Lin Yang

Lin Yang is a Researcher in the Department of Neuroscience at the Yale School of Medicine. Their work focuses on advancing medical imaging technologies through machine learning, particularly in domains like liver tumor treatment response prediction, cross-modality segmentation, and domain adaptation in clinical imaging. Yang's research bridges deep learning methodologies with clinical applications, addressing challenges in radiology and oncology through innovative algorithms.

Research interests include medical image segmentation, domain adaptation for cross-modality analysis, and uncertainty quantification in diagnostic imaging. Yang has contributed to improving the accuracy of liver tumor segmentation in cone-beam CT, predicting treatment outcomes for hepatocellular carcinoma, and developing robust models for unsupervised domain adaptation. Their work often emphasizes practical clinical applications, such as enhancing decision-making in interventional radiology and oncology.

Publications highlight trends in leveraging generative models for semantic segmentation, improving domain generalization in neural networks, and applying invertible networks for explainable AI. While no awards are explicitly mentioned, their contributions to the 2018 Robotic Scene Segmentation Challenge and cross-modality liver segmentation research demonstrate significant impact in medical AI.

Yang collaborates with clinical teams to advance translational research, focusing on real-world challenges in image-based diagnosis and treatment planning. Current work includes optimizing AI tools for liver disease assessment and improving the interpretability of medical imaging algorithms.