Parkinson's disease screening method and system based on image analysis and storage medium

Abstract

The invention discloses a Parkinson's disease screening method and system based on image analysis and a storage medium, and relates to the technical field of image analysis, and the method comprises the steps: controlling a shooting device to carry out video collection on a to-be-screened crowd, and obtaining a to-be-analyzed video; and performing analysis processing on the to-be-analyzed video to obtain to-be-verified features. According to the method, the video to be analyzed is preprocessed, irrelevant images in the video to be analyzed are deleted, the subsequent image analysis time is shortened, then the preprocessed video to be analyzed is subjected to feature extraction, the hand tremor frequency to be verified is determined, the judgment standard of the Parkinson's disease is analyzed, the set hand tremor frequency threshold value is determined, and the accuracy of the hand tremor frequency is improved. And finally, the to-be-verified hand tremor frequency and the set hand tremor frequency threshold value are judged and processed, whether people in the to-be-screened crowd suffer from the Parkinson's disease or not is determined, the Parkinson's disease is screened in an image processing mode, the working intensity of screening personnel is reduced, and meanwhile the screening precision of the Parkinson's disease is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image analysis, and in particular to a Parkinson's disease screening method, system and storage medium based on image analysis. Background Art

[0002] Parkinson's disease, also often referred to as "Parkinson's paralysis," is a neurodegenerative disease. The main cause of this disease is the degeneration and death of dopaminergic neurons in the substantia nigra, which may be related to multiple factors such as genetics, environmental factors, and aging of the nervous system. It is generally recognized that aging is the most important factor in the occurrence of Parkinson's disease. The disease has a significant high incidence in the elderly, and the incidence rate in men is slightly higher than that in women.

[0003] The symptoms of Parkinson's disease vary, mainly manifested in two categories: motor and non-motor symptoms. Motor symptoms include resting tremor, muscle rigidity, bradykinesia, and postural balance disorders. Non-motor symptoms mainly include constipation, olfactory disorders, sleep disorders, autonomic dysfunction, and mental and cognitive disorders.

[0004] The existing Parkinson's disease screening is carried out by manually counting the number of hand tremors in suspicious people. When the number of suspicious people is too large, the workload of the screeners will increase. When the screeners conduct screening for a long time, their attention will be reduced, and the number of hand tremors may be misrecorded or missed, thereby reducing the accuracy of the screening results. Summary of the invention

[0005] In order to solve the above technical problems, a Parkinson's disease screening method, system and storage medium based on image analysis are provided. The technical solution solves the problem proposed in the above background technology that the existing Parkinson's disease screening is to manually count the number of hand tremors in suspicious people. When the number of suspicious people is too large, the work intensity of the screening personnel will be increased, and when the screening personnel conduct screening for a long time, it will cause the screening personnel's attention to decrease, resulting in the number of hand tremors being misrecorded or missed, thereby reducing the accuracy of the screening results.

[0006] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0007] A Parkinson's disease screening method based on image analysis, comprising:

[0008] Based on the image analysis terminal, control the shooting equipment to collect videos of the people to be screened and obtain the videos to be analyzed;

[0009] Based on the image analysis terminal, the video to be analyzed is analyzed and processed to obtain the features to be verified;

[0010] Based on the image analysis terminal, the features to be verified are judged and processed to obtain the Parkinson's disease screening results;

[0011] Design treatment plans based on Parkinson's disease screening results.

[0012] Preferably, the step of analyzing and processing the video to be analyzed based on the image analysis terminal to obtain the features to be verified specifically includes the following steps:

[0013] Based on the image analysis terminal, preprocess the video to be analyzed to obtain a first sub-video to be analyzed;

[0014] Based on the image analysis terminal, data reading and processing are performed on the first sub-video to be analyzed to obtain the time length of the first sub-video to be analyzed;

[0015] Based on the image analysis terminal, the time length of the first sub-video to be analyzed is analyzed and processed to determine the video segmentation length;

[0016] The image analysis terminal performs video decomposition processing on the first sub-video to be analyzed according to the video segmentation length, and obtains multiple groups of second sub-videos to be analyzed;

[0017] Based on the image analysis terminal, multiple groups of second sub-videos to be analyzed are analyzed and processed to obtain features to be verified, wherein the features to be verified are specifically hand tremor frequencies to be verified.

