08.10.2026
Best Paper Award at ASMUS workshop at MICCAI 2026
Ultra-Wide-NeRF Recognized for Wide Field-of-View Ultrasound Reconstruction
The paper "Ultra-Wide-NeRF: Multivariate Gaussian NeRF for Wide Field-of-View Ultrasound Reconstruction" received the Best Paper Award at ASMUS 2026, the MICCAI Workshop on Medical Ultrasound. The workshop took place in Strasbourg, France, on October 1, 2026, and the award was sponsored by NVIDIA.
The paper is the outcome of Patris Valera's Master's thesis, carried out in collaboration with LUMA Vision. It was written by Patris Valera, Magdalena Wysocki, MCML Junior Members Felix Dülmer and Mohammad Farid Azampour, Sebastian Herz, Stefan Wörz, and MCML PI Nassir Navab.
Ultra-Wide-NeRF reconstructs wide field-of-view 3D ultrasound volumes from overlapping scans acquired with convex probes. It explicitly models how the acoustic beam spreads with depth, which reduces the stitching and aliasing artifacts of conventional methods. It can also generate new views from virtual probe positions. The team validated the method on intracardiac echocardiography data from phantom and porcine experiments, with a view toward improving spatial context during image-guided interventions.
MCML supported the work. Congratulations to the authors on this recognition!
Related
29.10.2026
Teaching Language Models to Express Uncertainty
An ICLR 2026 paper shows how reinforcement learning improves confidence estimates from language models.
27.10.2026
Runner-Up Prize at AutoML 2026 for Tabular-DC-Bench
Tabular-DC-Bench, by MCML Junior Member Mamdouh Aljoud and MCML Director Thomas Seidl, among others, won a runner-up prize at AutoML 2026.
27.10.2026
Welcoming Ewa Szczurek to MCML
Ewa Szczurek joins MCML as Professor of AI in Life Sciences at LMU, focusing on probabilistic and generative models for medicine.
