T2DM cognitive impairment detection method and system based on image feature fusion

Abstract

The invention relates to the field of T2DM cognitive impairment detection, and discloses a T2DM cognitive impairment detection method and system based on image feature fusion, and the method comprises the steps: obtaining a structural MRI examination image, a CT examination image and a TCD examination image of a patient; determining brain structural features of the patient according to the structural MRI examination image and the CT examination image, determining brain texture features of the patient according to the structural MRI examination image and the CT examination image through a gray level co-occurrence matrix, and determining cerebral hemodynamic features of the patient according to the TCD examination image; wherein the brain structure features comprise gray matter and white matter volume features, cortex thickness features and ventricular size features; and determining a T2DM cognitive impairment detection result through a cognitive impairment detection model according to the brain structure features, the brain texture features and the cerebral hemodynamic features of the patient. According to the invention, the diagnosis efficiency of the cognitive impairment of the T2DM patient according to the detection result can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of T2DM cognitive impairment detection, and more specifically, to a T2DM cognitive impairment detection method and system based on image feature fusion. Background Art

[0002] Type 2 diabetes mellitus (T2DM) is a chronic metabolic disease that is prevalent worldwide. It not only has a serious impact on the quality of life of patients, but is also closely related to the occurrence of a variety of complications. In recent years, more and more studies have pointed out that the incidence of cognitive impairment in T2DM patients is significantly higher than that in non-diabetic patients. Cognitive impairment is mainly manifested as memory loss, inattention, executive dysfunction, etc., and can progress to dementia in severe cases. The mechanism of cognitive impairment caused by T2DM is complex, involving abnormal insulin signaling pathways, chronic inflammation, oxidative stress, cerebrovascular disease and other aspects. Therefore, early detection and intervention of cognitive impairment in T2DM patients is of great significance for delaying the progression of the disease and improving patient prognosis.

[0003] With the development of medical imaging technology, structural MRI (Magnetic Resonance Imaging), CT (Computed Tomography) and transcranial Doppler ultrasound (TCD) have played an important role in the detection of cognitive impairment in T2DM. Structural MRI can clearly show changes in brain structure, such as reduced hippocampal volume and brain atrophy, which are closely related to cognitive decline. CT scans are helpful in detecting cerebrovascular lesions such as cerebral infarction and microbleeding, which are more common in T2DM patients and are related to the occurrence of cognitive impairment. As a non-invasive examination method, TCD can evaluate the blood flow velocity and resistance of cerebral vessels and provide hemodynamic information for diagnosis. At present, the early detection and risk stratification of cognitive impairment in T2DM patients mainly rely on the experience of doctors to judge structural MRI, CT and transcranial Doppler ultrasound, resulting in low efficiency in diagnosing cognitive impairment in T2DM patients based on experience and test results. Summary of the invention

[0004] The purpose of this application is to provide a T2DM cognitive impairment detection method and system based on image feature fusion, which solves the technical problem of low diagnostic efficiency of cognitive impairment in T2DM patients based on test results based on experience, and achieves the technical effect of improving the diagnostic efficiency of cognitive impairment in T2DM patients based on test results.

[0005] The embodiment of the present application provides a T2DM cognitive impairment detection method based on image feature fusion, the method comprising: acquiring a patient's structural MRI examination image, a CT examination image and a TCD examination image; determining the patient's brain structural features based on the structural MRI examination image and the CT examination image, determining the patient's brain texture features based on the structural MRI examination image and the CT examination image through a grayscale co-occurrence matrix, and determining the patient's cerebral hemodynamic characteristics based on the TCD examination image; wherein the brain structural features include volume features of gray matter and white matter, cortical thickness features and ventricle size features, and the cerebral hemodynamic features include blood flow velocity features and blood flow direction features; and determining the T2DM cognitive impairment detection result based on the patient's brain structural features, brain texture features and cerebral hemodynamic characteristics through a cognitive impairment detection model.

[0006] In a possible implementation, the patient's brain structure characteristics are determined based on the structural MRI examination images and the CT examination images, and the patient's brain texture characteristics are determined based on the structural MRI examination images and the CT examination images through the grayscale co-occurrence matrix, including: determining the gray matter area, white matter area and ventricular area of ​​the patient's brain structure based on the structural MRI examination images and the CT examination images; determining the volume characteristics, cortical thickness characteristics and ventricular size characteristics of the patient's brain structure based on the gray matter area, white matter area and ventricular area; and determining the texture characteristics of the gray matter area, white matter area and ventricular area through the grayscale co-occurrence matrix as the patient's brain texture characteristics.

