Intestinal image reconstruction method, device and equipment and computer readable storage medium

Abstract

The invention discloses an intestinal image reconstruction method, apparatus and device, and a computer readable storage medium. The method comprises the steps of obtaining a magnetic resonance image corresponding to a target intestinal region; determining intestinal wall region information of the target intestinal region according to the magnetic resonance image; extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information; and reconstructing a target intestinal image according to the intestinal wall region information and the intestinal image information. According to the invention, the safety of obtaining the intestinal image can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, equipment and computer-readable storage medium for intestinal image reconstruction. Background Art

[0002] With the improvement of living standards, the dietary structure and nutritional composition of residents have changed significantly. At the same time, the fast pace of life, high pressure, irregular diet, and intestinal problems are becoming more and more prominent. In the medical field, imaging examination is one of the important ways to examine intestinal system diseases. Commonly used ones include colonoscopy, ultrasound, X-ray, CT, magnetic resonance imaging, radionuclide examination, etc.

[0003] However, although colonoscopy can observe the internal conditions of the intestine, it is very harmful to patients and the experience is poor. Radioactive imaging such as X-rays and CT also causes certain radiation damage to the human body and is not suitable for post-image processing. It can be seen that the current intestinal imaging acquisition scheme used for diagnosis needs to be improved in safety. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, equipment and computer-readable storage medium for reconstructing intestinal images, aiming to improve the safety of obtaining intestinal images.

[0005] In a first aspect, an embodiment of the present invention provides a method for reconstructing an intestinal image, comprising:

[0006] Acquire magnetic resonance images corresponding to the target intestinal region;

[0007] Determining intestinal wall region information of the target intestinal region according to the magnetic resonance image;

[0008] extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information;

[0009] The target intestinal image is reconstructed according to the intestinal wall area information and the intestinal image information.

[0010] Optionally, determining the intestinal wall area information of the target intestinal area according to the magnetic resonance image includes:

[0011] For the sub-images of each magnetic resonance channel of the magnetic resonance image, determining the initial intestinal region and / or the initial intestinal wall region in the sub-images;

[0012] Determine a target intestinal wall region according to the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel;

[0013] The target intestinal wall area is measured to extract the intestinal wall area information.

[0014] Optionally, determining the target intestinal wall region according to the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel includes:

[0015] Acquire an overlapping area between the initial intestinal area and the initial intestinal wall area;

[0016] The overlapping area is set as the target intestinal wall area.

[0017] Optionally, before acquiring the magnetic resonance image corresponding to the target intestinal area, the method further includes:

[0018] Acquiring initial magnetic resonance images of a plurality of different sections of the target intestinal region by means of a magnetic resonance device;

[0019] For each magnetic resonance channel, acquiring a plurality of sub-initial images of different slices corresponding to the magnetic resonance channel from the initial magnetic resonance image;

[0020] sorting the sub-initial images according to the section positions corresponding to the sub-initial images;

[0021] fitting a sub-image of the target intestinal region corresponding to the magnetic resonance channel according to the sorted sub-initial images;

[0022] The magnetic resonance image is composed according to the sub-images corresponding to the respective magnetic resonance channels.

[0023] Optionally, the intestinal wall region information includes intestinal radius and intestinal section information, and extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information includes:

[0024] Obtaining the intestinal centerline within the target intestinal region;

[0025] Based on the intestinal radius and the intestinal section information, the magnetic resonance image is tracked along the intestinal centerline to obtain the intestinal image information from the magnetic resonance image.

[0026] Optionally, reconstructing a target intestinal image according to the intestinal wall region information and the intestinal image information includes:

[0027] Constructing a three-dimensional intestinal model according to the intestinal wall area information and the intestinal centerline;

[0028] The intestinal three-dimensional model is rendered according to the intestinal image information to obtain the target intestinal image.

[0029] Optionally, after reconstructing the target intestinal image according to the intestinal wall area information and the intestinal image information, the method further includes:

[0030] Inputting the target intestinal image and the intestinal wall area information into a preset intestinal health prediction model to obtain a health prediction result;

[0031] An intestinal examination report is outputted according to the health prediction result and the target intestinal image.

[0032] In a second aspect, an embodiment of the present invention provides an intestinal image reconstruction device, the intestinal image reconstruction device comprising:

[0033] An acquisition module, used for acquiring a magnetic resonance image corresponding to a target intestinal region;

[0034] A determination module, configured to determine intestinal wall region information of the target intestinal region according to the magnetic resonance image;

[0035] An extraction module, used for extracting intestinal image information from the magnetic resonance image based on the intestinal wall area information;

[0036] A construction module is used to reconstruct a target intestinal image according to the intestinal wall area information and the intestinal image information.

