13 papers
Operational digital twin clinics enable task-based evaluation of embodied AI
Xinyuan Wu, Jingrao Zhang, Mengdi Xu +3
Embodied artificial intelligence (AI) must be tested in the clinical environments where it will operate, but building realistic, robot-testable settings is costly and difficult to…
EyeWorld: A Generative World Model of Ocular State and Dynamics
Ziyu Gao, Xinyuan Wu, Xiaolan Chen +10
Ophthalmic decision-making depends on subtle lesion-scale cues interpreted across multimodal imaging and over time, yet most medical foundation models remain static and degrade und…
EyeAgent: An Agentic AI System for Multimodal Clinical Decision Support in Ophthalmology
Danli Shi, Xiaolan Chen, Bingjie Yan +24
Artificial intelligence has shown promise in medical imaging, yet most existing systems lack flexibility, interpretability, and adaptability - challenges especially pronounced in o…
APTOS-2024 challenge report: Generation of synthetic 3D OCT images from fundus photographs
Bowen Liu, Weiyi Zhang, Peranut Chotcomwongse +23
Optical Coherence Tomography (OCT) provides high-resolution, 3D, and non-invasive visualization of retinal layers in vivo, serving as a critical tool for lesion localization and di…
ChatMyopia: An AI Agent for Pre-consultation Education in Primary Eye Care Settings
Yue Wu, Xiaolan Chen, Weiyi Zhang +7
Large language models (LLMs) show promise for tailored healthcare communication but face challenges in interpretability and multi-task integration particularly for domain-specific…
Benchmarking Large Multimodal Models for Ophthalmic Visual Question Answering with OphthalWeChat
Pusheng Xu, Xia Gong, Xiaolan Chen +7
Purpose: To develop a bilingual multimodal visual question answering (VQA) benchmark for evaluating VLMs in ophthalmology. Methods: Ophthalmic image posts and associated captions p…