a server 205. The network 204 is used to provide a medium for communication links between the terminal devices 201, 202, 203 and the server 205. The network 204 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc. The terminal devices 201, 202, 203 may be various electronic devices with display screens, including but not limited to desktop computers, portable computers, smart phones, tablet computers, etc. It should be understood that Figure 2 The number of terminal devices, networks and servers in the embodiment is only for illustration. According to the implementation requirements, there may be any number of terminal devices, networks and servers. For example, the server 205 may be a server cluster composed of multiple servers, and the server 205 may also be a cloud server.

[0056] The method for determining the target area in the CT image provided in the embodiment of the present disclosure is generally executed by the server 205, and accordingly, the device for determining the target area in the CT image is generally set in the server 205. However, it is easy for those skilled in the art to understand that the method for determining the target area in the CT image provided in the embodiment of the present disclosure can also be executed by the terminal devices 201, 202, and 203, and accordingly, the device for determining the target area in the CT image can also be set in the terminal devices 201, 202, and 203, which is not particularly limited in this exemplary embodiment.

[0057] For example, in an exemplary embodiment, the terminal devices 201, 202, and 203 may send the original CT image to the server 205, so that the server 205 obtains the CT image data of the cavity surrounding the target area in the original CT image. Further, the server 205 obtains multiple sections of the cavity based on the CT image data of the cavity, and determines the outer position of the target area based on the shape characteristics of the cavity and the multiple sections, and determines the target area in the original CT image according to the outer position.

[0058] Exemplarily, the target area in the CT image can also be determined by the terminal devices 201, 202, and 203. Specifically, the terminal devices 201, 202, and 203 obtain CT image data of the cavity surrounding the target area in the original CT image. Further, the terminal devices 201, 202, and 203 obtain multiple sections of the cavity based on the CT image data of the cavity, and determine the outer position of the target area based on the shape characteristics of the cavity and the multiple sections, and determine the target area in the original CT image according to the outer position.

[0059] Exemplarily, the CT image data of the target area determined based on the above scheme can be applied in the medical diagnosis process, and the invalid scanning area in the CT image no longer hinders the medical researchers from focusing on the observation of the target area, which is conducive to the rapid and accurate determination of the disease. Exemplarily, the CT image data of the target area determined based on the above scheme can be used as training data / test data for the machine learning model, which can avoid the invalid scanning area affecting the overall quality of the data set and increasing the workload of data annotation. It should be noted that the CT image data of the target area determined based on the above scheme can be applied to other scenarios, and this scheme does not limit this.

[0060] Next, the method for determining the target area in the CT image provided by the technical solution is introduced. Figure 3 A schematic flow chart showing a method for determining a target region in a CT image in an exemplary embodiment of the present disclosure is shown. Figure 3 The method for determining a target area in a CT image provided in this embodiment includes:

[0061] Step S310, acquiring CT image data of a cavity surrounding a target area in an original CT image;

[0062] Step S320, acquiring a plurality of sections of the cavity according to the CT image data of the cavity, and determining the outer position of the target area based on the shape characteristics of the cavity and the plurality of sections; and

[0063] Step S330: intercepting the target area in the original CT image according to the outsourcing position.

[0064] Figure 3 The illustrated embodiment provides an efficient and robust solution for automatically extracting the target area in the CT image. First, the cavity surrounding the target area is determined to achieve preliminary positioning of the target area on the basis of ensuring the integrity of the target area. Furthermore, multiple sections of the cavity are obtained based on the CT image data of the cavity. Since the shape characteristics of the cavity belong to prior information, the outer position of the target area can be easily determined based on the multiple sections, such as the starting position and the end position of the target area in the preset direction. It can be seen that the technical solution can improve the recognition efficiency of the target area on the basis of ensuring the recognition accuracy of the target area, quickly remove the invalid scanning area in the original CT image, and avoid labor costs.

