Mental disease screening system, chip, device and computer readable storage medium

Abstract

The invention relates to the technical field of medical detection, and provides a mental disease screening system, a chip, a device and a computer readable storage medium. The system for screening mental diseases comprises the following modules: an image acquisition module, an ROI detection module, an ROI extraction module, a cutting module, a standardization module, an erythema segmentation module, a statistical feature extraction module and a report generation module. The system provided by the invention can be used for detecting or diagnosing whether a patient suffers from depression or not. The system for screening mental diseases is simple in use method, high in accuracy and capable of conveniently and quickly completing the diagnosis process.

Description

Technical Field

[0001] The present invention relates to the field of medical detection technology. Specifically, the present invention provides a system, chip, device and computer-readable storage medium for screening mental illness. Background Art

[0002] The diagnosis of depression usually relies on the assessment of clinical symptoms and needs to be conducted in a hospital, a relatively complex and subjective process.

[0003] Wang, J et al. published an article titled Identification of adolescent patients with depression via assessment of the niacin skin flushing response. Journal of Affective Disorders, which disclosed the specific manifestations of niacin skin flushing response (NSFR) in depression, specifically: there was a significant difference between the NSFR of adolescent patients with depression and the healthy control group, and NSFR had the potential to be used as a biomarker for depression. However, the article did not disclose how NSFR was used to systematically diagnose depression, and it could not be directly applied to the field of medical testing technology.

[0004] The existing technology lacks a direct, objective, rapid and accurate screening system for diagnosing depression. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention provides a system, chip, device and computer-readable storage medium for screening mental illness.

[0006] The specific technical solutions of the present invention are as follows:

[0007] In a first aspect, the present invention provides a system for screening mental illness, comprising the following modules:

[0008] (1) Image acquisition module: perform a niacin flushing reaction test on the subject's skin, take photos and collect images;

[0009] (2) ROI detection module: processing the image obtained by module (1) to obtain the rectangular coordinates of the inner border of the niacin patch;

[0010] (3) ROI extraction module: using the rectangular coordinates obtained by module (2) to extract, obtain the content in the inner border of the niacin patch and align it to obtain a standard rectangle;

[0011] (4) Cutting module: Cut the standard rectangle obtained in module (3) with the flushing reaction erythema as the center to obtain a segmentation map;

[0012] (5) Standardization module: standardize the segmentation map obtained by module (4) to obtain a standard segmentation map;

[0013] (6) Erythema segmentation module: the standard segmentation map obtained by module (5) is screened to obtain a feature map;

[0014] (7) Statistical feature extraction module: extract the area of ​​the erythema region in the feature map, sum it up, and obtain the detection value;

[0015] (8) Generate report module: output erythema area trend graph and detection value;

[0016] Specifically, the mental illness is depression;

[0017] Specifically, the method of photographing and collecting is:

[0018] ① Collect the reference image of the inner side of the forearm of the subject when niacin is not present, and this moment is recorded as t=0;

[0019] ② After the subject has used the niacin patch for 1 minute, the patch is removed and the skin reaction image is captured every 10 seconds for 10 minutes. The image at time t is recorded as x t ;

[0020] Specifically, the number of the niacin patches is greater than or equal to 1, and is coated with a 60 mM aqueous solution of methyl nicotinate.

[0021] Specifically, the skin niacin flushing reaction is: after human skin comes into contact with niacin, the skin at the contact point will produce a flushing reaction erythema;

[0022] Specifically, the processing method in the ROI detection module is:

[0023] c. Read all x t Grayscale image, denoted by x t,gray , remove x t,gray The redundant boundary information in the image is removed to obtain the processed grayscale image;

[0024] d. Obtain the maximum border of the grayscale image processed in step a, which corresponds to the inner border of the niacin patch and is fitted into a rectangle to obtain the coordinates of the rectangle vertices;

[0025] Specifically, the removal of x in step a t,gray The redundant boundary information in x is: Use the GaussianBlur function in the cv2 module in Python to t,gray Apply Gaussian blur;