[0018] Preferably, the preprocessing of the video to be analyzed based on the image analysis terminal to obtain the first sub-video to be analyzed specifically includes the following steps:

[0019] Based on the image analysis terminal, the video to be analyzed is subjected to video decomposition processing to obtain several groups of first video frames;

[0020] Based on the image analysis terminal, performing image analysis processing on the plurality of groups of first video frames to determine irrelevant images;

[0021] The image analysis terminal deletes a plurality of groups of first video frames according to irrelevant images to obtain a plurality of groups of second video frames;

[0022] Based on the image analysis terminal, video integration processing is performed on the multiple groups of second video frames to obtain the first sub-video to be analyzed.

[0023] Preferably, the image analysis terminal analyzes and processes the time length of the first sub-video to be analyzed, and determines the video segmentation length, specifically including the following steps:

[0024] Based on the image analysis terminal, data extraction and processing are performed on the disease database system to obtain relevant data on Parkinson's disease;

[0025] Based on the image analysis terminal, information retrieval and processing are performed on Parkinson's disease related data to obtain the evaluation criteria for Parkinson's disease;

[0026] Based on the image analysis terminal, the data of the Parkinson's disease evaluation criteria is traversed and processed to determine the video segmentation length.

[0027] Preferably, the step of analyzing and processing the plurality of groups of second sub-videos to be analyzed based on the image analysis terminal to obtain the features to be verified specifically comprises the following steps:

[0028] Based on the image analysis terminal, perform video decomposition processing on the second sub-video to be analyzed to obtain several groups of second video frames;

[0029] Based on the image analysis terminal, feature extraction processing is performed on the images in the plurality of groups of second video frames to determine a hand tremor image;

[0030] Based on the image analysis terminal, the hand tremor image is analyzed and processed to determine the hand tremor frequency to be verified.

[0031] Preferably, the step of analyzing and processing the hand tremor image based on the image analysis terminal to determine the hand tremor frequency to be verified specifically includes the following steps:

[0032] Based on the image analysis terminal, the hand tremor image is counted and processed to determine the number of hand tremors;

[0033] Based on the image analysis terminal, performing image counting processing on the second video frame to determine the total number of images of the second video frame;

[0034] Based on the image analysis terminal, the number of hand tremors and the total number of images of the second video frame are calculated and processed to determine the hand tremor frequency to be verified;

[0035] The specific calculation formula for determining the hand tremor frequency to be verified is:

[0036]

[0037] In the formula, F a The hand tremor frequency to be verified; I i is the hand tremor image; n is the specific number of hand tremor images; I j is the image in the second video frame; m is the total number of images in the second video frame; n <m。

[0038] Preferably, the image analysis terminal is used to judge and process the features to be verified, and obtain the Parkinson's disease screening results, which specifically includes the following steps:

[0039] Based on the image analysis terminal, the Parkinson's disease evaluation criteria are analyzed and processed to determine the frequency range of hand tremors in Parkinson's disease;

[0040] Based on the image analysis terminal, the hand tremor frequency range of Parkinson's disease is analyzed and processed to determine and set the hand tremor frequency threshold;

[0041] Based on the image analysis terminal, the hand tremor frequency to be verified and the set hand tremor frequency threshold are compared and judged to obtain the Parkinson's disease screening results.