[0065] The following Figure 3 The specific implementation methods of each step of the illustrated embodiment are described in detail:

[0066] In an exemplary embodiment, the target region extracted from the original CT image based on the present solution is used in the disease diagnosis process. For example, CT image data of the brain is extracted from the original CT image to diagnose the brain. In step S310, the target region is determined to be the brain, and the cavity surrounding the brain can be determined to be the skull. Furthermore, the specific implementation method of obtaining the CT image data of the above cavity in the original CT image is as follows:

[0067] Among them, in CT images, HU (Hounsfield Units) is used to reflect the degree of absorption of X-rays by organs and tissues. Since the tissues in the cavity (i.e. the above-mentioned target area, such as the brain) and the cavity (such as the skull) absorb X-rays to different degrees and the difference is large, the CT image data of the cavity can be obtained based on the difference between the HU data corresponding to the tissues in the cavity and the HU data corresponding to the cavity. For example, the HU value range of brain tissue is generally between 0 and 100, while the HU value range of the skull is generally above 400. Then, by extracting data with a HU value range of 400 to 800 from the original CT image, the HU value of the skull (such as Figure 4 CT image data shown).

[0068] Exemplarily, in step S310, it is determined that the target area may also be the thoracic tissue (such as the heart and / or lungs), and the cavity surrounding the thoracic tissue may be determined to be the sternum. Further, a specific implementation of obtaining the CT image data of the sternum in the original CT image may also be: obtaining the CT image data of the sternum based on the difference between the HU data corresponding to the thoracic tissue and the HU data corresponding to the sternum. Exemplarily, in step S310, it is determined that the target area may also be the pelvic tissue (such as one or more of the uterus, bladder, and ovaries), and the cavity surrounding the pelvic tissue may be determined to be the pelvis. Further, a specific implementation of obtaining the CT image data of the pelvis in the original CT image may also be: obtaining the CT image data of the pelvis based on the difference between the HU data corresponding to the pelvic tissue and the HU data corresponding to the pelvis.

[0069] It should be noted that the target area is not limited to the above-mentioned brain, thoracic tissue and pelvic tissue, but can also be other parts, which are not limited here.

[0070] refer to Figure 4 For the original CT image containing the invalid scanning area, the CT image data of the cavity surrounding the target area is determined based on the embodiment corresponding to step S310. Based on the CT image data of the cavity, steps S410 and S420 are respectively performed to determine the first outer surface of the target area in step S410 and the second outer surface of the target area in step S420. Then, the original CT image is clipped based on the first outer surface and the second outer surface to obtain a CT image of the target area.

[0071] The target area is taken as an example of the brain, and the cavity surrounding the brain is described by taking the skull as an example: in step S320, multiple sections of the skull are obtained according to the CT image data of the skull, and the external position of the brain can be determined according to the multiple sections based on the shape characteristics of the skull as prior information. That is, the starting position and the ending position of the brain can be determined in the vertical axis direction of the original CT image. Further, the original CT image is intercepted at the above starting position and ending position to obtain the brain area.

[0072] refer to Figure 5In this exemplary embodiment, the method for determining the outer envelope position of the target area includes: step S510, acquiring multiple transverse sections of the cavity according to the CT image data of the cavity, and based on the shape characteristics of the transverse sections, screening out a target transverse section from the multiple transverse sections as a first outer envelope surface of the target area; step S520, acquiring multiple coronal sections of the cavity according to the CT image data of the cavity, determining a target position in each coronal section based on the shape characteristics of the coronal sections, and determining a second outer envelope surface of the target area opposite to the first outer envelope surface according to the multiple target positions corresponding to the multiple coronal sections; and step S530, obtaining the outer envelope position of the target area according to the first outer envelope surface and the second outer envelope surface.

[0073] The target area is taken as the brain, and the cavity surrounding the brain is taken as the skull: Figure 6 , the skull is divided into upper and lower sections according to the section line AA, recorded as the transverse section; the skull is divided into left and right sections according to the section line BB, recorded as the sagittal section; the skull is divided into front and back sections according to the section line parallel to the paper, recorded as the coronal section. As a priori information, the transverse section of the skull is circular. As another priori information, the coronal section of the skull is approximately elliptical, that is, the width in the middle is larger and the width on both sides is smaller.

