8 papers
DeepSparse: A Foundation Model for Sparse-View CBCT Reconstruction
Yiqun Lin, Jixiang Chen, Hualiang Wang +4
Cone-beam computed tomography (CBCT) is a critical 3D imaging technology in the medical field, while the high radiation exposure required for high-quality imaging raises significan…
Forgetting-Resistant and Lesion-Aware Source-Free Domain Adaptive Fundus Image Analysis with Vision-Language Model
Zheang Huai, Hui Tang, Hualiang Wang +1
Source-free domain adaptation (SFDA) aims to adapt a model trained in the source domain to perform well in the target domain, with only unlabeled target domain data and the source…
Cross-view Generalized Diffusion Model for Sparse-view CT Reconstruction
Jixiang Chen, Yiqun Lin, Yi Qin +2
Sparse-view computed tomography (CT) reduces radiation exposure by subsampling projection views, but conventional reconstruction methods produce severe streak artifacts with unders…
VAMPIRE: Uncovering Vessel Directional and Morphological Information from OCTA Images for Cardiovascular Disease Risk Factor Prediction
Lehan Wang, Hualiang Wang, Chubin Ou +3
Cardiovascular disease (CVD) remains the leading cause of death worldwide, requiring urgent development of effective risk assessment methods for timely intervention. While current…
MedGround-R1: Advancing Medical Image Grounding via Spatial-Semantic Rewarded Group Relative Policy Optimization
Huihui Xu, Yuanpeng Nie, Hualiang Wang +9
Medical Image Grounding (MIG), which involves localizing specific regions in medical images based on textual descriptions, requires models to not only perceive regions but also ded…
Token Activation Map to Visually Explain Multimodal LLMs
Yi Li, Hualiang Wang, Xinpeng Ding +2
Multimodal large language models (MLLMs) are broadly empowering various fields. Despite their advancements, the explainability of MLLMs remains less explored, hindering deeper unde…