[0007] In another possible implementation, the method further includes: determining the patient's cerebrovascular position based on the TCD examination image, and determining the patient's ventricular area boundary based on the structural MRI examination image and the CT examination image; wherein the cerebrovascular position is the position of the cerebrovascular relative to the ventricular area; through a cognitive impairment detection model, the T2DM cognitive impairment detection result is determined according to the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position and ventricular area boundary; wherein the cerebrovascular position and ventricular area boundary are used to determine the cerebrovascular position offset characteristics caused by brain atrophy.

[0008] In another possible implementation, the position of the patient's cerebrovascular vessels is determined based on the TCD examination image, including: reconstructing the brain MRI three-dimensional structure through the structural MRI examination image, aligning the brain MRI three-dimensional structure and the TCD examination image, and determining the three-dimensional position coordinates of the cerebrovascular vessels in the TCD examination image on the brain MRI three-dimensional structure as the patient's cerebrovascular position.

[0009] In another possible implementation, the method also includes: obtaining theoretical cerebrovascular position coordinates on the three-dimensional structure of brain MRI, and determining the cerebrovascular position coordinate difference between the theoretical cerebrovascular position coordinates and the three-dimensional position coordinates; when the cerebrovascular position coordinate difference is greater than or equal to the preset cerebrovascular position coordinate difference, determining the T2DM cognitive impairment detection result through a cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics, and cerebral hemodynamic characteristics; when the cerebrovascular position coordinate difference is less than the preset cerebrovascular position coordinate difference, determining the T2DM cognitive impairment detection result through a cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position, and ventricular area boundary.

[0010] In another possible implementation, the method also includes: obtaining multiple MRI tomographic images of the patient's structural MRI examination images and tomographic detection positions corresponding to the multiple MRI tomographic images, determining multiple target MRI tomographic images with similar coordinates of the tomographic detection positions and cerebrovascular positions in the multiple MRI tomographic images, and determining brain structural features and brain texture features of brain structural features corresponding to the multiple target MRI tomographic images; through a cognitive impairment detection model, determining T2DM cognitive impairment detection results based on the brain structural features, brain texture features, cerebral hemodynamic characteristics, cerebrovascular positions and ventricular area boundaries corresponding to the multiple target MRI tomographic images.

[0011] In another possible implementation, the method also includes: determining first boundaries of gray matter areas, white matter areas, and ventricular areas in a first target MRI tomography image; when the first boundaries are all continuous boundaries, determining T2DM cognitive impairment detection results based on brain structure features, brain texture features, cerebral hemodynamic features, cerebral vascular locations, and ventricular area boundaries corresponding to the first target MRI tomography image.

[0012] In another possible implementation, the method also includes: determining the gray matter area and the white matter area in the first target MRI tomography image, and when the area ratio of the white matter area to the gray matter area is greater than a preset area ratio, and when the first boundaries are all continuous boundaries, determining the T2DM cognitive impairment detection result according to the brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebral blood vessel position and ventricular area boundaries corresponding to the first target MRI tomography image.

[0013] An embodiment of the present application also provides a T2DM cognitive impairment detection system based on image feature fusion, comprising a unit for executing any of the methods described above.

[0014] An embodiment of the present application also provides a T2DM cognitive impairment detection system based on image feature fusion, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0015] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in any one of the above items is implemented.

[0016] An embodiment of the present application also provides a computer program product, including a computer program, which implements the steps of any of the methods described above when executed by a processor.

[0017] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0018] The embodiment of the present application provides a T2DM cognitive impairment detection method based on image feature fusion, and the method includes: obtaining a patient's structural MRI examination image, a CT examination image, and a TCD examination image; determining the patient's brain structural features according to the structural MRI examination image and the CT examination image, determining the patient's brain texture features according to the structural MRI examination image and the CT examination image through the grayscale co-occurrence matrix, and determining the patient's cerebral hemodynamic features according to the TCD examination image; wherein the brain structural features include the volume features of gray matter and white matter, the cortical thickness features, and the ventricle size features, and the cerebral hemodynamic features include the blood flow velocity features and the blood flow direction features; through the cognitive impairment detection model, according to the patient's brain structural features, brain texture features, and cerebral hemodynamic features, determine the T2DM cognitive impairment detection results. The method in the embodiment of the present application can combine MRI examination images, CT examination images, and TCD examination images, and determine the T2DM cognitive impairment detection results according to the brain structural features, brain texture features, and cerebral hemodynamic features, thereby improving the efficiency and accuracy of T2DM cognitive impairment detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 A schematic diagram of a flow chart of a T2DM cognitive impairment detection method based on image feature fusion provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the workflow of a T2DM cognitive impairment detection method based on image feature fusion provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the workflow of another T2DM cognitive impairment detection method based on image feature fusion provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the flow of a second method for detecting cognitive impairment in T2DM based on image feature fusion provided in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of a process of a third method for detecting cognitive impairment in T2DM based on image feature fusion provided in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of the flow of a fourth method for detecting cognitive impairment in T2DM based on image feature fusion provided in an embodiment of the present application;