[0074] In an exemplary embodiment, the method determines the brain starting position on the CT vertical axis (i.e., the first outer surface) with reference to the shape of the cross-sectional surface of the skull. Figure 7 : Determine multiple transverse sections 52 based on the CT image data of the skull 51 (step S511), and scan the multiple transverse sections in sequence according to a preset direction (step S512). In order to determine the first outer surface located on the upper side of the brain, the preset direction is the direction from the top of the skull to the bottom of the skull. Further, based on the prior information that the transverse section of the skull is circular, determine whether a hollow area appears in the scan result (step S513). If a hollow area appears in the scan result, it means that the hollow part of the cross section belongs to the brain area.

[0075] Therefore, in response to the absence of a hollow area in the scan result, it indicates that the current transverse section has not reached the brain region, and step S511 is continued to be executed to obtain a transverse section and scan. In response to the presence of a hollow area in the scan result, it indicates that the interface with the brain region (i.e., the first outer surface) is reached, and step S514 is executed: the current transverse section is determined as the target transverse section, and the scanning of the next transverse section is stopped, and the position of the target transverse section in the original CT image is used as the first outer surface of the brain.

[0076] In an exemplary embodiment, the method determines the brain end position on the CT vertical axis (i.e., the second outer surface) with reference to the shape of the coronal section of the skull. Figure 8 : Determine N (positive integer) coronal sections according to the CT image data of the skull 51 (step S521), such as Figure 8 The coronal cross sections 53, 54, and 55 are obtained in sequence from the front side to the back side of the skull. For each coronal cross section, the skull width of the current coronal cross section is calculated multiple times according to a preset direction (step S522). In order to determine the second outer envelope located at the lower side of the brain, the preset direction may be the direction from the top to the bottom of the coronal plane.

[0077] Specifically, based on the prior information that the coronal section of the skull is elliptical, that is, the skull width value in the direction from the top to the bottom of the coronal plane first gradually increases to the maximum skull width and then gradually decreases. Therefore, for the i-th (a positive integer not greater than N) coronal section, determine whether the currently calculated skull width is greater than the maximum width calculated last time (step S523). If so, it means that the currently calculated skull width has not reached the widest point, and the current width is determined to be the maximum skull width of the i-th coronal section (step S524). And calculate and execute steps S522 and S523 for iterative calculations until it is determined that the currently calculated skull width is not greater than the maximum width calculated last time, and then determine the maximum skull width corresponding to the i-th coronal section. And further execute step S525.

[0078] If not, it means that the currently calculated skull width is already below the widest point, and then it is further determined whether the current skull width is less than t times the maximum skull width (t is a hyperparameter, a positive number less than 1) (step S525). If it is determined that the current skull width is not less than t times the maximum skull width, it means that the current position has not reached the bottom of the coronal plane, or has not reached the lower edge of the brain, then steps S522, S523 and S525 are continued to be iteratively calculated. If it is determined that the current skull width is less than t times the maximum skull width, it means that the current position has reached the lower edge of the brain, then step S526 is executed: the position corresponding to the current skull width is the target position of the i-th coronal section. Among them, in order to adapt to the needs of the target area in different scenarios, the cropping effect may be adjusted by the size of the hyperparameter t, so that the range of the target area can be flexibly controlled.

[0079] In an exemplary embodiment, after the target positions corresponding to the respective coronal slices are determined, in step S527, the second outer surface of the brain is determined according to the target positions corresponding to the N coronal slices.

[0080] Exemplarily, one implementation method of determining the second outer surface according to the above-mentioned target position is: respectively calculate the distances between the above-mentioned N target positions and the first outer surface, and determine the second outer surface of the brain according to the target position with the largest distance value from the first outer surface. In other words, the end position farthest from the top of the skull is taken as the end position of the brain area, so as to ensure the robustness and stability of the technical solution and avoid excessive shearing. The second outer surface determined according to this embodiment is a plane, which has the effect of determining the second outer surface of the target area more conveniently and quickly. Among them, the target area determined according to this embodiment includes as many brain areas as possible, providing more comprehensive CT image data for subsequent medical diagnosis.