[0026] Specifically, the step b of obtaining the maximum border of the grayscale image processed in step a is as follows: finding the maximum border through the Canny, FindContours and ContourArea functions in the cv2 module in Python;

[0027] Specifically, the fitting into a rectangle in step b is: using the MinAreaRect and BoxPoints functions in the cv2 module in Python to fit the inner border of the niacin patch into a rectangle;

[0028] Specifically, if the area of ​​the maximum border in step b is greater than the preset value 300000, then repeat steps a and b;

[0029] Specifically, the extraction method in the ROI extraction module is: read x t The color map of t,RGB , using the coordinates of the rectangle vertices obtained in step b and the GetPerspectiveTransform and GetPerspective functions in the cv2 module in Python, from x t,RGB Extract the content in the inner border and align it to a standard rectangle;

[0030] Specifically, the cutting method in the cutting module is: taking each flushing reaction erythema as the center, cutting the standard rectangle into a size of 1.8×2.2 cm 2 A fragment of t,i ;

[0031] Specifically, the method of standardization processing in the standardization module is: t,i Extract the mean of the surrounding non-erythema pixels, denoted as mean t,i , and mean t,i To uniformly adjust the image brightness, a standardized image is obtained. The standardized image obtained at time t is denoted as x t,i,norm , x t,i,norm =x t,i -mean t,i +150;

[0032] Specifically, the screening method described in the erythema segmentation module is:

[0033] S1, x t,i,norm The pixels in are converted into two states: black and white, generating a segmentation map (1);

[0034] S2, removing small noise from the segmentation map (1) obtained in step S1 to obtain a segmentation map (2);

[0035] S3, removing small holes from the segmentation map (2) obtained in step S2 to obtain a segmentation map (3);

[0036] S4, filtering out small components from the segmentation graph (3) obtained in step S3, obtaining its connected components, and obtaining a feature graph;

[0037] Specifically, in step S1, x t,i,norm The method of converting the pixel points in x into two states is as follows: t,i,norm With x 0,i,norm Difference to get diff t,i , calculate the diff t,i The standard deviation of t,i , and use this as the threshold to binarize diff t,i ;

[0038] Specifically, the x 0,i,norm is the standardized image at time 0;

[0039] Specifically, the method for removing small noise in step S2 is: using the MedianBluer function in the cv2 module in Python to perform median filtering on the segmentation map (1) obtained in step S1;

[0040] Specifically, the method for removing small holes in step S3 is: using the MorphologyEx function in the cv2 module in Python to perform morphological expansion on the segmentation map (2) obtained in step S2;

[0041] Specifically, the method for filtering out small components in step S4 is: using the ConnectedComponentsWithStats function in the cv2 module in Python on the segmentation map (3);

[0042] Specifically, the extracting the erythema area in the feature map in the statistical feature extraction module is: extracting the erythema area of ​​the feature map at each moment;

[0043] Specifically, the summation in the statistical feature extraction module is: summing up the erythema area of ​​the feature graph at each moment to obtain the detection value;

[0044] Specifically, a test value ≥ 4000 indicates a tendency toward depression;

[0045] The test value <4000 indicates mental health.

[0046] In a second aspect, the present invention further provides a chip, including a processor and a memory.

[0047] Specifically, the memory stores machine executable instructions of the above system;

[0048] Specifically, the processor may execute machine executable instructions in the memory to run the above system.

[0049] In a third aspect, the present invention also provides a device for screening mental illness, characterized in that it comprises a display, a controller and the above-mentioned chip;

[0050] Specifically, the display is used to: display operation status and images;

[0051] Specifically, the controller is a device that controls the operation of the device.

[0052] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a program for executing the above system.

