Cognitive level evaluation method based on images

Abstract

The invention provides an image-based cognitive level assessment method, which belongs to the technical field of cognitive level detection, and comprises the following steps of: S1, acquiring brain image data of a patient through MRI (Magnetic Resonance Imaging); s2, measuring an included angle of a fourth ventricle by using an image processing software tool; s3, based on the fourth ventricular included angle value measured in the step S2, mapping the fourth ventricular included angle value to a corresponding cognitive level score through a score calculation formula; and S4, judging the cognitive function according to the cognitive level score. According to the cognitive level evaluation method based on the images, complex post-processing steps are avoided, the included angle is directly measured and mapped to the preset scoring system, and the method aims to simplify iconography evaluation, so that clinicians can quickly and objectively evaluate the cognitive state, and the cognitive state can be effectively supplemented or replaced by a traditional cognitive scale.

Description

Technical Field

[0001] The present invention relates to the technical field of cognitive level detection, and in particular to an image-based cognitive level assessment method. Background Art

[0002] In clinical practice, the assessment of cognitive level mainly relies on cognitive function scales, such as the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA). These cognitive function scales assess cognitive function through the patient's subjective answers and the doctor's scores. Although they are easy to use, their results are often affected by subjective factors, which may lead to insufficient accuracy of the assessment results, especially in the screening of early cognitive decline, the sensitivity and specificity of the scales are low.

[0003] In recent years, studies have confirmed the potential relationship between changes in ventricular morphology and cognitive function. Changes in ventricular morphology, especially ventricular dilation or atrophy, may be associated with a decline in cognitive function. In addition, changes in complex brain network connectivity and fiber bundles have gradually become an important area of ​​research in cognitive impairment. Tracking and quantifying brain fiber bundles through techniques such as diffusion tensor imaging (DTI) can reveal changes in connectivity between different brain regions, which are crucial for understanding the decline of cognitive function. However, these methods usually involve a large number of post-processing steps and complex image analysis algorithms, which not only require a high level of expertise, but also greatly increase the workload and time cost in clinical applications. Therefore, these image-based assessment methods are difficult to be widely used in clinical practice.

[0004] In order to solve this problem, it is urgent to develop a method that can quickly and accurately assess an individual's cognitive level. Summary of the invention

[0005] The purpose of the present invention is to provide an image-based cognitive level assessment method that avoids complex post-processing steps. By directly measuring the angle and mapping it to a preset scoring system, it aims to simplify imaging assessment so that clinicians can quickly and objectively assess cognitive status as an effective supplement or substitute for traditional cognitive scales.

[0006] To achieve the above object, the present invention provides an image-based cognitive level assessment method, comprising the following steps: Step S1, obtaining brain imaging data of a patient through MRI; Step S2, using an image processing software tool to measure the angle of the fourth ventricle; Step S3, based on the fourth ventricle angle value measured in step S2, mapping the fourth ventricle angle value to a corresponding cognitive level score through a scoring calculation formula; Step S4: determining cognitive function according to the cognitive level score.

[0007] Preferably, in step S1, the data type of the brain image data is a 3D-T1 sagittal sequence image.

[0008] Preferably, in step S2, the angle of the fourth ventricle is measured using an imaging software tool, and the specific operation is: S21, loading brain image data into image processing software; S22, manually select the image slice where the long axis and short axis of the fourth ventricle are located; S23. Use image processing software to calibrate the major axis and minor axis, and automatically calculate the angle between the major axis and minor axis.

[0009] Preferably, in step S3, the score calculation formula is as follows: ; in, is the standardized cognitive score, with a value range of [0, 1]; is the angle of the fourth ventricle, and its value range is [10, 90].

[0010] Therefore, the present invention adopts the above-mentioned image-based cognitive level assessment method, and the beneficial technical effects are as follows: (1) Existing imaging assessment methods rely on complex post-processing steps, such as brain network analysis, fiber tract tracing, and brain volume measurement, which involve high-level expertise and complex image analysis algorithms and require a lot of time to process. The present invention directly generates a standardized cognitive score by measuring the angle of the fourth ventricle, which reduces the time and workload of clinicians in image data processing and is simple and easy to operate; (2) The present invention does not require complex image segmentation or brain region division, and can quickly measure the angle of the fourth ventricle and generate a cognitive score using conventional image processing software. This allows clinicians to complete the assessment in a shorter time, especially in the screening of early cognitive dysfunction, which can improve screening efficiency; (3) The present invention adopts a standardized scoring system from 0 to 1, which is convenient for use in different clinical scenarios or automated systems. By mapping the angle value to a scoring range of 0 to 1, it not only improves the intuitiveness of the evaluation, but also provides a convenient data format for subsequent machine learning, statistical model and other analyses; (4) The scoring system of the present invention was validated based on two datasets of different sizes, 200 and 2000 people, respectively, to verify the applicability of the angle range. The scoring system can be applied to different types of patient groups and has flexible scalability to adapt to more clinical data and application scenarios in the future; (5) The present invention uses image data to directly generate scores, avoiding the subjectivity of traditional cognitive function scales, and the evaluation results are more objective. In addition, the scoring criteria are clear and easy to repeat, with high reliability and consistency, and are not easily interfered by human factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A framework diagram of an image-based cognitive level assessment method of the present invention; Figure 2 is a schematic diagram of angle measurement; Figure 2 (A) is a midsagittal T1-weighted MRI image of a healthy control; Figure 2 (B) is the same MR image with FVRA depicted and measured; Figure 2 (C) is a midsagittal T1-weighted MRI image of an MCI patient; Figure 2 (D) is the same MR image depicting and measuring FVRA; Figure 3 It is the scatter plot of the correlation between FVRA Score and MMSE Score; Figure 4 Schematic diagram of ROC. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical scheme and advantages disclosed in the embodiments of the present invention clearer, the embodiments of the present invention are further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the embodiments of the present invention and are not intended to limit the embodiments of the present invention. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions.

