From the 3 of 109 papers with an AI index.
38 citations
- Centre National de la Recherche ScientifiqueFR74 papers
- Université Paris-SaclayFR72 papers
- University of BolognaIT69 papers
- University of PaduaIT69 papers
- California Institute of TechnologyUS68 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di BolognaIT68 papers
- University of GenoaIT68 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di TorinoIT67 papers
- Sapienza University of RomeIT66 papers
- University of TriesteIT66 papers
- Universidad Autónoma de MadridES65 papers
- Istituto Nazionale di Fisica Nucleare, Sezione di PadovaIT64 papers
5 papers · 1 filter
GEN-Guard: Correcting Generalization Failures for Deployable Federated Surgical AI
Julia Alekseenko, Pietro Mascagni, AI4SafeChole Consortium +1
Federated Learning (FL) in surgical video AI enables collaborative model training without sharing sensitive data. However, standard evaluation practices - selecting the "best" glob…
A geometric and deep learning reproducible pipeline for monitoring floating anthropogenic debris in urban rivers using in situ cameras
Gauthier Grimmer, Romain Wenger, Clément Flint +3
The proliferation of floating anthropogenic debris in rivers has emerged as a pressing environmental concern, exerting a detrimental influence on biodiversity, water quality, and h…
Deep Learning Pose Estimation for Multi-Label Recognition of Combined Hyperkinetic Movement Disorders
Laura Cif, Diane Demailly, Gabriella A. Horvà th +15
Hyperkinetic movement disorders (HMDs) such as dystonia, tremor, chorea, myoclonus, and tics are disabling motor manifestations across childhood and adulthood. Their fluctuating, i…
DefSynUS: Real-time Patient-specific Intrahepatic Vessel Identification via Deformation-Aware CT-US Domain Adaptation
Karl-Philippe Beaudet, Yordanka Velikova, Sidaty El Hadramy +4
Purpose: Laparoscopic ultrasound (LUS) enhances the safety of liver surgery by visualizing intrahepatic vessels in real-time. Still, vessel identification remains difficult due to…
S4M: 4-points to Segment Anything
Adrien Meyer, Lorenzo Arboit, Giuseppe Massimiani +3
Purpose: The Segment Anything Model (SAM) promises to ease the annotation bottleneck in medical segmentation, but overlapping anatomy and blurred boundaries make its point prompts…