[0026] Figure 7 A schematic diagram of the logical structure of a T2DM cognitive impairment detection system based on image feature fusion provided in an embodiment of the present application;

[0027] Figure 8 A schematic diagram of the physical structure of a T2DM cognitive impairment detection system based on image feature fusion provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0029] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0030] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0031] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] At present, the early detection and risk stratification of cognitive impairment in T2DM patients mainly rely on the doctors' experience to judge structural MRI, CT and transcranial Doppler ultrasound, resulting in low efficiency in diagnosing cognitive impairment in T2DM patients based on experience and test results.

[0034] Based on the above reasons, the embodiment of the present application provides a T2DM cognitive impairment detection method based on image feature fusion, the method comprising: obtaining a patient's structural MRI examination image, a CT examination image and a TCD examination image; determining the patient's brain structural features according to the structural MRI examination image and the CT examination image, determining the patient's brain texture features according to the structural MRI examination image and the CT examination image through the grayscale co-occurrence matrix, and determining the patient's cerebral hemodynamic features according to the TCD examination image; wherein the brain structural features include the volume features of gray matter and white matter, the cortical thickness features and the ventricular size features, and the cerebral hemodynamic features include the blood flow velocity features and the blood flow direction features; through the cognitive impairment detection model, according to the patient's brain structural features, brain texture features and cerebral hemodynamic features, determine the T2DM cognitive impairment detection results. The method in the embodiment of the present application can combine MRI examination images, CT examination images and TCD examination images, and determine the T2DM cognitive impairment detection results according to the brain structural features, brain texture features and cerebral hemodynamic features, thereby improving the efficiency and accuracy of T2DM cognitive impairment detection.

[0035] In some scenarios, a T2DM cognitive impairment detection method based on image feature fusion in an embodiment of the present application can be applied to the early detection and risk stratification of cognitive impairment in T2DM patients, which can improve the efficiency and accuracy of T2DM cognitive impairment detection.

[0036] The following is a detailed description of a T2DM cognitive impairment detection method based on image feature fusion provided in an embodiment of the present application with reference to specific examples.

[0037] Figure 1 A schematic diagram of a T2DM cognitive impairment detection method based on image feature fusion provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes S110 to S120, and S110 to S120 are described in detail below.

[0038] S110, obtaining the patient's structural MRI examination images, CT examination images and TCD examination images. Determine the patient's brain structural features based on the structural MRI examination images and CT examination images, determine the patient's brain texture features based on the structural MRI examination images and CT examination images through the gray level co-occurrence matrix, and determine the patient's cerebral hemodynamic characteristics based on the TCD examination images. Among them, the brain structural features include the volume features of gray matter and white matter, the cortical thickness features and the ventricle size features, and the cerebral hemodynamic features include the blood flow velocity features and the blood flow direction features.

[0039] Figure 2 A schematic diagram of the workflow of a T2DM cognitive impairment detection method based on image feature fusion provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, when the method in the embodiment of the present application is working, the patient's structural MRI examination images, CT examination images and TCD examination images can be first obtained, and then the patient's brain structure characteristics can be determined based on the structural MRI examination images and CT examination images. The brain structure characteristics characterize the characteristics of the brain in the brain examination structure. Through the brain structure characteristics, the atrophy of the hippocampus and frontal lobe and other areas of the brain structure can be determined, thereby realizing the identification of the potential risk of cognitive impairment in T2DM.

[0040] Illustratively, brain structural features may include volume features of gray matter and white matter, cortical thickness features, and ventricle size features.

[0041] When the method in the embodiment of the present application is working, it can also determine the patient's brain texture features based on the structural MRI examination images and CT examination images through the grayscale co-occurrence matrix. The brain texture features characterize the microstructural changes in the brain examination images, and then the brain state can be identified based on the microstructure in the brain examination images.

[0042] When the method in the embodiment of the present application is working, the patient's cerebral hemodynamic characteristics can also be determined based on the TCD examination images. The cerebral hemodynamic characteristics can characterize the blood flow velocity and resistance of the cerebral blood vessels. Diabetic patients may show a decrease in blood flow velocity or increased volatility. The patient's brain blood supply health status can be determined based on the cerebral hemodynamic characteristics, and the patient's potential T2DM cognitive impairment can be identified.

[0043] Exemplarily, the cerebral hemodynamic characteristics may include blood flow velocity characteristics and blood flow direction characteristics.

