Communication Dans Un Congrès Année : 2025

Detection of Peripheral Neuropathy from Walking Videos Using Pose Estimation and Anatomical Segmentation

Résumé

Peripheral neuropathy, a common complication of diabetes and kidney disease, impairs gait and often goes undetected in early stages. Current diagnostic methods require specialized equipment, limiting their accessibility in low-resource and home environments.

This research aims to develop a contactless, video-based deep learning pipeline for early detection of peripheral neuropathy. The method integrates YOLOv11-based pose estimation and SAM-guided anatomical segmentation to extract lower limb features, followed by gait classification using a pretrained ResNet34 model.

The approach was evaluated on 113 sagittal-view walking videos from 57 clinical participants, with strict participant-level separation between training and testing. Our pipeline achieved an accuracy of 80% when using the left ankle keypoint to guide segmentation, outperforming both YOLO-only and SAMonly baselines. The system also localized clinically relevant gait features without requiring wearable sensors.

This work demonstrates the feasibility of a low-cost, scalable, and fully contactless screening tool for early peripheral neuropathy detection, with strong potential for deployment in remote or home settings.

Fichier principal
Vignette du fichier
Albanna et al., 2025 - IEEE congress a92.pdf (305.27 Ko) Télécharger le fichier

Dates et versions

hal-05492595 , version 1 (04-02-2026)

Licence

Identifiants

  • HAL Id : hal-05492595 , version 1

Citer

Liwaa Albanna, Nassib Abdallah, Bassam Daya, Jean-Marie Marion, Antoine Chatrenet, et al.. Detection of Peripheral Neuropathy from Walking Videos Using Pose Estimation and Anatomical Segmentation. IEEE International Conference on Emerging Trends in Engineering and Computing (ETECOM), Oct 2025, Bahrain, Bahrain. ⟨hal-05492595⟩
185 Consultations
41 Téléchargements

Partager

  • More