[0081] Exemplarily, another implementation of determining the second outer envelope according to the target position is: fitting a surface according to the target positions corresponding to the N coronal sections, and using the fitted surface as the second outer envelope of the brain. The second outer envelope determined according to this embodiment is a curved surface, which has the effect of more accurately determining the target area. The target area determined according to this embodiment fits the real brain shape and contains less redundant data.

[0082] It should be noted that the greater the value of the number N of the coronal sections, the more accurate the second outer envelope is. The specific value of N can be determined according to actual needs and is not limited here.

[0083] In an exemplary embodiment, the first outer surface and the second outer surface are used as the external position of the target area in step S530. Then, the original CT image is intercepted based on the first outer surface and the second outer surface, and the invalid scanning area can be cut out from the original CY image to obtain the CT image data of the target area.

[0084] refer to Figure 9a For the original CT image 91 (shown as a sagittal section) containing the redundant scanning area, the original CT image 91 is uploaded to the back end through the front end A. The back end is deployed with the target area acquisition program provided by the present technical solution. Thus, the first outer surface and the second outer surface of the target area are acquired at the back end, and the original CT image 91 is intercepted based on the first outer surface and the second outer surface. Finally, the intercepted target area 91' (shown as a sagittal section) is output to the front end B. Reference Figure 9b, for the original CT image 92 (shown as a sagittal section) containing the repeated scanning area, the original CT image 92 is uploaded to the back end through the front end A. Among them, the back end is deployed with the target area acquisition program provided by the present technical solution. Therefore, the first outer surface and the second outer surface of the target area are acquired at the back end, and the original CT image 92 is intercepted based on the first outer surface and the second outer surface. Finally, the intercepted target area 92' (shown as a sagittal section) is output to the front end B.

[0085] Exemplarily, the front end A and the front end B may belong to the same terminal or different terminals, and this is not limited.

[0086] It can be seen that this solution provides an efficient and robust automatic extraction solution for target areas in CT images, which can improve the recognition efficiency of target areas while ensuring the recognition accuracy of target areas, so as to remove invalid scan parts in the original CT images and save labor costs. It can be applied to the diagnosis process in medical scenarios, and the acquired target areas can also be used as data sets in artificial intelligence scenarios for training or testing machine learning models.

[0087] Those skilled in the art will appreciate that all or part of the steps to implement the above embodiments are implemented as a computer program executed by a processor (including a GPU / CPU). When the computer program is executed by the GPU / CPU, the above functions defined by the above method provided in the present disclosure are performed. The program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk or an optical disk, etc.

[0088] In addition, it should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiment of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0089] The following Fig.10 An embodiment of a target model training device disclosed in the present invention is introduced, which can be used to execute the target model training method disclosed above.

[0090] Fig.10 FIG. 2 is a schematic diagram showing a structure of a device for determining a target area in a CT image in an exemplary embodiment of the present disclosure. Fig.10 As shown, the device 1000 for determining a target region in the CT image comprises: an acquisition module 1001 , an outsourcing position determination module 1002 and a target region determination module 1003 .

[0091] Among them, the above-mentioned acquisition module 1001 is configured to: acquire CT image data of the cavity surrounding the target area in the original CT image; the above-mentioned external position determination module 1002 is configured to: acquire multiple sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, and determine the external position of the above-mentioned target area based on the shape characteristics of the above-mentioned cavity and the above-mentioned multiple sections; and the above-mentioned target area determination module 1003 is configured to: intercept the above-mentioned target area in the above-mentioned original CT image according to the above-mentioned external position.