[0037] In a third aspect, an embodiment of the present invention further provides an intestinal image reconstruction device, comprising a processor and a memory, wherein the memory stores a computer program. When the computer program is executed by the processor, the processor executes the steps of any intestinal image reconstruction method provided by the embodiment of the present invention.

[0038] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, which includes a computer program. When the computer program runs on an electronic device, the computer program is used to enable the electronic device to execute the steps of any intestinal image reconstruction method provided by the embodiment of the present invention.

[0039] The present invention first obtains a magnetic resonance image corresponding to a target intestinal region; determines the intestinal wall region information of the target intestinal region based on the magnetic resonance image; extracts intestinal image information from the magnetic resonance image based on the intestinal wall region information; and reconstructs the target intestinal image based on the intestinal wall region information and the intestinal image information. In this way, by obtaining a magnetic resonance image corresponding to the target intestinal region, determining the intestinal wall region information in the intestinal region from the magnetic resonance image, and extracting the intestinal image information, the target intestinal image can be reconstructed by combining the intestinal wall region information and the intestinal image information. The doctor can make a diagnosis based on the target intestinal image. This process does not require radioactive imaging or colonoscopy of the user, and a complete and accurate target intestinal image can be obtained, thereby improving the safety of obtaining intestinal images. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 is a flow chart of an embodiment of a method for reconstructing intestinal images provided in an embodiment of the present invention;

[0042] Figure 2 is the magnetic resonance image involved in the embodiment of the present invention;

[0043] Figure 3 is the target intestinal image involved in the embodiment of the present invention;

[0044] Figure 4 is a schematic diagram of the structure of an intestinal image reconstruction device provided in an embodiment of the present invention;

[0045] Figure 5 Schematic diagram of the structure of the intestinal image reconstruction device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention. At the same time, in the description of the embodiments of the present invention, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0047] Embodiments of the present invention provide a method and apparatus for reconstructing intestinal images, an intestinal image reconstruction device, and a computer-readable storage medium.

[0048] Specifically, this embodiment will be described from the perspective of an intestinal image reconstruction device, which can be integrated into an intestinal image reconstruction device, that is, the intestinal image reconstruction method of the embodiment of the present invention can be executed by the intestinal image reconstruction device.

[0049] The following is a detailed description in conjunction with the accompanying drawings. In this embodiment, the execution subject is an intestinal image reconstruction device as an example. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments. Although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that shown in the accompanying drawings.

[0050] According to the background technology of the present invention, although colonoscopy can observe the internal conditions of the intestine, it is very harmful to patients and the experience is poor. Radioactive imaging such as X-rays and CT also has certain radiation damage to the human body and is not suitable for later image processing. It can be seen that the current intestinal image acquisition scheme used for diagnosis has a need to improve its safety.

[0051] In order to solve the above problems, the present invention discloses a method for reconstructing intestinal images. Figure 1 The specific process of the intestinal image reconstruction method can be as follows: Step S10 to Step S40, wherein:

[0052] Step S10, obtaining a magnetic resonance image corresponding to the target intestinal area;

[0053] In this embodiment, a magnetic resonance image of a target object is acquired by a magnetic resonance device, thereby obtaining a magnetic resonance image of a target intestinal region of the target object. The target object may be an organism with biological characteristics, such as a human body, a pet, etc. The target object includes an intestinal tract, and the region on the target object that includes the intestinal tract is the intestinal region, and the target intestinal region may be a region that includes all or part of the intestinal tract of the target object. According to the difference in intestinal diseases detected in the target object, the abdominal region may be divided in detail and an image may be acquired. A magnetic resonance image corresponding to the target intestinal region is acquired.

[0054] Magnetic resonance (MR) imaging is a medical imaging technique that uses magnetic fields and radio waves to obtain images of the internal structures of the human body. Unlike X-rays or CT scans, MRI does not use radiation, but uses a strong magnetic field and radio wave pulses to excite hydrogen nuclei in the body, and then detects the signals released when these nuclei return to their original state. These signals are processed by a computer to generate images of the inside of the body.

