Knee joint lumbar vertebra lesion analysis system and method based on multi-source point cloud fusion

By using multi-source point cloud fusion technology, a spatial mapping field of anatomical structure point cloud and motion trajectory point cloud is generated. Deformation simulation and multi-scale frequency domain decomposition under physical constraints are performed, which solves the problem of correlation between static anatomical structure and dynamic motion data in the analysis of knee joint and lumbar spine lesions, and realizes accurate qualitative description of lesions.

CN122289180APending Publication Date: 2026-06-26SUZHOU TRADITIONAL CHINESE MEDICINE HOSPITAL
0 Cites 0 Cited by

Patent Information

Application Number
CN202610377863.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-26
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing techniques for analyzing knee and lumbar spine lesions cannot achieve continuous spatial correlation between static anatomical structures and dynamic motion data, cannot accurately extract abnormal vibration characteristics of lesions, lack spatiotemporal integration and frequency domain decomposition of dynamic bone deformation, and are difficult to distinguish between physiological micro-tremors and pathological abnormal vibrations.

Method used

By using multi-source point cloud fusion technology, a spatial mapping field is generated between the anatomical structure point cloud and the motion trajectory point cloud sequence. Deformation simulation is performed under physical constraints, local curvature changes are calculated, and multi-scale frequency domain decomposition is carried out to extract abnormal vibration mode features and compare them with a standard lesion pattern library.

Benefits of technology

It achieves continuous spatial correlation between static anatomical structure and dynamic motion data, strengthens the motion correlation representation of the bone deformation process, and can accurately extract abnormal vibration characteristics of lesions, providing qualitative description.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of medical image lesion analysis, in particular to a knee joint lumbar vertebra lesion analysis system and method based on multi-source point cloud fusion, and the method comprises the steps: obtaining static medical image scanning data and dynamic motion capture data of a target area, carrying out the three-dimensional reconstruction of the static data, and generating an anatomical structure point cloud; performing space-time registration and track extraction on dynamic data to generate a motion track point cloud sequence, establishing a space mapping field of the two, transmitting a motion vector, driving anatomical structure point cloud to deform and simulate under physical constraints to generate dynamic skeleton point cloud, and calculating local curvature variation to form a curvature space-time evolution graph; and separating physiological low-frequency and pathological high-frequency components through multi-scale frequency domain decomposition, extracting abnormal vibration mode features, comparing the abnormal vibration mode features with a standard lesion knowledge base, and outputting qualitative description of potential lesions of knee joints or lumbar vertebrae. Static dissection and dynamic motion data are fused, physiological vibration and pathological vibration are accurately distinguished, and the accuracy of lesion analysis is improved.
Need to check novelty before this filing date? Find Prior Art