[0053] The beneficial effects of the present invention are:

[0054] (1) The present invention combines image processing technology and statistical methods to accurately analyze the degree of skin response to niacin;

[0055] (2) By performing niacin tests on patients and taking images of their skin reactions, the algorithm converts the image data into quantifiable biomarker indicators to effectively diagnose depression;

[0056] (3) The present invention is characterized by its high objectivity and accuracy. Compared with traditional symptom assessment methods, it provides a new technical means for the diagnosis of depression. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The present invention will be further described in detail below in conjunction with the accompanying drawings and preferred embodiments, but those skilled in the art will appreciate that these drawings are drawn only for the purpose of explaining the preferred embodiments and therefore should not be used as a limitation on the scope of the present invention. In addition, unless otherwise specified, the drawings are only schematically representing the composition or structure of the described objects and may contain exaggerated displays, and the drawings are not necessarily drawn to scale.

[0058] Figure 1 This image was taken 1 minute after the niacin flush reaction;

[0059] Figure 2 From top to bottom: a relatively obvious niacin flushing reaction image, and a characteristic diagram of a relatively obvious niacin flushing reaction image processed by an embodiment;

[0060] Figure 3 From top to bottom: an image of a milder niacin flushing reaction, and a characteristic diagram of an image of a milder niacin flushing reaction processed by an embodiment. DETAILED DESCRIPTION

[0061] The following non-limiting examples can enable those skilled in the art to more fully understand the present invention, but do not limit the present invention in any way. The following content is merely an exemplary description of the scope of the present invention, and those skilled in the art can make various changes and modifications to the present invention based on the disclosed content, which should also fall within the scope of the present invention.

[0062] The technical details of the present invention are described in detail by the following examples. It should be noted that the examples are only used to further illustrate the technical features of the present invention, rather than to limit the protection scope of the present invention.

[0063] Unless otherwise specified, all commodities or reagents in the present invention were purchased through market channels.

[0064] The present invention is further described in detail below with reference to specific embodiments, but the embodiments of the present invention are not limited thereto.

[0065] An embodiment of the present invention provides a system for screening mental illness, wherein the mental illness is depression, and the system includes the following modules:

[0066] (1) Image acquisition module: Perform a niacin flushing reaction test on the subject's skin, take photos and obtain images.

[0067] First, a reference image of the inner forearm of the subject without niacin is collected, and this time is recorded as t=0; after the subject uses a 60mM niacin patch on the inner forearm for 1 minute, the niacin patch is removed and images of the skin reaction are captured every 10 seconds for 10 minutes. The image at time t is recorded as x t .

[0068] In practical applications, the 0-second acquisition of the present invention corresponds to the reference image when no niacin is added. If the reference image is set to the first image taken 1 minute after the reaction, this is unreasonable for a faster reaction, because erythema may already exist at this time. Figure 1 shown.

[0069] (2) ROI detection module: Process the image obtained by module (1) to obtain the rectangular coordinates of the inner border of the niacin patch.

[0070] In practical applications, first, for the image at time t, read its grayscale image and record it as x t,gray , use the GaussianBlur function in the cv2 module in Python to perform Gaussian blur on it to obtain the processed grayscale image. The purpose of this is to remove redundant boundary information.

[0071] The maximum border in the processed grayscale image is found through the Canny, findContours and contourArea functions in the cv2 module in Python, which corresponds to the inner border of the niacin patch.

[0072] If the area of ​​the border is larger than the preset value (300000) during the processing, the Gaussian blur and the operation of finding the maximum border are repeated. The purpose of this is to ensure that the niacin patch border found corresponds to the inner border of the niacin patch rather than the outer border of the niacin patch.

[0073] The minAreaRect and boxPoints functions in the cv2 module in Python were used to fit a rectangle to the inner border of the niacin patch and obtain the coordinates of the four vertices of the rectangle.

[0074] (3) ROI extraction module: Use the rectangular coordinates obtained by module (2) to extract the content in the inner border of the niacin patch and align it to obtain a standard rectangle.