[0055] Optionally, a magnetic resonance scan is performed on the abdominal area of ​​the target object to obtain a magnetic resonance image of the abdominal area, a pre-trained physiological tissue segmentation algorithm is used to segment the physiological tissue in the abdominal area, and a magnetic resonance image that may contain the target intestinal area is extracted. The segmentation can quickly identify most of the physiological tissue in the abdominal area so that noise can be removed more quickly later.

[0056] Step S20, determining the intestinal wall area information of the target intestinal area according to the magnetic resonance image;

[0057] In this embodiment, since the magnetic resonance image is an image that can reflect the inside of the body, the magnetic resonance image of the target intestinal area can reflect the intestinal condition in the target intestinal area. However, the magnetic resonance image is generally a two-dimensional image, and it is a cross-sectional image, which cannot intuitively give a detailed intestinal image. Therefore, it is necessary to extract the intestinal wall area information based on the magnetic resonance image corresponding to the target intestinal area. Through further analysis and processing of the magnetic resonance image, for example, using image processing techniques such as threshold segmentation, edge detection, regional growth or more advanced machine learning algorithms, etc., to identify and segment each image area in the magnetic resonance image. The tissue information of the target object represented by each image area in the magnetic resonance image, such as blood vessels, intestinal wall, intestinal cavity, etc., and then by measuring each image area in the magnetic resonance image, the intestinal wall area information can be obtained. The intestinal wall area information is the relevant data information of the intestinal wall of the intestine, which may include geometric information such as the thickness, diameter, and trend of the intestinal wall.

[0058] Step S30, extracting intestinal image information from the magnetic resonance image based on the intestinal wall area information;

[0059] In this embodiment, the intestinal wall area information is geometric information about the intestinal wall. Based on the intestinal wall area information, the area range of the intestinal wall and the intestinal cavity in the intestine can be delineated. The area range can also be applied to magnetic resonance imaging to extract the image area containing the intestinal area in the magnetic resonance image. The image area is what is called the true value area in medicine, and the image information within the image area, such as pixel value, brightness, contrast, etc., is extracted as intestinal image information.

[0060] Step S40: reconstructing a target intestinal image according to the intestinal wall area information and the intestinal image information.

[0061] In this embodiment, the intestinal wall area information is the geometric information of the intestine in the target intestinal area. According to the intestinal wall area information, the intestinal model can be reconstructed. The intestinal model can be a three-dimensional intestinal model, which fully reflects the morphology of the intestine in the target intestinal area. Optionally, morphological operations such as expansion, corrosion, opening and closing operations can also be performed on the reconstructed intestinal model to improve the details of the intestinal model. Surface smoothing algorithms can also be applied to reduce noise and discontinuities that may be generated during the reconstruction process, and refine the intestinal surface to make it smoother and more natural. The intestinal model is rendered by intestinal image information to obtain a target intestinal image, so that the target intestinal image can more intuitively and distinctively characterize the characteristics of the intestine in the target intestinal area, including lesions and tissue areas of different colors, which are displayed differently in the target intestinal image. The reconstructed target intestinal image can stereoscopically and accurately reflect the characteristics of the intestine in the target intestinal area. The target intestinal image can assist doctors in diagnosis, surgical planning or patient education, etc., and can improve the efficiency of medical work.

[0062] In the technical solution disclosed in this embodiment, the magnetic resonance image corresponding to the target intestinal area is first obtained; the intestinal wall area information of the target intestinal area is determined based on the magnetic resonance image; the intestinal image information is extracted from the magnetic resonance image based on the intestinal wall area information; and the target intestinal image is reconstructed based on the intestinal wall area information and the intestinal image information. In this way, by obtaining the magnetic resonance image corresponding to the target intestinal area, determining the intestinal wall area information in the intestinal area from the magnetic resonance image, and extracting the intestinal image information, the target intestinal image can be reconstructed by combining the intestinal wall area information and the intestinal image information. Figure 2 Doctors can make diagnoses based on the target intestinal images. This process does not require radioactive imaging or colonoscopy of the user to obtain complete and accurate target intestinal images, thereby improving the safety of obtaining intestinal images. The reconstructed target intestinal images are also mainly intestinal images within the target intestinal area, reducing the impact of other non-intestinal areas on the observation of the target intestine. The reconstructed target intestinal images can assist doctors in diagnosis, surgical planning or patient education, etc., and can improve the efficiency of medical work.

[0063] Furthermore, step S20 of “determining the intestinal wall region information of the target intestinal region according to the magnetic resonance image” may also include:

[0064] For the sub-images of each magnetic resonance channel of the magnetic resonance image, determining the initial intestinal region and / or the initial intestinal wall region in the sub-images;

[0065] Determine a target intestinal wall region according to the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel;

[0066] The target intestinal wall area is measured to extract the intestinal wall area information.