[0044] For example, the blood flow velocity characteristics and the blood flow direction characteristics can be represented by marking the blood flow velocity and the blood flow direction on the structural MRI examination image and the CT examination image.

[0045] S120. Determine the T2DM cognitive impairment detection result through the cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics and cerebral hemodynamic characteristics.

[0046] like Figure 2 As shown, after obtaining the brain structure characteristics, brain texture characteristics and cerebral hemodynamic characteristics, the T2DM cognitive impairment detection results can be determined through the cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics and cerebral hemodynamic characteristics, thereby achieving accurate identification of the T2DM cognitive impairment detection results based on the patient's brain examination structural characteristics, brain microscopic texture structure, and brain blood supply health status.

[0047] The beneficial effect of the above-mentioned implementation method is that it can accurately identify the T2DM cognitive impairment detection results based on the patient's brain examination structural characteristics, the microscopic texture structure of the brain, and the healthy status of brain blood supply, thereby improving the accurate detection of T2DM cognitive impairment.

[0048] In some implementations, in the above S110, the patient's brain structure features are determined based on the structural MRI examination images and the CT examination images, and the patient's brain texture features are determined based on the structural MRI examination images and the CT examination images through the gray level co-occurrence matrix, including: determining the gray matter area, white matter area and ventricular area of ​​the patient's brain structure based on the structural MRI examination images and the CT examination images. The volume features, cortical thickness features and ventricular size features of the patient's brain structure are determined based on the gray matter area, white matter area and ventricular area. The texture features of the gray matter area, white matter area and ventricular area are determined by the gray level co-occurrence matrix as the patient's brain texture features.

[0049] Figure 3 A schematic diagram of the workflow of another T2DM cognitive impairment detection method based on image feature fusion provided in an embodiment of the present application is shown in FIG. Figure 3As shown, in the method in the embodiment of the present application, the gray matter area, white matter area and ventricular area of ​​the patient's brain structure can be determined according to the structural MRI examination images and CT examination images through an edge recognition algorithm, and the gray matter area, white matter area and ventricular area are different areas of the brain.

[0050] like Figure 3 As shown, after obtaining the gray matter area, white matter area and ventricular area, the volume characteristics, cortical thickness characteristics and ventricular size characteristics of the patient's brain structure can be determined according to the gray matter area, white matter area and ventricular area, and then the potential risk of T2DM cognitive impairment can be determined according to the volume characteristics, cortical thickness characteristics and ventricular size characteristics.

[0051] like Figure 3 As shown, after obtaining the gray matter area, white matter area and ventricular area, the texture features of the gray matter area, white matter area and ventricular area can be determined respectively through the gray-level co-occurrence matrix as the patient's brain texture features, and then the potential risk of T2DM cognitive impairment can be improved according to the brain texture features of the gray matter area, white matter area and ventricular area.

[0052] The beneficial effect of the above-mentioned implementation method is that by identifying the gray matter area, white matter area and ventricular area of ​​the patient's brain structure, the volume characteristics, cortical thickness characteristics, ventricular size characteristics can be determined in the gray matter area, white matter area and ventricular area of ​​the patient's brain structure, respectively, and the texture characteristics of the gray matter area, white matter area and ventricular area can be determined, so as to improve the reliability of determining the risk of cognitive impairment in T2DM based on the characteristics of the gray matter area, white matter area and ventricular area.

[0053] Figure 4 A schematic diagram of the flow of a second method for detecting cognitive impairment in T2DM based on image feature fusion provided in an embodiment of the present application is shown in FIG. Figure 4 As shown, the above method further includes S210 to S220, and S210 to S220 are described in detail below.

[0054] S210, determining the position of the patient's cerebral blood vessels according to the TCD examination image, and determining the boundary of the patient's ventricle region according to the structural MRI examination image and the CT examination image, wherein the position of the cerebral blood vessels is the position of the cerebral blood vessels relative to the ventricle region.

[0055] In order to further improve the accuracy of identifying the risk of cognitive impairment in T2DM, the location of the patient's cerebrovascular vessels can be determined based on the TCD examination images, and the state of brain atrophy can be identified based on the location of the cerebrovascular vessels.

[0056] In order to further improve the accuracy of identifying the risk of cognitive impairment in T2DM, the patient's ventricular regional boundaries can be determined based on structural MRI examination images and CT examination images. The ventricular regional boundaries represent the boundaries of the space corresponding to the ventricles. The atrophy state of the brain can then be determined based on the comparison of the ventricular regional boundaries and the position of cerebral blood vessels, thereby improving the accuracy of identifying the risk of cognitive impairment in T2DM.

[0057] Illustratively, the cerebral blood vessel position is the position of the cerebral blood vessel relative to the ventricular region.