[0075] In practical applications, the first color image to be read is denoted by x t,RGB , using the obtained rectangle vertex coordinates and the GetPerspectiveTransform and GetPerspective functions in the cv2 module in Python, from x t,RGB Extract the content within the inner border and align it to a standard rectangle.

[0076] (4) Cutting module: With the flushing reaction erythema as the center, the standard rectangle obtained by module (3) is cut to obtain a segmentation map.

[0077] In practical applications, when cutting, the standard rectangle is cut into a segment of 1.8×2.2 cm2 with the flushing reaction erythema as the center, recorded as x t,i .

[0078] (5) Standardization module: standardize the segmentation map to obtain a standard segmentation map.

[0079] In practical applications, t,i Extract the mean of the surrounding non-erythema pixels, denoted as mean t,i , and adjust the image brightness uniformly based on it to obtain a standardized image. The standardized image obtained at time t is recorded as x t,i,norm ,x t,i,norm =x t,i -mean t,i +150.

[0080] (6) Erythema segmentation module: The standard segmentation map is screened out to obtain a feature map.

[0081] In practical applications, for the normalized image x at time t≠0 t,i,norm , its erythema segmentation includes the following steps. First, x t,i,norm With x 0,i,norm Difference to get diff t,i , calculate the diff t,i The standard deviation of t,i , and use this as the threshold to binarize diff t,i The purpose of this is to convert x t,i,norm The pixels in the image are converted into two states: black and white, making our segmentation algorithm more robust to uncontrollable factors such as ambient lighting changes. In this way, the segmentation map (1) is obtained.

[0082] Use the medianBluer function in the cv2 module in Python to perform median filtering on the segmentation map (1). The purpose of this is to remove small noises to make the result more accurate. In this way, the segmentation map (2) is obtained.

[0083] Use the morphologyEx function in the cv2 module in Python to perform morphological dilation on the segmentation map (2). The purpose of this is to remove small holes in the segmentation map to make the result more accurate. In this way, the segmentation map (3) is obtained.

[0084] Finally, the connectedComponentsWithStats function in the cv2 module in Python is used to obtain the connected components in the segmentation map (3) and filter out small components to make the result more reliable. In this way, a feature map is obtained.

[0085] The ROI detection module, ROI extraction module, cutting module, standardization module and erythema segmentation module of the present invention are used for processing Figure 2 The more obvious niacin flush reaction image, Figure 3 The milder niacin flush reaction image is shown in the image of the niacin flush reaction. Figure 2 , Figure 3 .

[0086] like Figure 2 As the flushing reaction erythema becomes lighter and more irregular, the characteristic graph processed by the technical solution of the present invention still appears complete and connected.

[0087] Figure 3 The skin image is a relatively mild niacin flush reaction image, and the technical solution of the present invention can still extract a clear and complete feature map.

[0088] The present invention reduces the influence of uncontrollable factors such as ambient light changes, removes small noises and small holes, and screens out small components, making the processing results more reliable.

[0089] The mental illness screening system of the present invention can accurately analyze the degree of skin response to niacin without missing small differences and with small errors; it can convert image data into quantifiable biomarker indicators to effectively diagnose depression with high objectivity and accuracy.

[0090] Statistical feature extraction module: extract the area of ​​erythema in the feature map, sum it up, and get the detection value.

[0091] Generate report module: Based on the experimental data of the preliminary experiment, a test value ≥ 4000 indicates a tendency to depression, and a test value < 4000 indicates mental health.

[0092] Based on the same inventive concept, an embodiment of the present invention also provides a chip for a system based on mental illness screening, including a processor and a memory.