[0067] In this embodiment, magnetic resonance imaging uses strong magnetic fields and radio waves to produce detailed images of the internal structures of the human body. When performing an MRI examination, different pulse sequences are used to obtain different types of images. The pulse sequences are called magnetic resonance channels. Each magnetic resonance channel can highlight different tissue characteristics, thereby providing complementary information. For example, channel T1-weighted imaging (T1-weighted imaging) is often used to display anatomical structures, in which fat tissue appears bright, while water and muscle tissue are darker. Channel T2-weighted imaging (T2-weighted imaging) can highlight tissues that contain more water, such as cysts or edema, and these areas will appear brighter in the image. Different magnetic resonance channels can observe different information, refer to Figure 3 The intestinal wall region in the magnetic resonance image containing the target intestinal region is preliminarily determined by integrated analysis of multiple channel information of the MR image.

[0068] First, the sub-images of each magnetic resonance channel of the magnetic resonance image are segmented to obtain the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel, and then the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel are integrated and analyzed to determine the target intestinal wall region.

[0069] In some embodiments, the weight of the tissue type that can be displayed by each magnetic resonance channel can be determined based on the attribute information of each magnetic resonance channel, that is, some weights are given to the display of different tissue types, and the higher the weight, the clearer the display content is, and then the tissue area corresponding to the tissue type is extracted from each magnetic resonance channel according to the tissue type, and the tissue area will include the initial intestinal wall area and / or the intestinal wall area. The target intestinal wall area is determined based on the weight of each magnetic resonance channel for the initial intestinal wall area and / or the initial intestinal area, and its corresponding initial intestinal wall area and / or intestinal wall area. After determining the target intestinal wall area, the intestinal wall area information of the target intestinal wall area can be extracted by measuring the target intestinal wall area.

[0070] In this way, the sub-images of each magnetic resonance channel of the magnetic resonance image can represent different tissue information, and after the initial intestinal area and / or initial intestinal wall area corresponding to the sub-image are determined, a more accurate target intestinal wall area is integrated, and the geometric intestinal wall area information is measured, thereby further improving the accuracy of reconstructing the target intestinal image.

[0071] Furthermore, the step of “determining the target intestinal wall region according to the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel” may include:

[0072] Acquire an overlapping area between the initial intestinal area and the initial intestinal wall area;

[0073] The overlapping area is set as the target intestinal wall area.

[0074] In this embodiment, each magnetic resonance channel can display a different range of tissue regions, but they can all accurately reflect the regional intestinal information actually detected by the magnetic resonance channel in which they are located. After the intestinal wall region is determined in a sub-image of a magnetic resonance channel and the intestinal wall region is determined in another magnetic channel, the overlapping region after the integration of the two can be considered to belong to the intestinal region and the intestinal wall region, then it must belong to the intestinal wall region and has a high degree of feasibility. For example, region 1 extracted by channel A in the MR image is a possible intestinal region, and region 2 extracted by channel B is a possible intestinal wall region, then the overlapping region between region 1 and region 2 is the intestinal wall region. By integrating and judging the initial intestinal region corresponding to the sub-images of multiple channels and the overlapping region in the initial intestinal wall region, the target intestinal wall region can be accurately judged.

[0075] In this way, the overlapping area between the initial intestinal area and the initial intestinal wall area corresponding to the sub-images through multiple channels is used as the target intestinal wall area, which further improves the intestinal wall area information and thus further improves the accuracy of reconstructing the target intestinal image.

[0076] Furthermore, before the step of “obtaining a magnetic resonance image corresponding to the target intestinal region”, the method further includes:

[0077] Acquiring initial magnetic resonance images of a plurality of different sections of the target intestinal region by means of a magnetic resonance device;

[0078] For each magnetic resonance channel, acquiring a plurality of sub-initial images of different slices corresponding to the magnetic resonance channel from the initial magnetic resonance image;

[0079] sorting the sub-initial images according to the section positions corresponding to the sub-initial images;

[0080] fitting a sub-image of the target intestinal region corresponding to the magnetic resonance channel according to the sorted sub-initial images;

[0081] The magnetic resonance image is composed according to the sub-images corresponding to the respective magnetic resonance channels.