[0042] Preferably, the image analysis terminal is used to compare and judge the hand tremor frequency to be verified and the set hand tremor frequency threshold to obtain the Parkinson's disease screening result, which specifically includes the following steps:

[0043] Based on the image analysis terminal, the hand tremor frequency to be verified and the hand tremor frequency threshold to be set are judged and processed;

[0044] If the hand tremor frequency to be verified is less than the set first hand tremor frequency threshold, output that the screening person corresponding to the hand tremor frequency to be verified does not suffer from Parkinson's disease;

[0045] If the hand tremor frequency to be verified is greater than or equal to the set first hand tremor frequency threshold, and the hand tremor frequency to be verified is less than the set second hand tremor frequency threshold, output that the screened person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the early stage;

[0046] If the hand tremor frequency to be verified is greater than or equal to the set second hand tremor frequency threshold, and the hand tremor frequency to be verified is less than the set third hand tremor frequency threshold, output that the screening person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the middle stage;

[0047] If the hand tremor frequency to be verified is greater than or equal to the set third hand tremor frequency threshold, it is output that the screening person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the late stage.

[0048] Furthermore, a Parkinson's disease screening system based on image analysis is proposed, which is used to implement the Parkinson's disease screening method based on image analysis as described above, comprising:

[0049] An image analysis terminal, which is used to control the shooting device to collect videos of the people to be screened, and is used to perform video preprocessing, video segmentation, video analysis, feature judgment, and Parkinson's disease determination on the videos to be analyzed, and is used to realize data transmission and information exchange between various modules;

[0050] A disease database system, wherein the disease database system is used to store relevant data of various diseases;

[0051] A shooting device, wherein the shooting device is used to collect videos of the people to be screened and obtain videos to be analyzed;

[0052] An image preprocessing module, the image preprocessing module is used to preprocess the video to be analyzed and determine a first sub-video to be analyzed;

[0053] A video segmentation module, wherein the video segmentation module performs analysis and processing according to the Parkinson's disease evaluation criteria to determine the video segmentation length, and the video segmentation module performs video decomposition processing on the first sub-video to be analyzed according to the video segmentation length to obtain the second sub-video to be analyzed;

[0054] A feature extraction module, the feature extraction module is used to perform feature analysis on the second sub-video to be analyzed, and determine the hand tremor frequency to be verified;

[0055] A threshold determination module, wherein the threshold determination module performs information analysis and processing on the evaluation criteria of Parkinson's disease to determine the hand tremor frequency interval of Parkinson's disease, and the threshold determination module performs analysis and processing according to the hand tremor frequency interval of Parkinson's disease to set the hand tremor frequency threshold;

[0056] A disease judgment module is provided, wherein the disease judgment module judges and processes the hand tremor frequency to be verified and the hand tremor frequency threshold to be set, so as to determine whether the person to be screened suffers from Parkinson's disease.

[0057] Furthermore, a storage medium is proposed, on which a computer program is stored, and when the computer program is called and run, it executes the above-mentioned Parkinson's disease screening method based on image analysis.

[0058] Compared with the prior art, the present invention provides a Parkinson's disease screening method, system and storage medium based on image analysis, which have the following beneficial effects:

[0059] The present invention firstly pre-processes the video to be analyzed, deletes irrelevant images in the video to be analyzed, and shortens the time of subsequent image analysis. Then, the pre-processed video to be analyzed is feature extracted to determine the hand tremor frequency to be verified. Then, the judgment criteria of Parkinson's disease are analyzed to determine and set the hand tremor frequency threshold. Finally, the hand tremor frequency to be verified and the set hand tremor frequency threshold are judged and processed to determine whether anyone in the population to be screened suffers from Parkinson's disease. Parkinson's disease is screened by image processing, which reduces the work intensity of the screening personnel and improves the screening accuracy of Parkinson's disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a flow chart of steps S100-S400 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0061] Figure 2This is a flow chart of steps S201-S205 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0062] Figure 3 A schematic flow chart of steps S2011-S2014 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0063] Figure 4 This is a flow chart of steps S2031-S2033 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0064] Figure 5 This is a flow chart of steps S2051-S2053 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0065] Figure 6 This is a flow chart of steps S20531-S20533 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0066] Figure 7 This is a flow chart of steps S301-S303 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0067] Figure 8 This is a flow chart of steps S3031-S3034 in a Parkinson's disease screening method based on image analysis proposed by the present invention;