[0092] In some embodiments of the present disclosure, based on the aforementioned scheme, the acquisition module 1001 is specifically configured to: acquire CT image data surrounding the cavity in the original CT image based on the Hounsfield unit HU data corresponding to the cavity and the Hounsfield unit HU data corresponding to the target area.

[0093] In some embodiments of the present disclosure, based on the above-mentioned solution, the above-mentioned outsourcing position determination module 1002 includes: a transverse section processing unit, a coronal section processing unit and an outsourcing position determination unit.

[0094] Wherein, the above-mentioned transverse section processing unit is configured to: obtain multiple transverse sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, and based on the shape characteristics of the above-mentioned transverse sections, screen out a target transverse section from the above-mentioned multiple transverse sections as the first outer surface of the above-mentioned target area; the above-mentioned coronal section processing unit is configured to: obtain multiple coronal sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, determine the target position in each coronal section based on the shape characteristics of the coronal sections, and determine the second outer surface of the target area opposite to the first outer surface according to the multiple target positions corresponding to the multiple coronal sections; and the above-mentioned outer surface determination unit is configured to: obtain the outer surface position of the above-mentioned target area according to the above-mentioned first outer surface and the above-mentioned second outer surface.

[0095] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being a circle, the above-mentioned transverse section processing unit is specifically configured to: scan the above-mentioned multiple transverse sections in sequence according to a preset direction; in response to the appearance of a hollow area in the scanning result, determine that the current transverse section is the above-mentioned target transverse section, and stop scanning the next transverse section; and, use the position of the above-mentioned target transverse section in the above-mentioned original CT image as the first outer surface of the above-mentioned target area.

[0096] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being an ellipse, wherein the above-mentioned coronal section processing unit includes a position determination subunit, and is specifically configured as: scanning N coronal sections in sequence along a preset direction, N being a positive integer; for the i-th coronal section, performing multiple cavity width calculations in a preset direction, i being a positive integer not greater than N; determining the maximum cavity width corresponding to the i-th coronal section; and when the current cavity width is less than a preset multiple of the above-mentioned maximum cavity width, determining the position corresponding to the current cavity width as the target position of the i-th coronal section.

[0097] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being an ellipse, the above-mentioned coronal section processing unit includes an outer surface determination subunit, and is configured to: calculate the distances between the above-mentioned multiple target positions and the above-mentioned first outer surface respectively; and determine the second outer surface of the above-mentioned target area according to the target position having the largest distance value from the above-mentioned first outer surface.

[0098] In some embodiments of the present disclosure, based on the aforementioned scheme, based on the shape feature of the above-mentioned transverse section being an ellipse, wherein the above-mentioned coronal section processing unit includes an outer surface determination subunit, and is configured to: determine a surface by fitting according to the target positions corresponding to the above-mentioned N coronal sections, and use the fitted determined surface as the second outer surface of the above-mentioned target area.

[0099] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area determination module 1003 is specifically configured to: intercept the original CT image at the first outer surface and the second outer surface, respectively, and take the portion between the first outer surface and the second outer surface as the target area.

[0100] In some embodiments of the present disclosure, based on the above scheme, the device for determining the target area in the CT image further includes: a sample determination module. The sample determination module is configured to: use the CT image data of the target area as model training sample data to train the machine learning model.

[0101] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area is the brain, and the acquisition module 1001 is specifically configured as follows: based on the fact that the HU data corresponding to the brain tissue is different from the HU data corresponding to the skull surrounding the brain, the CT image data of the skull is acquired in the original CT image according to the HU data corresponding to the skull.

[0102] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area is the intrathoracic tissue, and the acquisition module 1001 is specifically configured as follows: based on the fact that the HU data corresponding to the intrathoracic tissue is different from the HU data corresponding to the sternum surrounding the intrathoracic tissue, the CT image data surrounding the sternum is acquired in the original CT image according to the HU data corresponding to the sternum.

[0103] In some embodiments of the present disclosure, based on the aforementioned scheme, the target area is pelvic tissue, and the acquisition module 1001 is specifically configured as follows: based on the fact that the HU data corresponding to the pelvic tissue is different from the HU data corresponding to the pelvic bone surrounding the pelvic tissue, the CT image data of the pelvis surrounding the target area is acquired in the original CT image according to the HU data corresponding to the pelvic bone.