[0082] In this embodiment, the target object is scanned by a magnetic resonance device to obtain magnetic resonance images of different sections of the target object's abdominal region, so that initial magnetic resonance images of multiple different sections of the target intestinal region can be segmented. For each magnetic resonance channel, sub-initial images of several sections corresponding to the magnetic resonance channel can be obtained from the initial magnetic resonance image, and then the sub-initial images can be sorted according to the section positions corresponding to the sub-initial images, so as to obtain a slice sequence of sub-initial images of the target intestinal region under the magnetic resonance channel. After the sub-initial images are sorted, the slice positions corresponding to two adjacent sub-initial images are the closest, and the intestine has a certain continuity at the slice position. By performing non-maximum suppression on the sub-initial images, the boundary lines of various tissue regions in the sub-initial images are optimized to make them clearer, and then the boundary lines of various tissue regions can be determined by comparing the pixel values ​​in the optimized sub-initial images or by threshold segmentation, and then fitting can be performed based on the boundary lines of various regions in the sorted sub-initial images, such as using interpolation technology to fill in missing data, and using a three-dimensional modeling algorithm to construct a continuous structure of the intestine, so as to fit the sub-image of the complete target intestinal region corresponding to the magnetic resonance channel, and the sub-images corresponding to each magnetic resonance channel then constitute the magnetic resonance image of the target intestinal region.

[0083] In this way, by using the initial magnetic resonance images of different sections, the sub-images of the complete target intestinal area are fitted in different channels to form a magnetic resonance image. By combining the sub-images of each magnetic resonance channel, the target intestinal wall area can be integrated more accurately and completely, thereby further improving the accuracy of reconstructing the target intestinal image.

[0084] Furthermore, the intestinal wall region information may include intestinal radius and intestinal section information, and the step of “extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information” may include:

[0085] Constructing a three-dimensional intestinal model according to the intestinal wall area information and the intestinal centerline;

[0086] The intestinal three-dimensional model is image-filled according to the intestinal image information to obtain the target intestinal image.

[0087] In this embodiment, the intestinal wall area information is the geometric information of the intestine, and the intestinal wall area information includes the intestinal radius and intestinal section information. The intestinal centerline in the target intestinal area is obtained, and the intestinal centerline represents the trend of the intestine in the target intestinal area. After the intestinal image is reconstructed, the point on the intestinal centerline is located at the center of the horizontal cross-section of the intestine corresponding to the point in the intestinal image. Because the trend of the human intestine is basically the same, the intestinal centerline can also be preset information. In some embodiments, the intestinal centerline can also be determined based on the center of the target intestinal area of ​​the target object in the magnetic resonance image.

[0088] After obtaining the intestinal centerline within the target intestinal area, the intestinal wall area information is used as a reference to determine the image area that meets the intestinal screening conditions corresponding to the intestinal wall area information in the magnetic resonance image, that is, determine the true value area in the image, and extract the true value area as the intestinal image information.

[0089] For example, the target intestinal wall regions are a, b, c, and d, and geometric information such as the intestinal radius and intestinal section can be extracted from these target intestinal wall regions as intestinal wall region information. Based on these geometric information, the intestinal centerline is tracked to determine the complete intestinal image information in the medical image.

[0090] In this way, based on the geometric information of the intestinal radius and intestinal section information, the magnetic resonance image is tracked along the centerline of the intestine, thereby obtaining complete intestinal image information in the magnetic resonance image, thereby improving the integrity of the intestinal image information and further improving the accuracy of reconstructing the target intestinal image.

[0091] Furthermore, the step of “reconstructing the target intestinal image according to the intestinal wall area information and the intestinal image information” may include:

[0092] Constructing a three-dimensional intestinal model according to the intestinal wall area information and the intestinal centerline;

[0093] The intestinal three-dimensional model is image-filled according to the intestinal image information to obtain the target intestinal image.

[0094] In this embodiment, based on the intestinal wall area information, the intestinal 3D model is constructed along the intestinal centerline. Specifically, according to the intestinal centerline, the intestinal 3D path is first constructed, and the intestinal wall area information and the 3D path are used to create the intestinal 3D surface through surface reconstruction technology such as Marching Cubes algorithm to obtain the intestinal 3D model. The surface of the reconstructed intestinal 3D model is smoothed to reduce noise and discontinuity and improve the visual effect of the model. According to human anatomy, the intestinal 3D model is morphologically adjusted and dimensionally corrected to ensure the anatomical accuracy of the model.