[0068] Fig. 9 This is a structural block diagram of a Parkinson's disease screening system based on image analysis proposed by the present invention. DETAILED DESCRIPTION

[0069] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0070] Reference Figure 1 As shown, a Parkinson's disease screening method based on image analysis comprises:

[0071] S100, based on the image analysis terminal, controlling the shooting device to collect videos of the people to be screened, and obtaining the videos to be analyzed;

[0072] S200, based on the image analysis terminal, analyzing and processing the video to be analyzed to obtain features to be verified;

[0073] S300, based on the image analysis terminal, judging and processing the features to be verified, and obtaining the Parkinson's disease screening results;

[0074] S400. Design treatment plan based on Parkinson's disease screening results;

[0075] Those skilled in the art will understand that when a person suffers from Parkinson's disease, his hands will tremble, but not all hand tremors necessarily indicate Parkinson's disease. Therefore, the shooting equipment is controlled to capture video of the people to be screened, and feature analysis is performed on the captured video to determine the frequency of the hand tremors to be verified. Finally, the hand tremor frequency to be verified is judged according to the evaluation criteria of Parkinson's disease to determine whether the person to be screened suffers from Parkinson's disease. The severity of the disease in patients with Parkinson's disease is determined by the different frequencies of the hand tremors to be verified, and a corresponding treatment plan is designed.

[0076] Reference Figure 2 As shown, based on the image analysis terminal, the video to be analyzed is analyzed and processed, and obtaining the features to be verified specifically includes the following steps:

[0077] S201, based on the image analysis terminal, preprocessing the video to be analyzed to obtain a first sub-video to be analyzed;

[0078] S202: Based on the image analysis terminal, data reading and processing are performed on the first sub-video to be analyzed to obtain the time length of the first sub-video to be analyzed;

[0079] S203, based on the image analysis terminal, analyzing and processing the time length of the first sub-video to be analyzed, and determining the video segmentation length;

[0080] S204, the image analysis terminal performs video decomposition processing on the first sub-video to be analyzed according to the video segmentation length, and obtains multiple groups of second sub-videos to be analyzed;

[0081] S205, based on the image analysis terminal, analyzing and processing the multiple groups of second sub-videos to be analyzed to obtain features to be verified, wherein the features to be verified are specifically hand tremor frequencies to be verified;

[0082] In this embodiment, the hand tremor frequency of Parkinson's disease refers to the number of tremors within a certain period of time. Therefore, a certain time is set as the video segmentation length to segment the first sub-video to be analyzed. Then, the hand tremor frequency to be analyzed can be determined by analyzing the number of hand tremors that appear in the second sub-video to be analyzed.

[0083] Reference Figure 3 As shown, based on the image analysis terminal, preprocessing the video to be analyzed and obtaining the first sub-video to be analyzed specifically include the following steps:

[0084] S2011, based on the image analysis terminal, performing video decomposition processing on the video to be analyzed to obtain several groups of first video frames;

[0085] S2012, based on the image analysis terminal, performing image analysis processing on a plurality of groups of first video frames to determine irrelevant images;

[0086] S2013, the image analysis terminal deletes a plurality of groups of first video frames according to irrelevant images to obtain a plurality of groups of second video frames;

[0087] S2014, based on the image analysis terminal, performing video integration processing on the multiple groups of second video frames to obtain a first sub-video to be analyzed;

[0088] In this embodiment, when the video of the person to be screened is captured by the shooting device, images of the surrounding environment may be captured, but the person to be screened does not appear in the image. Therefore, in order to reduce the subsequent image analysis time and to reduce interference, the video to be analyzed is decomposed to obtain video frames, and each image in the video frame is analyzed to eliminate images that only show the environment, that is, irrelevant images. It can be understood that a video is composed of a combination of images, so the video is disassembled to eliminate irrelevant images.

