Understand movement

Helping the diagnosis and the monitoring of patients with cerebral palsy

The development of AI in the field of health opens up promising prospects for improving the quality of care, personalized care, and improved support for medical decision. The use of statistical learning algorithms could revolutionize the field of medical imaging. The AI4Child project focuses on the development of new methods to analyze medical images to help diagnose and monitor patient with cerebral palsy. AI4Child aims to develop new tools based on AI to improve new diagnosis phase based on brain MRI data of prematured babies and ensure better care of children. Research is conducted at IMT Atlantique and CHRU of Brest, in partnetship with Philips and the ILDYS Foundation, under the supervision of François Rousseau (ERC Starting Grant 2008), professor in the Image and Information Processing department at IMT Atlantique and researcher at the Laboratory of Medical Information Processing (LaTIM Inserm U1101). The AI-4-Child project is supported by the French National Research Agency (ANR).

Deep Learning application for automatic detection of walking events

DeepEvent is an application based on recurrent neural networks, which has been developed for the automatic detection of walking events. The network uses the 3D position and velocity of markers placed on the lateral malleolus, calcaneus, and second metatarsal to estimate the pose (PP) and detachment (DP) of the foot. The method was developed using 10526 PP and 9375 DP from 226 children with motor disabilities. The prediction error is 5.5ms for PP and 10.7ms for DP. DeepEvent is more accurate than trajectory-based algorithms usually used in motion analysis.

Télécharger le code en open source

En savoir plus sur la méthode de DeepEvent