[0104] The specific details of each unit in the above-mentioned device for determining a target region in a CT image have been described in detail in the method for determining a target region in an original CT image, and thus will not be repeated here.

[0105] Fig.11 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present disclosure is shown.

[0106] It should be noted that Fig.11 The computer system 1100 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0107] like Fig.11 As shown, the computer system 1100 includes a processor 1101, wherein the processor 1101 may specifically include: a graphics processing unit (Graphics Processing Unit, referred to as: GPU) and a central processing unit (Central Processing Unit, referred to as: CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory (Read-Only Memory, referred to as: ROM) 1102 or the program loaded from the storage part 1108 to the random access memory (Random Access Memory, referred to as: RAM) 1103. In RAM 1103, various programs and data required for system operation are also stored. The processor 1101, ROM 1102 and RAM 1103 are connected to each other through a bus 1104. An input / output (Input / Output, referred to as: I / O) interface 1105 is also connected to the bus 1104.

[0108] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a local area network (LAN) card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed so that a computer program read therefrom is installed into the storage section 1108 as needed.

[0109] In particular, according to an embodiment of the present disclosure, the process described below with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1109, and / or installed from a removable medium 1111. When the computer program is executed by the processor 1101, various functions defined in the system of the present application are executed.

[0110] It should be noted that the computer-readable medium shown in the embodiment of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0111] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0113] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment. For example, the electronic device may implement the following: Figure 3 As shown in: step S310, obtaining CT image data of a cavity surrounding a target area in an original CT image; step S320, obtaining multiple cross-sections of the cavity based on the CT image data of the cavity, and determining the outer position of the target area based on the shape characteristics of the cavity and the multiple cross-sections; and step S330, intercepting the target area in the original CT image according to the outer position.

[0114] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0115] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0116] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0117] It should be understood that the present disclosure is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A method for determining a target area in a CT image, characterized in that: The method comprises: Acquiring CT image data of a cavity surrounding a target area in an original computed tomography (CT) image; Acquire multiple transverse sections of the cavity according to the CT image data of the cavity, and select a target transverse section from the multiple transverse sections as a first outer surface of the target area based on shape characteristics of the transverse sections; Acquire multiple coronal sections of the cavity according to the CT image data of the cavity; based on the shape feature of the coronal section being an ellipse, sequentially scan N coronal sections in a preset direction, where N is a positive integer; for the i-th coronal section, perform multiple cavity width calculations in a preset direction, where i is a positive integer not greater than N; determine the maximum cavity width corresponding to the i-th coronal section; when the current cavity width is less than a preset multiple of the maximum cavity width, determine the position corresponding to the current cavity width as the target position of the i-th coronal section, and determine the second outer envelope of the target area opposite to the first outer envelope according to the multiple target positions corresponding to the multiple coronal sections; Obtaining the outer envelope position of the target area according to the first outer envelope surface and the second outer envelope surface; The target area is intercepted in the original CT image according to the outer position.

2. The method according to claim 1, characterized in that The step of acquiring CT image data of a cavity surrounding a target area in an original CT image includes: Based on the Hounsfield unit HU data corresponding to the cavity and the Hounsfield unit HU data corresponding to the target area, CT image data surrounding the cavity is acquired in the original CT image.

3. The method according to claim 1, characterized in that Based on the shape feature of the transverse section being a circle, wherein selecting a target transverse section from the plurality of transverse sections as a first outer surface of the target area comprises: Scanning the multiple transverse sections sequentially along a preset direction; In response to a hollow area appearing in the scanning result, determining the current transverse section as the target transverse section, and stopping scanning of the next transverse section; The position of the target transverse section in the original CT image is used as the first outer surface of the target area.