[0095] Similarly, along the center line of the intestine, the intestinal 3D model is rendered according to the intestinal image information, and the intestinal 3D model is colored to distinguish between normal intestinal wall areas, lesion areas on the intestinal wall, intestinal cavity areas, intestinal wall folds, etc., to obtain a three-dimensional target intestinal image.

[0096] In this way, the intestinal 3D model is constructed through the intestinal wall area information and the intestinal centerline, and the intestinal 3D model is rendered according to the intestinal image information to obtain a 3D target intestinal image. The intestinal condition can be observed more intuitively based on the target intestinal image, so as to further improve the efficiency of auxiliary medical treatment.

[0097] Furthermore, after “reconstructing a target intestinal image according to the intestinal wall area information and the intestinal image information”, it also includes:

[0098] Inputting the target intestinal image and the intestinal wall area information into a preset intestinal health prediction model to obtain a health prediction result;

[0099] An intestinal examination report is outputted according to the health prediction result and the target intestinal image.

[0100] In this embodiment, the target intestinal image and intestinal wall area information can be preprocessed first, such as standardization, normalization or feature extraction, to meet the input requirements of the model. Among them, the target intestinal image can reflect the condition of the intestine in the target intestinal area from a global perspective, while the intestinal wall area information can reflect the condition of the intestine from direct data. For example, if the intestinal radius of a certain position is too large, then the feature information corresponding to the intestinal radius of the position and the feature information corresponding to the target intestinal image can be combined and fused to determine whether there is a lesion in the area. Then, the preprocessed target intestinal image and intestinal wall area information are input into a preset intestinal health prediction model. The intestinal health prediction model integrates the target intestinal image and intestinal wall area information to obtain the lesion location and the corresponding lesion type, and then forms and outputs an intestinal examination report based on the lesion location and lesion type to further assist doctors in treatment, thereby improving diagnostic efficiency.

[0101] This embodiment also provides a device for reconstructing an intestinal image, which can be integrated into an intestinal image reconstruction device. Figure 4 As shown, the intestinal image reconstruction device may include:

[0102] An acquisition module 1001 is used to acquire a magnetic resonance image corresponding to a target intestinal region;

[0103] A determination module 1002, configured to determine intestinal wall region information of the target intestinal region according to the magnetic resonance image;

[0104] An extraction module 1003, configured to extract intestinal image information from the magnetic resonance image based on the intestinal wall region information;

[0105] The construction module 1004 is used to reconstruct the target intestinal image according to the intestinal wall area information and the intestinal image information.

[0106] Optionally, the determination module 1002 is further configured to:

[0107] For the sub-images of each magnetic resonance channel of the magnetic resonance image, determining the initial intestinal region and / or the initial intestinal wall region in the sub-images;

[0108] Determine a target intestinal wall region according to the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel;

[0109] The target intestinal wall area is measured to extract the intestinal wall area information.

[0110] Optionally, the determination module 1002 is further configured to:

[0111] Acquire an overlapping area between the initial intestinal area and the initial intestinal wall area;

[0112] The overlapping area is set as the target intestinal wall area.

[0113] Optionally, the acquisition module 1001 is further used for:

[0114] Acquiring initial magnetic resonance images of a plurality of different sections of the target intestinal region by means of a magnetic resonance device;

[0115] For each magnetic resonance channel, acquiring a plurality of sub-initial images of different slices corresponding to the magnetic resonance channel from the initial magnetic resonance image;

[0116] sorting the sub-initial images according to the section positions corresponding to the sub-initial images;

[0117] fitting a sub-image of the target intestinal region corresponding to the magnetic resonance channel according to the sorted sub-initial images;

[0118] The magnetic resonance image is composed according to the sub-images corresponding to the respective magnetic resonance channels.

[0119] Optionally, the intestinal wall region information includes intestinal radius and intestinal section information, and the extraction module 1003 is further used to:

[0120] Obtaining the intestinal centerline within the target intestinal region;

[0121] Based on the intestinal radius and the intestinal section information, the magnetic resonance image is tracked along the intestinal centerline to obtain the intestinal image information from the magnetic resonance image.

[0122] Optionally, the construction module 1004 is further configured to:

[0123] Constructing a three-dimensional intestinal model according to the intestinal wall area information and the intestinal centerline;

[0124] The intestinal three-dimensional model is rendered according to the intestinal image information to obtain the target intestinal image.

[0125] Optionally, the intestinal image reconstruction device may further include:

[0126] A reporting module, used for inputting the target intestinal image and the intestinal wall area information into a preset intestinal health prediction model to obtain a health prediction result;

[0127] An intestinal examination report is outputted according to the health prediction result and the target intestinal image.

