Multi-source feature-based automatic assessment method for limb dysfunction of lumbago patient

Abstract

The invention discloses an automatic assessment method for limb dysfunction of a lumbago patient based on multi-source features, and the method comprises the steps: firstly, carrying out the automatic segmentation of multifidus muscle and erector spine muscle in a waist nuclear magnetic resonance (MRI) image through a U-Net neural network, and achieving the extraction of imaging features, such as the muscle cross-sectional area and the fat infiltration degree, through a maximum between-class variance method; secondly, screening clinical common lumbago patient evaluation scales, and extracting scale characteristics; then, screening all features by using a support vector machine recursive feature elimination algorithm (SVM-RFE), reducing feature redundancy, and determining an optimal feature combination; and finally, a support vector machine (SVM) method in machine learning is selected to construct a limb dysfunction assessment model of the lumbago patient, and automatic assessment and discrimination of dysfunction of the lumbago patient are realized. According to the method, the automatic assessment of the limb dysfunction degree of the lumbago patient is realized by combining a support vector machine method based on multi-source feature combination such as scale and iconography for the first time.

Description

technical field [0001] The invention belongs to the technical field of limb dysfunction assessment, and in particular relates to an automatic assessment method for limb dysfunction in patients with low back pain based on multi-source features. Background technique [0002] Low back pain is a common clinical disease with high incidence, which seriously affects the work and life of patients, and brings a heavy burden to patients and families. Accurate assessment of functional impairment is an important prerequisite for the determination of patient rehabilitation treatment and assistive device adaptation plans. [0003] At present, the assessment of limb dysfunction in patients with low back pain is mainly based on behavioral scales. The commonly used clinical scales include the Visual Analogue Scale (VAS), the Oswestry Disability Index (ODI), Japan Japanese Orthopaetic Association Scores (JOA), Roland-Morris Disability Questionnaire (RMDQ), Quebec Back Pain Disability Scale (...

AI Technical Summary

Problems solved by technology

[0009] In view of the defects of strong subjectivity and low reliability in the existing clinical assessment methods of limb dysfunction in patients with low back pain, the purpose of the present invention is to provide an automatic assessment method for limb dysfunction in patients with low back pain based on multi-source features

Images