[0089] Reference Figure 4 As shown, based on the image analysis terminal, analyzing and processing the time length of the first sub-video to be analyzed, determining the video segmentation length specifically includes the following steps:

[0090] S2031. Based on the image analysis terminal, extract data from the disease database system to obtain relevant data on Parkinson's disease;

[0091] S2032. Based on the image analysis terminal, perform information retrieval processing on Parkinson's disease related data to obtain the evaluation criteria of Parkinson's disease;

[0092] S2033, based on the image analysis terminal, performing data traversal processing on the evaluation criteria of Parkinson's disease to determine the video segmentation length;

[0093] In this embodiment, when a patient suffers from Parkinson's disease, his hands will produce a certain amount of tremors within a certain period of time. Therefore, the acquisition time of Parkinson's disease, that is, the video segmentation length, is determined according to the evaluation criteria of Parkinson's disease. The first sub-video to be analyzed is decomposed according to the video segmentation length, that is, the second sub-video to be analyzed. When counting the hand tremors in the second sub-video to be analyzed later, there is no need to pay attention to its time, thereby avoiding the influence of too many parameters on the analysis process.

[0094] Reference Figure 5 As shown, based on the image analysis terminal, multiple groups of second sub-videos to be analyzed are analyzed and processed to obtain the features to be verified, which specifically includes the following steps:

[0095] S2051. Based on the image analysis terminal, perform video decomposition processing on the second sub-video to be analyzed to obtain several groups of second video frames;

[0096] S2052, based on the image analysis terminal, performing feature extraction processing on the images in the plurality of groups of second video frames to determine a hand tremor image;

[0097] S2053. Analyze and process the hand tremor image based on the image analysis terminal to determine the hand tremor frequency to be verified.

[0098] Reference Figure 6 As shown, based on the image analysis terminal, analyzing and processing the hand tremor image to determine the hand tremor frequency to be verified specifically includes the following steps:

[0099] S20531. Based on the image analysis terminal, counting processing is performed on the hand tremor image to determine the number of hand tremors;

[0100] S20532. Based on the image analysis terminal, perform image counting processing on the second video frame to determine the total number of images in the second video frame;

[0101] S20533, based on the image analysis terminal, calculating and processing the number of hand tremors and the total number of images of the second video frame to determine the hand tremor frequency to be verified;

[0102] The specific calculation formula for determining the hand tremor frequency to be verified is:

[0103]

[0104] In the formula, F a The hand tremor frequency to be verified; I i is the hand tremor image; n is the specific number of hand tremor images; I j is the image in the second video frame; m is the total number of images in the second video frame; n <m;

[0105] In this embodiment, the images in which hand tremors appear in each video frame are counted, that is, the number of hand tremors, and then all images in each video frame are counted, that is, the total number of images in the video frame. Finally, the two are calculated to obtain the hand tremor frequency in each video frame.

[0106] Reference Figure 7 As shown, based on the image analysis terminal, the features to be verified are judged and processed, and the Parkinson's disease screening results are obtained, which specifically include the following steps:

[0107] S301, based on the image analysis terminal, performing information analysis and processing on the evaluation criteria of Parkinson's disease to determine the frequency range of hand tremors of Parkinson's disease;

[0108] S302, analyzing and processing the hand tremor frequency interval of Parkinson's disease based on the image analysis terminal to determine and set the hand tremor frequency threshold;

[0109] S303: Based on the image analysis terminal, a comparison and judgment process is performed on the hand tremor frequency to be verified and the set hand tremor frequency threshold to obtain a Parkinson's disease screening result.

