activity
20172026
most citedUnsupervised End-to-end Learning for Deformable Medical Image Registration

38 citations · 40 across the 16 of their papers we have counts for

collaborators
Showing cs.CVShow all

12 papers · 1 filter

cs.CV2026

Causal-Adversarial Probing of Clinical Covariates for Prostate MRI Grading

Yipei Wang, Shiqi Huang, Wen Yan +6

Deep learning models for prostate MRI-based cancer grading may encode clinical covariates that either reflect useful disease-related signal or non-generalising shortcut information…

cs.CV2026

Maximizing T2-Only Prostate Cancer Localization from Expected Diffusion Weighted Imaging

Weixi Yi, Yipei Wang, Wen Yan +10

Multiparametric MRI is increasingly recommended as a first-line noninvasive approach to detect and localize prostate cancer, requiring at minimum diffusion-weighted (DWI) and T2-we…

cs.CV2026

ProFound: A moderate-sized vision foundation model for multi-task prostate imaging

Yipei Wang, Yinsong Xu, Weixi Yi +11

Many diagnostic and therapeutic clinical tasks for prostate cancer increasingly rely on multi-parametric MRI. Automating these tasks is challenging because they necessitate expert…

cs.CV2026

Flow Matching-enabled Test-Time Refinement for Unsupervised Cardiac MR Registration

Yunguan Fu, Wenjia Bai, Wen Yan +3

Diffusion-based unsupervised image registration has been explored for cardiac cine MR, but expensive multi-step inference limits practical use. We propose FlowReg, a flow-matching…

cs.CV2026

Deep EM with Hierarchical Latent Label Modelling for Multi-Site Prostate Lesion Segmentation

Wen Yan, Yipei Wang, Shiqi Huang +5

Label variability is a major challenge for prostate lesion segmentation. In multi-site datasets, annotations often reflect centre-specific contouring protocols, causing segmentatio…

cs.CV2025

Impact of Clinical Image Quality on Efficient Foundation Model Finetuning

Yucheng Tang, Pawel Rajwa, Alexander Ng +11

Foundation models in medical imaging have shown promising label efficiency, achieving high performance on downstream tasks using only a fraction of the annotated data otherwise req…