Uncertainty for Safe Utilization of Machine Learning in Medical Imaging

7th International Workshop, UNSURE 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 27, 2025, Proceedings
Herausgegeben:Sudre, Carole H.; Hoque, Mobarak I.; Mehta, Raghav; Ouyang, Cheng; Qin, Chen; Rakic, Marianne; Wells, William M.

• Broschiertes Buch

Produktbeschreibung

This book constitutes the refereed proceedings of the 7th Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, UNSURE 2025, held in conjunction with MICCAI 2025, in Daejon, South Korea, on September 27, 2025.

The 22 full papers included in this book were carefully reviewed and selected from 33 submissions. They were organized in topical sections as follows: Risk management, uncertainty interpretation and visualisation; domain shift and out-of-distribution management; uncertainty calibration; and uncertainty modelling and estimation, Bayesian deep learning.

Produktdetails

• Lecture Notes in Computer Science 16166
• Verlag: Springer / Springer Nature Switzerland / Springer, Berlin
• Artikelnr. des Verlages: 89577975, 978-3-032-06592-6
• Seitenzahl: 260
• Erscheinungstermin: 29. September 2025
• Englisch
• Abmessung: 235mm x 155mm x 15mm
• Gewicht: 400g
• ISBN-13: 9783032065926
• ISBN-10: 3032065925
• Artikelnr.: 75242478

Inhaltsangabe

.- Risk management, Uncertainty interpretation and visualisation
.- MEGAN: Mixture of Experts for Robust Uncertainty Estimation in Endoscopy Videos.
.- Unsupervised Artifact Detection and Quantification via Contrastive Learning with Noise Reference.

.-Disagreement-Driven Uncertainty Quantification in Late Gadolinium
Enhancement Cardiac MRI.

.- Is Uncertainty Quantification a Viable Alternative to Learned Deferral?.
.- Evaluation of Uncertainty-Aware Multi-Software Ensembles for Hippocampal Segmentation.
.- Numerical Uncertainty in Linear Registration: An Experimental Study.
.- Domain shift and out-of-distribution management
.- SPARTA: Spectral Prompt Agnostic Adversarial Attack on Medical Vision-Language Models.
.- Label-free estimation of clinically relevant performance metrics under distribution shifts.
.- Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories.
.- SCORPION: Addressing Scanner-Induced Variability in Histopathology.
.- LEXU: Learning from Expert Disagreement for Single-Pass Uncertainty Estimation in Medical Image Segmentation.
.- Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift.
.- Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching.
.- Uncertainty Calibration
.- Multi-Rater Calibration Error Estimation.
.- Pseudo-D: Informing Multi-View Uncertainty Estimation with Calibrated Neural Training Dynamics.
.- Metric-Guided Conformal Bounds for Probabilistic Image Reconstruction.
.- Evaluation of Monte Carlo Dropout for Uncertainty Quantification in Multi-task Deep Learning-Based Glioma Subtyping.
.- Uncertainty modelling and estimation, Bayesian deep learning
.- Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification.
.- Uncertainty-Aware Classification: A Human-Guided Bayesian Deep Learning Framework.
.- Empirical Bayesian Methods and BNNs for Medical OOD Detection.
.- A Proper Structured Prior for Bayesian T1 Mapping.
.- Bayesian MRI Reconstruction with Structured Uncertainty Distributions.