[0128] In this embodiment, a magnetic resonance image corresponding to a target intestinal region is obtained; intestinal wall region information of the target intestinal region is determined based on the magnetic resonance image; intestinal image information is extracted from the magnetic resonance image based on the intestinal wall region information; and a target intestinal image is reconstructed based on the intestinal wall region information and the intestinal image information. In this way, by obtaining a magnetic resonance image corresponding to a target intestinal region, determining intestinal wall region information in the intestinal region from the magnetic resonance image, and extracting intestinal image information, the target intestinal image can be reconstructed by combining the intestinal wall region information and the intestinal image information. Figure 2 Doctors can make diagnoses based on the target intestinal images. This process does not require radioactive imaging or colonoscopy of the user to obtain complete and accurate target intestinal images, thereby improving the safety of obtaining intestinal images. The reconstructed target intestinal images are also mainly intestinal images within the target intestinal area, reducing the impact of other non-intestinal areas on the observation of the target intestine. The reconstructed target intestinal images can assist doctors in diagnosis, surgical planning or patient education, etc., and can improve the efficiency of medical work.

[0129] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0130] like Figure 5 As shown, Figure 5 A schematic diagram of the structure of an intestinal image reconstruction device provided in an embodiment of the present invention. The intestinal image reconstruction device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. Those skilled in the art will appreciate that the intestinal image reconstruction device structure shown in the figure does not constitute a limitation on the intestinal image reconstruction device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0131] The processor 1101 is the control center of the intestinal image reconstruction device 1100. It uses various interfaces and lines to connect various parts of the entire intestinal image reconstruction device 1100, and executes various functions and processes data of the intestinal image reconstruction device 1100 by running or loading software programs and / or units stored in the memory 1102, and calling data stored in the memory 1102, so as to monitor the intestinal image reconstruction device 1100 as a whole. The processor 1101 can be a processor CPU, a graphics processor GPU, a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention.

[0132] In the embodiment of the present invention, the processor 1101 in the intestinal image reconstruction device 1100 will load instructions corresponding to the processes of one or more application programs into the memory 1102 according to the following steps, and the processor 1101 will run the application programs stored in the memory 1102 to implement various functions, such as:

[0133] Acquire magnetic resonance images corresponding to the target intestinal region;

[0134] Determining intestinal wall region information of the target intestinal region according to the magnetic resonance image;

[0135] extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information;

[0136] The target intestinal image is reconstructed according to the intestinal wall area information and the intestinal image information.

[0137] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0138] Optional, such as Figure 5 As shown, the intestinal image reconstruction device 1100 also includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106 and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106 and the power supply 1107 respectively. Those skilled in the art can understand that Figure 5 The intestinal image reconstruction device structure shown in the figure does not constitute a limitation of the intestinal image reconstruction device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0139] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the intestinal image reconstruction device, and these graphical user interfaces can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-EmittingDiode), etc. The touch panel can be used to collect the user's touch operation on or near it (such as the user uses any suitable object or attachment such as a finger, a stylus, etc. on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 1101, and can receive the command sent by the processor 1101 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event, and then the processor 1101 provides corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present invention, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 1103 can also be used as a part of the input unit 1106 to realize the input function.

[0140] The radio frequency circuit 1104 may be used to send and receive radio frequency signals, so as to establish wireless communication with a network device or other intestinal image reconstruction devices through wireless communication, and to send and receive signals between the network device or other intestinal image reconstruction devices.

[0141] The audio circuit 1105 can be used to provide an audio interface between the user and the intestinal image reconstruction device through a speaker and a microphone. The audio circuit 1105 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and converted into audio data, and then the audio data is output to the processor 1101 for processing, and then sent to another intestinal image reconstruction device through the radio frequency circuit 1104, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earplug jack to provide communication between an external headset and the intestinal image reconstruction device.

[0142] The input unit 1106 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0143] The power supply 1107 is used to supply power to various components of the intestinal image reconstruction device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 1107 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0144] although Figure 5 Not shown, the intestinal image reconstruction device 1100 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be repeated here.

[0145] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0146] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0147] To this end, an embodiment of the present invention provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer program can be loaded by a processor to execute any of the intestinal image reconstruction methods provided by the embodiments of the present invention. The computer program can execute the following steps of the intestinal image reconstruction method:

[0148] Acquire magnetic resonance images corresponding to the target intestinal region;

[0149] Determining intestinal wall region information of the target intestinal region according to the magnetic resonance image;

[0150] extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information;

[0151] The target intestinal image is reconstructed according to the intestinal wall area information and the intestinal image information.