[0058] S220. Determine the T2DM cognitive impairment detection result through the cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position and ventricular regional boundaries. Among them, the cerebrovascular position and ventricular regional boundaries are used to determine the cerebrovascular position deviation characteristics caused by brain atrophy.

[0059] When identifying the risk of cognitive impairment in T2DM, the cognitive impairment detection model can be used to determine the T2DM cognitive impairment detection results based on the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position and ventricular regional boundaries. The cerebrovascular position and ventricular regional boundaries are used to determine the cerebrovascular position deviation characteristics caused by brain atrophy, and then the accuracy of identifying the risk of cognitive impairment in T2DM can be improved by combining the cerebrovascular position deviation characteristics on the basis of S110 to S120.

[0060] For example, when there is a large difference between the position of the cerebrovascular position and the position of the ventricular area boundary, it indicates that there is a high possibility that the cerebrovascular position is shifted due to brain atrophy, and the patient has a higher risk of T2DM cognitive impairment.

[0061] For example, when the difference between the position of the cerebrovascular position and the position of the ventricular area boundary is small, it means that the possibility of cerebrovascular position displacement due to brain atrophy is small, and the patient's risk of T2DM cognitive impairment is small.

[0062] The beneficial effect of the above implementation method is that the cerebrovascular position deviation characteristics caused by brain atrophy can be determined by the cerebrovascular position and the ventricular area boundary, and the accuracy of identifying the risk of cognitive impairment in T2DM can be improved by combining the cerebrovascular position deviation characteristics.

[0063] In some implementations, in the above-mentioned S210, the position of the patient's cerebrovascular vessels is determined based on the TCD examination image, including: reconstructing the brain MRI three-dimensional structure through the structural MRI examination image, aligning the brain MRI three-dimensional structure and the TCD examination image, and determining the three-dimensional position coordinates of the cerebrovascular vessels in the TCD examination image on the brain MRI three-dimensional structure as the patient's cerebrovascular position.

[0064] In order to further improve the accuracy of risk identification of cognitive impairment in T2DM, the three-dimensional structure of brain MRI can be reconstructed through structural MRI examination images, and the three-dimensional structure of brain MRI and TCD examination images can be registered to obtain the three-dimensional position coordinates of cerebrovascular vessels in the TCD examination image on the three-dimensional structure of brain MRI. This is used as the patient's cerebrovascular position, thereby realizing the position mapping of cerebrovascular positions in TCD examination images to the three-dimensional structure of brain MRI.

[0065] For example, when reconstructing the three-dimensional structure of brain MRI through structural MRI examination images, it can be achieved through medical image processing software, such as FSL, SPM, FreeSurfer, 3D Slicer, etc.

[0066] The beneficial effect of the above-mentioned implementation method is that by aligning the brain MRI three-dimensional structure and the TCD examination image, and determining the three-dimensional position coordinates of the cerebral blood vessels in the TCD examination image on the brain MRI three-dimensional structure, the accuracy of identifying the risk of cognitive impairment in T2DM can be improved by combining the cerebral blood vessel position offset characteristics.

[0067] Figure 5 A schematic diagram of the process of the third T2DM cognitive impairment detection method based on image feature fusion provided in the embodiment of the present application is shown in FIG. Figure 5 As shown, the above method also includes S310 to S320, and S310 to S320 are described in detail below.

[0068] S310, obtaining theoretical cerebrovascular position coordinates on the three-dimensional structure of brain MRI, and determining the cerebrovascular position coordinate difference between the theoretical cerebrovascular position coordinates and the three-dimensional position coordinates.

[0069] In order to further determine whether the detection results of the cerebrovascular position coordinates are accurate, the theoretical cerebrovascular position coordinates on the three-dimensional structure of the brain MRI can be obtained. The theoretical cerebrovascular position coordinates are the theoretical positions of the brain blood vessels on the medical structure. The theoretical cerebrovascular position coordinates can then be used as a reference to verify the rationality of the position of the theoretical cerebrovascular position coordinates.

[0070] After obtaining the theoretical cerebrovascular position coordinates, the cerebrovascular position coordinate difference between the theoretical cerebrovascular position coordinates and the three-dimensional position coordinates can be determined to verify the position rationality of the cerebrovascular position coordinates according to the cerebrovascular position coordinate difference.

[0071] Exemplarily, the theoretical cerebral blood vessel position coordinates may be obtained from sample data of the patient with the same gender and similar age.

[0072] S320, when the cerebrovascular position coordinate difference is greater than or equal to the preset cerebrovascular position coordinate difference, the T2DM cognitive impairment detection result is determined by the cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics, and cerebral hemodynamic characteristics. When the cerebrovascular position coordinate difference is less than the preset cerebrovascular position coordinate difference, the T2DM cognitive impairment detection result is determined by the cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position, and ventricular region boundaries.

