Visual in-context learning (ICL) enables medical image segmentation models to adapt to new tasks using only a small set of annotated support images, without additional model fine-tuning. This makes visual ICL promising for clinical deployment, yet a fundamental limitation remains. Current ICL models lack the intrinsic...
Tiana-Tian-Ying Chen, Liang-Li Zhen, Yan-Yu Xu et al.· IEEE Transactions on Medical...· 0 citations
Whole-slide image (WSI) reasoning requires an agent to sequentially acquire visual evidence before answering a diagnostic question. Existing training-free agentic frameworks formulate this process as iterative patch retrieval based on semantic relevance to the question. However, semantic relevance does not necessarily...
Ultra-low-dose computed tomography (ULDCT) reduces radiation exposure but suffers from severe noise that degrades diagnostic image quality. Existing deep learning-based denoising methods are typically trained in an organ-specific fashion, resulting in limited generalization across heterogeneous multi?organ imaging scen...
Bao-Shun Shi, Shuang-Yi Yang, Ke Jiang et al.· 0 citations
AdaFusion is presented, a lightweight adaptive fusion framework that integrates complementary signals from multiple frozen PFMs through low-dimensional feature compression and a sample-conditioned gating module that reweights model-wise (and optionally channel-wise) contributions.
Yu Xiao, Yang Hu, Bin Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