[0013] It should be noted that the terms "include", "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or devices.

[0014] Like reference numerals and letters denote similar items in the following drawings, and thus, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0015] In the description of the present invention, it should be noted that the terms "upper", "lower", "inside", "outside", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings, or are directions or positional relationships in which the product of the invention is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation on the present invention.

[0016] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "setting", "installation" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0017] Embodiment 1 like Figure 1 As shown, the present invention provides an image-based cognitive level assessment method, comprising the following steps: Step S1, obtaining brain imaging data of a patient through magnetic resonance imaging (MRI); The data type of brain imaging data is 3D-T1 sagittal sequence images.

[0018] Step S2: using image processing software (such as ITK-SNAP or ImageJ, etc.) to measure the angle of the fourth ventricle, specifically including the following steps: Step 1: Load the brain image data into the image processing software and manually select the image slice where the long axis and short axis of the fourth ventricle are located; Step 2: Use image processing software to calibrate the major axis and minor axis, and automatically calculate the angle between the major axis and minor axis.

[0019] Step S3, based on the fourth ventricle angle value measured in step S2, mapping the fourth ventricle angle value to a corresponding cognitive level score through a scoring calculation formula; The scoring formula is as follows: ; in, is the standardized cognitive score, with a value range of [0, 1]; is the angle of the fourth ventricle, and its value range is [10, 90].

[0020] The angle range selection of the present invention is based on the actual results of clinical data, and the angle range is verified by two data sets, wherein data set one contains 200 people and data set two contains 2000 people, and the angle range of the two data sets is both between 10° and 90°.

[0021] In order to cope with the possible boundary conditions of different data sets, elastic boundaries are introduced to allow angles less than 10° or greater than 90°. For example: When the angle was less than 10°, it was mapped to 1 point, indicating optimal cognitive function.

[0022] When the angle was greater than 90°, it was mapped to a score of 0, indicating the worst cognitive function.

[0023] The introduction of elastic boundaries can ensure that the scoring system remains effective in extreme cases and that situations that cannot be evaluated will not occur.

[0024] Step S4: determining cognitive function according to the cognitive level score.

[0025] The present invention is further described below by means of a specific example.

[0026] MRI data of the subjects were collected on a Philips 3.0T MRI scanner (Ingenia, Philips Healthcare, Best, The Netherlands) using a 32-channel head coil. Figure 2 ), the scores were converted and correlated with the MMSE scores.

[0027] The experimental results show that the FVRA score (the present invention) is significantly positively correlated with the MMSE score, as follows: Correlation coefficient r =0.6894, statistic t =7.9564, p The value is 3.5133×10 −12 (p<0.05), indicating that there is a significant positive correlation between FVRAscore and MMSE ( Figure 3 ), as the FVRA score increases, the MMSE score also increases. This shows that there is consistency between the FVRA score and MMSE in assessing cognitive level.

[0028] In order to further evaluate the diagnostic ability of FVRA score, FVRA score was compared with other indicators (such as gray matter volume, white matter volume, and cortical thickness). The results of ROC (receiver operating characteristic) curve analysis showed that ( Figure 4): FVRA score is superior to traditional imaging indicators such as gray matter volume, white matter volume and cortical thickness in diagnosing cognitive impairment.

[0029] ROC analysis showed that the FVRA score had higher diagnostic accuracy and sensitivity in distinguishing patients with normal cognitive function from those with cognitive decline, which further supports the validity of the FVRA score as a simple imaging-based cognitive assessment tool.

[0030] Therefore, the present invention adopts the above-mentioned image-based cognitive level assessment method, avoiding complex post-processing steps, and directly measuring the angle and mapping it to a preset scoring system, aiming to simplify imaging assessment, so that clinicians can quickly and objectively assess cognitive status, as an effective supplement or substitute for traditional cognitive scales.

[0031] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for assessing cognitive level based on images, characterized in that: The following steps are involved: Step S1, obtaining brain imaging data of a patient through MRI; Step S2, using an image processing software tool to measure the angle of the fourth ventricle; Step S3, based on the fourth ventricle angle value measured in step S2, mapping the fourth ventricle angle value to a corresponding cognitive level score through a scoring calculation formula; Step S4: determining cognitive function according to the cognitive level score.

2. The method for evaluating cognitive level based on images according to claim 1, characterized in that: In step S1, the data type of the brain image data is 3D-T1 sagittal sequence images.

3. The method for evaluating cognitive level based on images according to claim 1, characterized in that: In step S2, the angle of the fourth ventricle is measured using an imaging software tool, and the specific operation is as follows: S21, loading brain image data into image processing software; S22, manually select the image slice where the long axis and short axis of the fourth ventricle are located; S23. Use image processing software to calibrate the major axis and minor axis, and automatically calculate the angle between the major axis and minor axis.

4. The method for evaluating cognitive level based on images according to claim 1, characterized in that: In step S3, the scoring calculation formula is as follows: ； in, is the standardized cognitive score, with a value range of [0, 1]; is the angle of the fourth ventricle, and its value range is [10, 90].

Images