[0073] After obtaining the cerebrovascular position coordinate difference, when the cerebrovascular position coordinate difference is greater than or equal to the preset cerebrovascular position coordinate difference, it means that the cerebrovascular position coordinate difference is too large. At this time, the deviation between the detection result of the cerebrovascular position coordinate and the theoretical value is too large, indicating that the cerebrovascular position coordinate detection result is inaccurate. At this time, the cognitive impairment detection model can be used to determine the T2DM cognitive impairment detection result based only on the patient's brain structure characteristics, brain texture characteristics and cerebral hemodynamic characteristics, thereby ensuring the accuracy of the T2DM cognitive impairment detection result.

[0074] Exemplarily, the cerebral blood vessel position coordinate difference may be determined by the vector modulus corresponding to the cerebral blood vessel position coordinate difference.

[0075] After obtaining the cerebrovascular position coordinate difference, when the cerebrovascular position coordinate difference is less than the preset cerebrovascular position coordinate difference, through the cognitive impairment detection model, the detection result of the cerebrovascular position coordinate is not much different from the theoretical value, indicating that the cerebrovascular position coordinate detection result is relatively accurate. The T2DM cognitive impairment detection result can be determined based on the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position and ventricular regional boundaries to improve the accuracy of the T2DM cognitive impairment detection result.

[0076] The beneficial effect of the above-mentioned implementation method is that by determining the difference between the theoretical cerebrovascular position coordinates and the three-dimensional position coordinates, the position rationality of the cerebrovascular position coordinates can be verified according to the difference between the cerebrovascular position coordinates, and the T2DM cognitive impairment detection results can be determined based on the more accurate cerebrovascular position coordinate detection results to improve the accuracy of the T2DM cognitive impairment detection results.

[0077] The beneficial effect of the above-mentioned implementation method is that when the cerebrovascular position coordinate detection results are inaccurate, the T2DM cognitive impairment detection results are determined only based on the patient's brain structure characteristics, brain texture characteristics and cerebral hemodynamic characteristics, thereby ensuring the accuracy of the T2DM cognitive impairment detection results.

[0078] Figure 6 A schematic diagram of the flow of a fourth method for detecting cognitive impairment in T2DM based on image feature fusion provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the above method further includes S410 to S420, and S410 to S420 are described in detail below.

[0079] S410, obtaining multiple MRI tomographic images of the patient's structural MRI examination images and tomographic detection positions corresponding to the multiple MRI tomographic images, determining multiple target MRI tomographic images having similar coordinates of the tomographic detection positions and cerebral blood vessel positions in the multiple MRI tomographic images, and determining brain structural features and brain texture features of brain structural features corresponding to the multiple target MRI tomographic images.

[0080] In order to eliminate the interference of MRI tomographic images that are far away from the cerebral blood vessel position in multiple MRI tomographic images of the structural MRI examination image, multiple MRI tomographic images of the patient's structural MRI examination image and the tomographic detection positions corresponding to the multiple MRI tomographic images can be obtained, one MRI tomographic image corresponds to one tomographic detection position, and then the position corresponding to the MRI tomographic image and the cerebral blood vessel position can be verified according to the tomographic detection position.

[0081] When determining an MRI tomographic image that is close to the location of cerebral blood vessels, multiple target MRI tomographic images whose tomographic detection positions are close to the coordinates of the cerebral blood vessel locations can be determined in the multiple MRI tomographic images, and then the T2DM cognitive impairment detection results can be determined based on the multiple target MRI tomographic images.

[0082] Exemplarily, when determining multiple target MRI tomographic images whose tomographic detection positions and cerebral blood vessel position coordinates are similar among multiple MRI tomographic images, the multiple target MRI tomographic images can be determined based on the coordinates of the tomographic detection positions of the multiple MRI tomographic images and the coordinates of the cerebral blood vessel positions, and the difference between the coordinates of the tomographic detection positions of the multiple target MRI tomographic images and the coordinates of the cerebral blood vessel positions is within a preset distance difference range.

[0083] After obtaining multiple target MRI tomograms, the brain structure features and brain texture features of the brain structure features corresponding to the multiple target MRI tomograms can be determined, and then the T2DM cognitive impairment detection results can be determined based on the multiple target MRI tomograms.

[0084] S420. Determine the T2DM cognitive impairment detection result through the cognitive impairment detection model according to the brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebral blood vessel positions and ventricular area boundaries corresponding to multiple target MRI tomography images.

