activity
20242026
most citedT2-Only Prostate Cancer Prediction by Meta-Learning from Bi-Parametric MR Imaging

1 citations · 1 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CV2026

Understanding the Transfer Limits of Vision Foundation Models

Shiqi Huang, Yipei Wang, Natasha Thorley +8

Foundation models leverage large-scale pretraining to capture extensive knowledge, demonstrating generalization in a wide range of language tasks. By comparison, vision foundation…

cs.CV2025

Learning to learn skill assessment for fetal ultrasound scanning

Yipei Wang, Qianye Yang, Lior Drukker +3

Traditionally, ultrasound skill assessment has relied on expert supervision and feedback, a process known for its subjectivity and time-intensive nature. Previous works on quantita…

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…

cs.CV2025

Policy to Assist Iteratively Local Segmentation: Optimising Modality and Location Selection for Prostate Cancer Localisation

Xiangcen Wu, Shaheer U. Saeed, Yipei Wang +2

Radiologists often mix medical image reading strategies, including inspection of individual modalities and local image regions, using information at different locations from differ…

cs.CV2025

Analysis of Image-and-Text Uncertainty Propagation in Multimodal Large Language Models with Cardiac MR-Based Applications

Yucheng Tang, Yunguan Fu, Weixi Yi +4

Multimodal large language models (MLLMs) can process and integrate information from multimodality sources, such as text and images. However, interrelationship among input modalitie…

eess.IV2025

Promptable cancer segmentation using minimal expert-curated data

Lynn Karam, Yipei Wang, Veeru Kasivisvanathan +3

Automated segmentation of cancer on medical images can aid targeted diagnostic and therapeutic procedures. However, its adoption is limited by the high cost of expert annotations r…