[0110] Reference Figure 8 As shown, based on the image analysis terminal, the hand tremor frequency to be verified and the set hand tremor frequency threshold are compared and judged, and obtaining the Parkinson's disease screening result specifically includes the following steps:

[0111] S3031, based on the image analysis terminal, determining and processing the hand tremor frequency to be verified and setting the hand tremor frequency threshold;

[0112] S3032: if the hand tremor frequency to be verified is less than the set first hand tremor frequency threshold, outputting that the screening person corresponding to the hand tremor frequency to be verified does not suffer from Parkinson's disease;

[0113] S3033: if the hand tremor frequency to be verified is greater than or equal to the set first hand tremor frequency threshold, and the hand tremor frequency to be verified is less than the set second hand tremor frequency threshold, output that the screening person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the early stage;

[0114] S3034: if the hand tremor frequency to be verified is greater than or equal to the set second hand tremor frequency threshold, and the hand tremor frequency to be verified is less than the set third hand tremor frequency threshold, output that the screening person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the middle stage;

[0115] S3035: if the hand tremor frequency to be verified is greater than or equal to the set third hand tremor frequency threshold, outputting that the screening person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the late stage;

[0116] In the present embodiment, Parkinson's disease is divided into early, middle and late stages, and the condition of each stage is different, therefore, the hand tremor frequency will also be different, therefore, by comparing the hand tremor frequency to be verified with the set first hand tremor frequency threshold, the set second hand tremor frequency threshold, and the set third hand tremor frequency threshold, it is determined whether the person to be screened suffers from Parkinson's disease, and if suffering from Parkinson's disease, a judgment is made to determine the stage of the disease, and finally, a corresponding treatment plan is designed according to the stage of the disease. The above method not only reduces the work intensity of the screening personnel, but also reduces the misjudgment caused by long-term work of the screening personnel, thereby improving the screening accuracy.

[0117] Reference Fig. 9 As shown, a Parkinson's disease screening system based on image analysis is used to implement the Parkinson's disease screening method based on image analysis as described above, comprising:

[0118] An image analysis terminal, which is used to control the shooting device to collect videos of the people to be screened, and is used to perform video preprocessing, video segmentation, video analysis, feature judgment, and Parkinson's disease determination on the videos to be analyzed, and is used to realize data transmission and information exchange between various modules;

[0119] A disease database system, wherein the disease database system is used to store relevant data of various diseases;

[0120] A shooting device, wherein the shooting device is used to collect videos of the people to be screened and obtain videos to be analyzed;

[0121] An image preprocessing module, the image preprocessing module is used to preprocess the video to be analyzed and determine a first sub-video to be analyzed;

[0122] A video segmentation module, wherein the video segmentation module performs analysis and processing according to the Parkinson's disease evaluation criteria to determine the video segmentation length, and the video segmentation module performs video decomposition processing on the first sub-video to be analyzed according to the video segmentation length to obtain the second sub-video to be analyzed;

[0123] A feature extraction module, the feature extraction module is used to perform feature analysis on the second sub-video to be analyzed, and determine the hand tremor frequency to be verified;

[0124] A threshold determination module, wherein the threshold determination module performs information analysis and processing on the evaluation criteria of Parkinson's disease to determine the hand tremor frequency interval of Parkinson's disease, and the threshold determination module performs analysis and processing according to the hand tremor frequency interval of Parkinson's disease to set the hand tremor frequency threshold;

[0125] A disease judgment module is provided, wherein the disease judgment module judges and processes the hand tremor frequency to be verified and the hand tremor frequency threshold to be set, so as to determine whether the person to be screened suffers from Parkinson's disease.

[0126] Furthermore, a storage medium is proposed, on which a computer program is stored. When the computer program is called and run, it executes a Parkinson's disease screening method based on image analysis as described above, wherein the storage medium can be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid-state drive (SSD).