[0085] When determining the T2DM cognitive impairment detection results, the cognitive impairment detection model can be used to determine the T2DM cognitive impairment detection results based on the brain structure features, brain texture features, cerebral hemodynamic features, cerebral vascular positions and ventricular area boundaries corresponding to multiple target MRI tomography images, thereby achieving the determination of the T2DM cognitive impairment detection results based on multiple target MRI tomography images with similar coordinates of tomography detection positions and cerebral vascular positions in multiple MRI tomography images.

[0086] The beneficial effect of the above-mentioned implementation method is that the T2DM cognitive impairment detection results are determined based on multiple target MRI tomography images with similar coordinates of tomographic detection positions and cerebrovascular positions in multiple MRI tomography images, which can better reveal the correlation between brain structure and cerebrovascular position and improve the accuracy of T2DM cognitive impairment detection results.

[0087] In some implementations, the above method also includes: determining the first boundaries of the gray matter area, white matter area and ventricular area in the first target MRI tomography image, and when the first boundaries are all continuous boundaries, determining the T2DM cognitive impairment detection results according to the brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebral blood vessel positions and ventricular area boundaries corresponding to the first target MRI tomography image.

[0088] When determining the T2DM cognitive impairment detection result, the image quality of the target MRI tomographic image can be further detected to ensure the accuracy of the T2DM cognitive impairment detection result.

[0089] When detecting the image quality of the target MRI tomographic image, the first boundaries of the gray matter area, white matter area and ventricular area in the first target MRI tomographic image can be determined. When the first boundaries are all continuous boundaries, it means that the boundaries of the gray matter area, white matter area and ventricular area in the first target MRI tomographic image are complete and the image quality is high. Then, the T2DM cognitive impairment detection result can be determined according to the brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebral blood vessel position and ventricular area boundaries corresponding to the first target MRI tomographic image, so that the T2DM cognitive impairment detection result can be determined according to the gray matter area, white matter area and ventricular area in the high-quality first target MRI tomographic image, thereby improving the accuracy of the T2DM cognitive impairment detection result.

[0090] The beneficial effect of the above-mentioned implementation method is that it can screen out the first target MRI tomography image with complete boundaries and high image quality of gray matter areas, white matter areas and ventricular areas, and then determine the T2DM cognitive impairment detection results based on the gray matter areas, white matter areas and ventricular areas in the high-quality first target MRI tomography image, thereby improving the accuracy of the T2DM cognitive impairment detection results.

[0091] In some implementations, the above method also includes: determining the gray matter area and the white matter area in the first target MRI tomography image, when the area ratio of the white matter area to the gray matter area is greater than a preset area ratio, and when the first boundaries are all continuous boundaries, determining the T2DM cognitive impairment detection result according to the brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebral blood vessel position and ventricular area boundaries corresponding to the first target MRI tomography image.

[0092] When detecting the image quality of the target MRI tomographic image, the gray matter area and the white matter area in the first target MRI tomographic image can be further determined, and then the imaging position of the first target MRI tomographic image can be judged according to the gray matter area and the white matter area, thereby detecting the imaging position of the first target MRI tomographic image.

[0093] After obtaining the gray matter area and the white matter area, the area ratio of the white matter area to the gray matter area can be used to determine whether the detection position of the target MRI tomography image is suitable as a basis for determining the T2DM cognitive impairment detection result. When the area ratio of the white matter area to the gray matter area is greater than the preset area ratio, it means that the imaging position of the first target MRI tomography image is located at the top or bottom of the brain, thereby capturing more white matter areas, and then being able to detect the anterior cerebral artery (ACA) and the posterior cerebral artery (PCA) based on the target MRI tomography image at the top or bottom of the brain, thereby improving the accuracy of the T2DM cognitive impairment detection result determined comprehensively based on brain blood vessels and brain structures.

[0094] When the area ratio of the white matter region to the gray matter region is greater than the preset area ratio, and when the first boundaries are all continuous boundaries, the T2DM cognitive impairment detection results can be determined based on the brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebral blood vessel positions and ventricular area boundaries corresponding to the first target MRI tomography image, thereby improving the accuracy of the T2DM cognitive impairment detection results determined comprehensively based on brain blood vessels, brain structure, brain texture characteristics, etc.

[0095] The beneficial effect of the above implementation method is that the imaging position of the first target MRI tomography image is judged according to the gray matter area and the white matter area, and then the accuracy of the T2DM cognitive impairment detection result can be comprehensively determined according to the brain blood vessels, brain structure, brain texture features, etc.

[0096] An embodiment of the present application also provides a T2DM cognitive impairment detection system based on image feature fusion, comprising a unit for executing any of the methods described above.

