7 papers
Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception
Jingyun Chen, Fengchun Liu, Linghan Cai +5
Whole-slide visual reasoning requires identifying sparse diagnostic evidence in gigapixel pathology slides and integrating observations across spatial scales. Existing WSI methods…
Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging
Haoxu Huang, Long Chen, Jingyun Chen +8
Brain MRIs are routinely acquired as multiple complementary sequences with unique contrast weighting, including T1-weighed imaging (T1w) anatomic and fluid-sensitive T2-weighted (T…
UAM: A Unified Attention-Mamba Backbone of Multimodal Framework for Tumor Cell Classification
Taixi Chen, Jingyun Chen, Nancy Guo
Inspired by the recent success of the Mamba architecture in vision and language domains, we introduce a Unified Attention-Mamba (UAM) backbone. Unlike previous hybrid approaches th…
PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning
Jingyun Chen, Linghan Cai, Zhikang Wang +5
Analyzing whole-slide images (WSIs) requires an iterative, evidence-driven reasoning process that parallels how pathologists dynamically zoom, refocus, and self-correct while colle…
Federated prediction for scalable and privacy-preserved knowledge-based planning in radiotherapy
Jingyun Chen, David Horowitz, Yading Yuan
Background: Deep learning has potential to improve the efficiency and consistency of radiation therapy planning, but clinical adoption is hindered by the limited model generalizabi…
Decentralized Personalization for Federated Medical Image Segmentation via Gossip Contrastive Mutual Learning
Jingyun Chen, Yading Yuan
Federated Learning (FL) presents a promising avenue for collaborative model training among medical centers, facilitating knowledge exchange without compromising data privacy. Howev…