Parkinson's disease fist-clenching task evaluation method and system, storage medium and terminal

Abstract

The invention provides a Parkinson's disease fist-clenching task evaluation method and system, a storage medium and a terminal. The Parkinson's disease fist-clenching task evaluation method comprises the following steps: acquiring video information including the fist-clenching action of a Parkinson's disease patient; extracting hand skeleton sequence data from the video information, and preprocessing the hand skeleton sequence data; extracting hand joint point position features and hand skeleton vector features based on the preprocessed hand skeleton sequence; inputting the hand joint point position features and the hand skeleton vector features into a double-flow adaptive space-time diagram convolutional neural network; and inputting the fist-clenching action features output by the double-flow adaptive space-time diagram convolutional neural network into a classifier to obtain an evaluation score of the Parkinson's disease fist-clenching task. According to the evaluation method for the Parkinson's disease fist-clenching task, reliability evaluation of the Parkinson's disease fist-clenching task is achieved based on the tree pooling module and the space-time diagram convolutional network.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to an evaluation method and system, a storage medium and a terminal for Parkinson's disease fist-clenching task. Background technique [0002] Parkinson's Disease (PD) is one of the common neurodegenerative diseases, which affects the motor system of the human body. Parkinson's disease usually occurs in about 1% of people over the age of 55. With the aging of the population, the number of patients with Parkinson's disease will gradually increase. Experts from the World Health Organization predict that by 2030, the number of patients with Parkinson's disease in China will reach 5 million. Parkinson's disease has brought great distress and burden to patients and their families. Early diagnosis and appropriate treatment plan are the key to relieve symptoms and prolong survival period. [0003] Studies have shown that early diagnosis of Parkinson's disease symptoms can e...

AI Technical Summary

Problems solved by technology

In clinical practice, doctors usually score the severity of Parkinson's disease symptoms based on evaluation scales and their own experience, so there are certain subjective differences

However, this method requires high professional skills of assessors, and there are the following challenges:

[0004] 1) At present, there are about 4 million Parkinson's disease patients in China, and each patient needs to do multiple UPDRS checks every year, and it takes about 30 minutes to complete a manual check, which will consume a lot of manpower and time resources;

[0005] 2) Even for professional clinicians, the scoring results of different doctors will have subjective differences, which is not conducive to the objective consistency of disease diagnosis

[0016] At present, there are very few studies on applying deep learning skeleton sequence recognition algorithms to the field of PD action recognition, which almost belongs to a blank field.

Images