[0093] The memory stores machine executable instructions for the following modules:

[0094] (1) Image acquisition module: perform a niacin flushing reaction test on the subject's skin, take photos and collect images;

[0095] (2) ROI detection module: processing the image obtained by module (1) to obtain the rectangular coordinates of the inner border of the niacin patch;

[0096] (3) ROI extraction module: using the rectangular coordinates obtained by module (2) to extract, obtain the content in the inner border of the niacin patch and align it to obtain a standard rectangle;

[0097] (4) Cutting module: Cut the standard rectangle obtained in module (3) with the flushing reaction erythema as the center to obtain a segmentation map;

[0098] (5) Standardization module: standardize the segmentation map obtained by module (4) to obtain a standard segmentation map;

[0099] (6) Erythema segmentation module: the standard segmentation map obtained by module (5) is screened to obtain a feature map;

[0100] (7) Statistical feature extraction module: extract the area of ​​the erythema region in the feature map, sum it up, and obtain the detection value;

[0101] (8) Generate report module: output erythema area trend chart and detection value.

[0102] The processor executes the machine executable instructions of the above modules in the memory.

[0103] The memory may include a volatile memory, such as a random access memory, or may include a non-volatile memory.

[0104] In some specific embodiments, the present invention selects non-volatile memory.

[0105] The processor may be a general-purpose processor or a special-purpose processor, or may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0106] In some specific embodiments, the present invention selects a general purpose processor.

[0107] Based on the same inventive concept, an embodiment of the present invention also provides a device for screening mental illness, comprising a display, a controller and a chip of the above-mentioned system based on screening mental illness.

[0108] Among them, the display is used to display the operating status and the captured images and processed images; the controller is used to control the operation of the device.

[0109] Based on the same inventive concept, the present invention also provides a computer-readable storage medium in which a computer program is stored, and when the computer program is executed by a processor, the method steps described in any one of the above-mentioned systems based on mental illness screening can be implemented.

[0110] The computer-readable storage medium may be a non-volatile memory, such as at least one disk storage, or at least one storage device located away from the aforementioned processor. The processor may be a general-purpose processor, a dedicated processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc.

[0111] In some specific embodiments, the present invention selects a non-volatile memory as the memory and a general-purpose processor as the processor.

[0112] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art can understand and implement other changes to the disclosed embodiments by viewing the drawings and the disclosed content. The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, without departing from the concept of the present invention, several simple deductions or substitutions can be made, which should all be deemed to fall within the scope of protection of the present invention.

Claims

1. A system for screening mental illness, characterized in that: Includes the following modules: (1) Image acquisition module: perform a niacin flushing reaction test on the subject's skin, take photos and collect images; (2) ROI detection module: processing the image obtained by module (1) to obtain the rectangular coordinates of the inner border of the niacin patch; (3) ROI extraction module: using the rectangular coordinates obtained by module (2) to extract, obtain the content in the inner border of the niacin patch and align it to obtain a standard rectangle; (4) Cutting module: Cut the standard rectangle obtained in module (3) with the flushing reaction erythema as the center to obtain a segmentation map; (5) Standardization module: standardize the segmentation map obtained by module (4) to obtain a standard segmentation map; (6) Erythema segmentation module: the standard segmentation map obtained by module (5) is screened to obtain a feature map; (7) Statistical feature extraction module: extract the area of ​​the erythema region in the feature map, sum it up, and obtain the detection value; (8) Generate report module: output erythema area trend chart and detection value.

2. The system according to claim 1, characterized in that The mental illness is depression.

3. The system according to claim 1, characterized in that The method of photographing and collecting is: ① Collect the reference image of the inner side of the forearm of the subject when niacin is not present, and this moment is recorded as t=0; ② After the subject has used the niacin patch for 1 minute, the patch is removed and the skin reaction image is captured every 10 seconds for 10 minutes. The image at time t is recorded as x t .

4. The system according to claim 3, characterized in that The number of the nicotinic acid patches is greater than or equal to 1, and is coated with a 60 mM aqueous solution of methyl nicotinate.

5. The system according to claim 1, characterized in that The skin niacin flushing reaction is: after human skin comes into contact with niacin, the skin at the contact point will produce flushing reaction erythema.