4. The method according to claim 1, characterized in that The step of determining a second outer surface of the target area opposite to the first outer surface according to the multiple target positions corresponding to the multiple coronal sections comprises: Calculating the distances between the plurality of target positions and the first outer surface respectively; The second outer surface of the target area is determined according to the target position having the largest distance value from the first outer surface.

5. The method according to claim 1, characterized in that The step of determining a second outer surface of the target area opposite to the first outer surface according to the multiple target positions corresponding to the multiple coronal sections comprises: A curved surface is determined by fitting according to the target positions respectively corresponding to the N coronal sections, and the curved surface determined by fitting is used as the second outer surface of the target area.

6. The method according to any one of claims 1 to 5, characterized in that The intercepting the target area in the original CT image according to the outsourcing position comprises: The original CT image is intercepted at the first outer surface and the second outer surface respectively, and the portion between the first outer surface and the second outer surface is used as the target area.

7. The method according to claim 6, characterized in that The method further comprises: The CT image data of the target area is used as model training sample data to train the machine learning model.

8. The method according to any one of claims 1 to 5, characterized in that The target area is the brain, and acquiring CT image data of a cavity surrounding the target area in the original CT image includes: Because the HU data corresponding to the brain tissue is different from the HU data corresponding to the skull surrounding the brain, the CT image data of the skull is acquired in the original CT image according to the HU data corresponding to the skull.

9. The method according to any one of claims 1 to 2, characterized in that: The target area is tissue in the chest cavity, and the step of acquiring CT image data of a cavity surrounding the target area in the original CT image includes: Because the HU data corresponding to the intrathoracic tissue is different from the HU data corresponding to the sternum surrounding the intrathoracic tissue, the CT image data surrounding the sternum is acquired in the original CT image according to the HU data corresponding to the sternum.

10. The method according to any one of claims 1 to 2, characterized in that: The target area is tissue in the pelvic cavity, and the step of acquiring CT image data of a cavity surrounding the target area in the original CT image includes: Because the HU data corresponding to the pelvic tissue is different from the HU data corresponding to the pelvic bone surrounding the pelvic tissue, CT image data of the pelvic bone surrounding the target area is acquired in the original CT image according to the HU data corresponding to the pelvic bone.

11. A device for determining a target area in a CT image, characterized in that: The device comprises: An acquisition module is configured to: acquire CT image data of a cavity surrounding a target area in an original computed tomography (CT) image; The outer covering position determination module includes: a transverse section processing unit, a coronal section processing unit and an outer covering position determination unit. The transverse section processing unit is configured to: obtain multiple transverse sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, and based on the shape characteristics of the above-mentioned transverse sections, select a target transverse section from the above-mentioned multiple transverse sections as the first outer covering surface of the above-mentioned target area; the coronal section processing unit is configured to: obtain multiple coronal sections of the above-mentioned cavity according to the CT image data of the above-mentioned cavity, and based on the shape characteristics of the coronal section being elliptical, sequentially scan N coronal sections in a preset direction, where N is A positive integer; for the i-th coronal section, multiple cavity width calculations are performed in a preset direction, where i is a positive integer not greater than N; the maximum cavity width corresponding to the i-th coronal section is determined; when the current cavity width is less than a preset multiple of the maximum cavity width, the position corresponding to the current cavity width is determined as the target position of the i-th coronal section, and a second outer covering surface of the target area opposite to the first outer covering surface is determined according to the multiple target positions corresponding to the multiple coronal sections; the outer covering position determination unit is configured to: obtain the outer covering position of the target area according to the first outer covering surface and the second outer covering surface; The target region determination module is configured to intercept the target region in the original CT image according to the outsourcing position.

12. A computer-readable storage medium, characterized in that: A computer program is stored thereon; When the computer program is executed by a processor, the method for determining a target area in a computed tomography (CT) image according to any one of claims 1 to 10 is implemented.

13. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method for determining a target area in a computed tomography (CT) image as described in any one of claims 1 to 10.

14. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for determining a target area in a computed tomography (CT) image as described in any one of claims 1 to 10.

Images