[0127] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A Parkinson's disease screening method based on image analysis, characterized in that: include: Based on the image analysis terminal, control the shooting equipment to collect videos of the people to be screened and obtain the videos to be analyzed; Based on the image analysis terminal, the video to be analyzed is analyzed and processed to obtain the features to be verified; Based on the image analysis terminal, the features to be verified are judged and processed to obtain the Parkinson's disease screening results; Design treatment plans based on Parkinson's disease screening results.

2. A Parkinson's disease screening method based on image analysis according to claim 1, characterized in that: The image analysis terminal is used to analyze and process the video to be analyzed, and obtain the features to be verified, which specifically includes the following steps: Based on the image analysis terminal, preprocess the video to be analyzed to obtain a first sub-video to be analyzed; Based on the image analysis terminal, data reading and processing are performed on the first sub-video to be analyzed to obtain the time length of the first sub-video to be analyzed; Based on the image analysis terminal, the time length of the first sub-video to be analyzed is analyzed and processed to determine the video segmentation length; The image analysis terminal performs video decomposition processing on the first sub-video to be analyzed according to the video segmentation length, and obtains multiple groups of second sub-videos to be analyzed; Based on the image analysis terminal, multiple groups of second sub-videos to be analyzed are analyzed and processed to obtain features to be verified, wherein the features to be verified are specifically hand tremor frequencies to be verified.

3. A Parkinson's disease screening method based on image analysis according to claim 2, characterized in that: The method of preprocessing the video to be analyzed based on the image analysis terminal to obtain the first sub-video to be analyzed specifically includes the following steps: Based on the image analysis terminal, the video to be analyzed is subjected to video decomposition processing to obtain several groups of first video frames; Based on the image analysis terminal, performing image analysis processing on the plurality of groups of first video frames to determine irrelevant images; The image analysis terminal deletes a plurality of groups of first video frames according to irrelevant images to obtain a plurality of groups of second video frames; Based on the image analysis terminal, video integration processing is performed on the multiple groups of second video frames to obtain the first sub-video to be analyzed.

4. A Parkinson's disease screening method based on image analysis according to claim 2, characterized in that: The image analysis terminal analyzes and processes the time length of the first sub-video to be analyzed, and determines the video segmentation length, specifically including the following steps: Based on the image analysis terminal, data extraction and processing are performed on the disease database system to obtain relevant data on Parkinson's disease; Based on the image analysis terminal, information retrieval and processing are performed on Parkinson's disease related data to obtain the evaluation criteria for Parkinson's disease; Based on the image analysis terminal, the data of the Parkinson's disease evaluation criteria is traversed and processed to determine the video segmentation length.

5. The method for screening Parkinson's disease based on image analysis according to claim 2, characterized in that: The image analysis terminal is used to analyze and process multiple groups of second sub-videos to be analyzed, and obtain the features to be verified, which specifically includes the following steps: Based on the image analysis terminal, perform video decomposition processing on the second sub-video to be analyzed to obtain several groups of second video frames; Based on the image analysis terminal, feature extraction processing is performed on the images in the plurality of groups of second video frames to determine a hand tremor image; Based on the image analysis terminal, the hand tremor image is analyzed and processed to determine the hand tremor frequency to be verified.

