When AI learns human physiology…

Designing an inverse modeling approach to estimate the parameters of a computational model of cardiac function can be challenging, in particular when available clinical data is sparse and noisy. Instead, we propose to train an artificial agent exactly like a new user is trained: first learn how the computational model behaves by random and playful experiments. Then let it devise the optimal strategy for parameter identification through reinforcement learning. Applied on several problems, the agent could learn its new task and perform it much more efficiently and accurately than available inverse modeling strategies!

A Self-Taught Artificial Agent for Multi-Physics Computational Model Personalization“, D. Neumann et al., Medical Image Analysis 2016

Outstanding Paper Award at the ABDI-MICCAI Workshop, 2014

Chloé Audigier received the Outstanding Paper Award for the below paper at the 6th International Workshop on Abdominal Imaging: Computational and Clinical Applications, held in conjunction with MICCAI 2014 on September 14, 2014, Cambridge, USA. The Outstanding Paper Award aims at recognizing outstanding scientific work and clinical applications that are presented at the workshop.

Parameter Estimation for Personalization of Liver Tumor Radiofrequency Ablation C. Audigier, T Mansi, H. Delingette, S. Rapaka, V. Mihalef, D. Carnegie, E. Boctor, M. Choti, A. Kamen, D. Comaniciu, and N. Ayache

Congratulations Chloé!

MICCAI 2013 Awards

A big congratulation to Oliver Zettinig who won the prestigious MICCAI Young Scientist Award for the paper “Towards patient-specific models of cardiac electrophysiology thanks to a clever personalization of a concise model from clinical ECG measurements”!

Congratulation also to Ozan Oktay, who also got the honorable mention for his paper “Biomechanically Driven Registration of Pre- to Intra- Operative 3D Images for Laparoscopic Surgery”.

More information here.

Great job!