6. The system according to claim 3, characterized in that The processing method described in the ROI detection module is: a. Read all x t Grayscale image, denoted by x t,gray , remove x t,gray The redundant boundary information in the image is removed to obtain the processed grayscale image; b. Obtain the maximum border of the grayscale image processed in step a, which corresponds to the inner border of the niacin patch and is fitted into a rectangle to obtain the coordinates of the rectangle vertices.

7. The system according to claim 6, characterized in that Removal of x as described in step a t,gray The redundant boundary information in x is: Use the GaussianBlur function in the cv2 module in Python to t,gray Apply Gaussian blur; The maximum border of the grayscale image processed in step a is obtained in step b by using the Canny, FindContours and ContourArea functions in the cv2 module in Python to find the maximum border; The step b of fitting into a rectangle is: using the MinAreaRect and BoxPoints functions in the cv2 module in Python to fit the inner border of the niacin patch into a rectangle.

8. The system according to claim 7, characterized in that If the area of ​​the maximum border in step b is greater than the preset value 300000, then steps a and b are repeated.

9. The system according to claim 8, characterized in that The extraction method described in the ROI extraction module is: read x t The color map of t,RGB , using the coordinates of the rectangle vertices obtained in step b and the GetPerspectiveTransform and GetPerspective functions in the cv2 module in Python, from x t,RGB Extract the content within the inner border and align it to a standard rectangle.

10. The system according to claim 9, characterized in that The cutting method described in the cutting module is: take the flushing reaction erythema as the center, cut out a standard rectangle with a size of 1.8×2.2cm 2 A fragment of t,i .

11. The system according to claim 10, characterized in that The method of standardization processing in the standardization module is: t,i Extract the mean of the surrounding non-erythema pixels, denoted as mean t,i , and mean t,i To uniformly adjust the image brightness, a standardized image is obtained. The standardized image obtained at time t is denoted as x t,i,norm , x t,i,norm =x t,i -mean t,i +150.

12. The system according to claim 11, characterized in that The screening method described in the erythema segmentation module is: S1, x t,i,norm The pixels in are converted into two states: black and white, generating a segmentation map (1); S2, removing small noise from the segmentation map (1) obtained in step S1 to obtain a segmentation map (2); S3, removing small holes from the segmentation map (2) obtained in step S2 to obtain a segmentation map (3); S4. Remove small components from the segmentation map (3) obtained in step S3, obtain its connected components, and obtain a feature map.

13. The system according to claim 12, characterized in that In step S1, x t,i,norm The method of converting the pixel points in x into two states is as follows: t,i,norm With x 0,i,norm Difference to get diff t,i , calculate the diff t,i The standard deviation of t,i , and use this as the threshold to binarize diff t,i ; The x 0,i,norm is the standardized image at time 0; The method for removing small noise in step S2 is: using the MedianBluer function in the cv2 module in Python to perform median filtering on the segmentation map (1) obtained in step S1; The method for removing small holes in step S3 is: using the MorphologyEx function in the cv2 module in Python to perform morphological expansion on the segmentation map (2) obtained in step S2; The method for filtering out small components in step S4 is: using the ConnectedComponentsWithStats function in the cv2 module in Python on the segmentation map (3).

14. The system according to claim 13, characterized in that The extraction of the erythema area in the feature map in the statistical feature extraction module is as follows: extracting the erythema area of ​​the feature map at each moment; The summation in the statistical feature extraction module is: summing up the erythema area of ​​the feature graph at each moment to obtain the detection value.

15. The system according to claim 14, characterized in that A test value ≥4000 indicates a tendency toward depression; The test value <4000 indicates mental health.

16. A chip, characterized in that: comprising a processor and a memory, wherein: The memory stores machine executable instructions of the system according to any one of claims 1 to 15; The processor can execute machine executable instructions in the memory to run the system described in any one of claims 1-15.

17. A device for screening mental illness, characterized in that: comprising a display, a controller and the chip according to claim 16; The display is used to: display operation status and images; The controller is a device that controls the operation of the device.

18. A computer-readable storage medium, characterized in that: A program for executing the system according to any one of claims 1 to 15 is stored.

Images