[0097] Figure 7A logical structure diagram of a T2DM cognitive impairment detection system based on image feature fusion provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12 and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12 and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0098] An embodiment of the present application also provides a T2DM cognitive impairment detection system based on image feature fusion, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0099] Figure 8 A schematic diagram of the physical structure of a T2DM cognitive impairment detection system based on image feature fusion provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the system 2 of this embodiment includes: at least one processor 20 ( Figure 8 Only one processor 20 is shown in the figure), a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20. When the processor 20 executes the computer program 22, the steps in any of the above-mentioned method embodiments are implemented. The beneficial effects of the embodiments of the present application have been described in the above-mentioned methods and will not be repeated here.

[0100] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0101] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0102] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0103] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0105] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0106] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0107] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0108] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0109] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting cognitive impairment in T2DM based on image feature fusion, characterized in that: The method comprises: Acquire the patient's structural MRI examination images, CT examination images and TCD examination images; determine the patient's brain structural features according to the structural MRI examination images and CT examination images, determine the patient's brain texture features according to the structural MRI examination images and CT examination images respectively through the gray-level co-occurrence matrix, and determine the patient's cerebral hemodynamic characteristics according to the TCD examination images; wherein the brain structural features include the volume features of gray matter and white matter, the cortical thickness features and the ventricle size features, and the cerebral hemodynamic features include the blood flow velocity features and the blood flow direction features; Through the cognitive impairment detection model, the T2DM cognitive impairment detection results are determined according to the patient's brain structure characteristics, brain texture characteristics and cerebral hemodynamic characteristics.

2. The method according to claim 1, characterized in that The brain structure characteristics of the patient are determined according to the structural MRI examination images and the CT examination images, and the brain texture characteristics of the patient are determined according to the structural MRI examination images and the CT examination images through the gray level co-occurrence matrix, including: The gray matter area, white matter area and ventricular area of ​​the patient's brain structure are determined based on the structural MRI examination images and CT examination images; the volume characteristics, cortical thickness characteristics and ventricular size characteristics of the patient's brain structure are determined based on the gray matter area, white matter area and ventricular area; the texture characteristics of the gray matter area, white matter area and ventricular area are determined respectively through the gray-level co-occurrence matrix as the patient's brain texture characteristics.

3. The method according to claim 2, characterized in that The method further comprises: Determine the patient's cerebrovascular position based on the TCD examination image, and determine the patient's ventricular region boundary based on the structural MRI examination image and the CT examination image; wherein the cerebrovascular position is the position of the cerebrovascular relative to the ventricular region; Through the cognitive impairment detection model, the T2DM cognitive impairment detection results are determined according to the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position and ventricular regional boundaries; among them, the cerebrovascular position and ventricular regional boundaries are used to determine the cerebrovascular position deviation characteristics caused by brain atrophy.

4. The method according to claim 3, characterized in that Determine the location of the patient's cerebrovascular vessels based on TCD examination images, including: The brain MRI three-dimensional structure is reconstructed through structural MRI examination images, the brain MRI three-dimensional structure and TCD examination images are aligned, and the three-dimensional position coordinates of the cerebral blood vessels in the TCD examination image on the brain MRI three-dimensional structure are determined as the patient's cerebral blood vessel position.

5. The method according to claim 4, characterized in that The method further comprises: Obtaining theoretical cerebrovascular position coordinates on the three-dimensional structure of brain MRI, and determining the cerebrovascular position coordinate difference between the theoretical cerebrovascular position coordinates and the three-dimensional position coordinates; When the cerebrovascular position coordinate difference is greater than or equal to the preset cerebrovascular position coordinate difference, the T2DM cognitive impairment detection result is determined through the cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics, and cerebral hemodynamic characteristics; when the cerebrovascular position coordinate difference is less than the preset cerebrovascular position coordinate difference, the T2DM cognitive impairment detection result is determined through the cognitive impairment detection model according to the patient's brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebrovascular position, and ventricular area boundaries.

6. The method according to claim 5, characterized in that The method further comprises: Acquire multiple MRI tomographic images of the patient's structural MRI examination image and tomographic detection positions corresponding to the multiple MRI tomographic images, determine multiple target MRI tomographic images having similar coordinates of the tomographic detection positions and cerebral blood vessel positions in the multiple MRI tomographic images, and determine brain structural features and brain texture features of brain structural features corresponding to the multiple target MRI tomographic images; Through the cognitive impairment detection model, the T2DM cognitive impairment detection results are determined based on the brain structure characteristics, brain texture characteristics, cerebral hemodynamic characteristics, cerebral vascular locations and ventricular area boundaries corresponding to multiple target MRI tomography images.

7. A T2DM cognitive impairment detection system based on image feature fusion, characterized in that: Comprising means for performing the method according to any one of claims 1 to 6.

8. A T2DM cognitive impairment detection system based on image feature fusion, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images