[0152] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0153] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0154] Since the computer program stored in the computer-readable storage medium can execute any of the intestinal image reconstruction methods provided in the embodiments of the present invention, the beneficial effects that can be achieved by any of the intestinal image reconstruction methods provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0155] In the above-mentioned intestinal image reconstruction device, computer-readable storage medium, intestinal image reconstruction equipment, and computer program product embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, refer to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the intestinal image reconstruction device, computer-readable storage medium, computer program product, intestinal image reconstruction equipment and its corresponding units described above can refer to the description of the intestinal image reconstruction method in the above embodiment, and will not be repeated here.

[0156] The above is a detailed introduction to an intestinal image reconstruction method, an intestinal image reconstruction device, an intestinal image reconstruction equipment, a computer-readable storage medium and a computer program product provided by an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for reconstructing intestinal images, characterized in that: The intestinal image reconstruction method comprises: Acquire magnetic resonance images corresponding to the target intestinal region; Determining intestinal wall region information of the target intestinal region according to the magnetic resonance image; extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information; The target intestinal image is reconstructed according to the intestinal wall area information and the intestinal image information.

2. The intestinal image reconstruction method according to claim 1, characterized in that: The determining the intestinal wall area information of the target intestinal area according to the magnetic resonance image includes: For the sub-images of each magnetic resonance channel of the magnetic resonance image, determining the initial intestinal region and / or the initial intestinal wall region in the sub-images; Determine a target intestinal wall region according to the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel; The target intestinal wall area is measured to extract the intestinal wall area information.

3. The intestinal image reconstruction method according to claim 2, characterized in that: Determining the target intestinal wall region according to the initial intestinal region and / or the initial intestinal wall region in the sub-images of each magnetic resonance channel includes: Acquire an overlapping area between the initial intestinal area and the initial intestinal wall area; The overlapping area is set as the target intestinal wall area.

4. The intestinal image reconstruction method according to claim 1, characterized in that: Before acquiring the magnetic resonance image corresponding to the target intestinal area, the method further includes: Acquiring initial magnetic resonance images of a plurality of different sections of the target intestinal region by means of a magnetic resonance device; For each magnetic resonance channel, acquiring a plurality of sub-initial images of different slices corresponding to the magnetic resonance channel from the initial magnetic resonance image; sorting the sub-initial images according to the section positions corresponding to the sub-initial images; fitting a sub-image of the target intestinal region corresponding to the magnetic resonance channel according to the sorted sub-initial images; The magnetic resonance image is composed according to the sub-images corresponding to the respective magnetic resonance channels.

5. The intestinal image reconstruction method according to claim 1, characterized in that: The intestinal wall region information includes intestinal radius and intestinal section information, and extracting intestinal image information from the magnetic resonance image based on the intestinal wall region information includes: Obtaining the intestinal centerline within the target intestinal region; Based on the intestinal radius and the intestinal section information, the magnetic resonance image is tracked along the intestinal centerline to obtain the intestinal image information from the magnetic resonance image.

6. The intestinal image reconstruction method according to claim 5, characterized in that: The step of reconstructing a target intestinal image according to the intestinal wall region information and the intestinal image information includes: Constructing a three-dimensional intestinal model according to the intestinal wall area information and the intestinal centerline; The intestinal three-dimensional model is rendered according to the intestinal image information to obtain the target intestinal image.

7. The intestinal image reconstruction method according to any one of claims 1 to 6, characterized in that: After reconstructing the target intestinal image according to the intestinal wall area information and the intestinal image information, the method further includes: Inputting the target intestinal image and the intestinal wall area information into a preset intestinal health prediction model to obtain a health prediction result; An intestinal examination report is outputted according to the health prediction result and the target intestinal image.

8. A device for reconstructing intestinal images, characterized in that: The intestinal image reconstruction device comprises: An acquisition module, used for acquiring a magnetic resonance image corresponding to a target intestinal region; A determination module, configured to determine intestinal wall region information of the target intestinal region according to the magnetic resonance image; An extraction module, used for extracting intestinal image information from the magnetic resonance image based on the intestinal wall area information; A construction module is used to reconstruct a target intestinal image according to the intestinal wall area information and the intestinal image information.

9. An intestinal image reconstruction device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the intestinal image reconstruction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the intestinal image reconstruction method according to any one of claims 1 to 7.

Images