A multimodal generative AI copilot for human pathology

This paper introduces PathChat, a vision-language AI assistant for human pathology. PathChat leverages a foundational vision encoder, a large language model, and a substantial visual-language instruction dataset for fine-tuning. Evaluations demonstrate state-of-the-art performance on multiple-choice diagnostic questions and superior performance in generating pathologist-preferred responses to open-ended queries compared to several other multimodal AI assistants and GPT-4. PathChat shows promise for applications in pathology education, research, and clinical decision-making.

Ming Y. Lu, Bowen Chen, Drew F. K. Williamson, Richard J. Chen, Melissa Zhao, Aaron K. Chow, Kenji Ikemura, Ahrong Kim, Dimitra Pouli, Ankush Patel, Amr Soliman, Chengkuan Chen, Tong Ding, Judy J. Wang, Georg Gerber, Ivy Liang, Long Phi Le, Anil V. Parwani, Luca L. Weishaupt, Faisal Mahmood