News

[Nature Communications] A Large Model for Non-invasive and Personalized Management of Breast Cancer from Multiparametric MRI

HKUST's Smart Lab, in collaboration with leading institutions, has developed a groundbreaking mpMRI-based model for personalized breast cancer management, now published in Nature Communications.

Last updated on 2025/04/21

[Nature Biomedical Engineering] Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation

See our latest work on pathology foundation model GPFM, which distills knowledge from multiple expert models and achieves the best average rank of 1.6 across 72 diverse clinical tasks.

Last updated on 2024/07/30

A Multimodal Knowledge-Enhanced Whole-Slide Pathology Foundation Model: A New Pathology Pretraining Paradigm

See our latest work on pathology foundation model mSTAR, which leverages multimodal knowledge to enhance these models while achieving whole-slide-level pretraining.

Last updated on 2024/07/31

[MICCAI 2024 Paper] Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspective

Our paper titled 'Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspective' has been accepted by MICCAI 2024.

Last updated on 2024/07/27

[MICCAI 2024 Paper & HKUST CSE Best FYP] Aligning Medical Image Analysis Tasks with General Knowledge from Large Language Models

A study on medical vision-language models by HKUST Smart Lab has been accepted for publication at MICCAI 2024. This paper has been awarded the 2024 Best Final Year Project (CSE Best FYP Award) by the Department of Computer Science and Engineering at Hong Kong University of Science and Technology. Congratulations to the authors!

Last updated on 2024/07/26