Lhassane Idoumghar

About

Lhassane Idoumghar is a leading researcher in artificial intelligence and its application to surgical skill assessment. His work focuses on developing deep learning models that can automatically and objectively evaluate surgical performance from kinematic motion data. Idoumghar’s major contributions include pioneering the use of convolutional neural networks (CNNs) for this task, as demonstrated in his highly cited 2018 paper, “Evaluating Surgical Skills from Kinematic Data Using Convolutional Neural Networks” (120 citations). He further advanced the field with his 2019 study on fully convolutional neural networks, which improved both accuracy and interpretability (105 citations). By addressing the limitations of manual feedback from senior surgeons—which is laborious, expensive, and subjective—Idoumghar’s work offers a scalable solution to meet the growing demand for surgical training. His research has significant implications for improving surgical education and patient outcomes, making him a key figure in the intersection of machine learning and medical technology.

Research Focus

Key Achievements

Top Papers

1. 1
   Evaluating Surgical Skills from Kinematic Data Using Convolutional Neural Networks

   120 citations · 2018
2. 2
   Accurate and interpretable evaluation of surgical skills from kinematic data using fully convolutional neural networks

   105 citations · 2019

Key Collaborators

Contact & Links