6. A Parkinson's disease screening method based on image analysis according to claim 5, characterized in that: The method of analyzing and processing the hand tremor image based on the image analysis terminal to determine the hand tremor frequency to be verified specifically includes the following steps: Based on the image analysis terminal, the hand tremor image is counted and processed to determine the number of hand tremors; Based on the image analysis terminal, performing image counting processing on the second video frame to determine the total number of images of the second video frame; Based on the image analysis terminal, the number of hand tremors and the total number of images of the second video frame are calculated and processed to determine the hand tremor frequency to be verified; The specific calculation formula for determining the hand tremor frequency to be verified is: In the formula, F a The hand tremor frequency to be verified; I i is the hand tremor image; n is the specific number of hand tremor images; I j is the image in the second video frame; m is the total number of images in the second video frame; n <m。 7. A Parkinson's disease screening method based on image analysis according to claim 1, characterized in that: The image analysis terminal is used to judge and process the features to be verified, and obtain the Parkinson's disease screening results, which specifically includes the following steps: Based on the image analysis terminal, the Parkinson's disease evaluation criteria are analyzed and processed to determine the frequency range of hand tremors in Parkinson's disease; Based on the image analysis terminal, the hand tremor frequency range of Parkinson's disease is analyzed and processed to determine and set the hand tremor frequency threshold; Based on the image analysis terminal, the hand tremor frequency to be verified and the set hand tremor frequency threshold are compared and judged to obtain the Parkinson's disease screening results.

8. A Parkinson's disease screening method based on image analysis according to claim 7, characterized in that: The image analysis terminal is based on which the hand tremor frequency to be verified is compared with the set hand tremor frequency threshold to obtain the Parkinson's disease screening result, which specifically includes the following steps: Based on the image analysis terminal, the hand tremor frequency to be verified and the hand tremor frequency threshold to be set are judged and processed; If the hand tremor frequency to be verified is less than the set first hand tremor frequency threshold, output that the screening person corresponding to the hand tremor frequency to be verified does not suffer from Parkinson's disease; If the hand tremor frequency to be verified is greater than or equal to the set first hand tremor frequency threshold, and the hand tremor frequency to be verified is less than the set second hand tremor frequency threshold, output that the screened person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the early stage; If the hand tremor frequency to be verified is greater than or equal to the set second hand tremor frequency threshold, and the hand tremor frequency to be verified is less than the set third hand tremor frequency threshold, output that the screening person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the middle stage; If the hand tremor frequency to be verified is greater than or equal to the set third hand tremor frequency threshold, it is output that the screening person corresponding to the hand tremor frequency to be verified suffers from Parkinson's disease, and the Parkinson's disease is in the late stage.

9. A Parkinson's disease screening system based on image analysis, used to implement a Parkinson's disease screening method based on image analysis as claimed in any one of claims 1 to 8, characterized in that: include: An image analysis terminal, which is used to control the shooting device to collect videos of the people to be screened, and is used to perform video preprocessing, video segmentation, video analysis, feature judgment, and Parkinson's disease determination on the videos to be analyzed, and is used to realize data transmission and information exchange between various modules; A disease database system, wherein the disease database system is used to store relevant data of various diseases; A shooting device, wherein the shooting device is used to collect videos of the people to be screened and obtain videos to be analyzed; An image preprocessing module, the image preprocessing module is used to preprocess the video to be analyzed and determine a first sub-video to be analyzed; A video segmentation module, wherein the video segmentation module performs analysis and processing according to the Parkinson's disease evaluation criteria to determine the video segmentation length, and the video segmentation module performs video decomposition processing on the first sub-video to be analyzed according to the video segmentation length to obtain the second sub-video to be analyzed; A feature extraction module, the feature extraction module is used to perform feature analysis on the second sub-video to be analyzed, and determine the hand tremor frequency to be verified; A threshold determination module, wherein the threshold determination module performs information analysis and processing on the evaluation criteria of Parkinson's disease to determine the hand tremor frequency interval of Parkinson's disease, and the threshold determination module performs analysis and processing according to the hand tremor frequency interval of Parkinson's disease to set the hand tremor frequency threshold; A disease judgment module is provided, wherein the disease judgment module judges and processes the hand tremor frequency to be verified and the hand tremor frequency threshold to be set, so as to determine whether the person to be screened suffers from Parkinson's disease.

10. A storage medium, characterized in that: A computer program is stored thereon, and when the computer program is called and run, it executes a Parkinson's disease screening method based on image analysis as described in any one of claims 1 to 8.

Images