AI-Assisted Pathology

Some researchers say that deep-learning ‘foundation’ models will revolutionize the field — but others are not so sure.

The authors of this Perspective evaluate the developments in the use of artificial intelligence (AI) in digital pathology for oncology applications between 2019 and 2024, addressing technological innovations, regulatory trends, implementation and financial implications. Importantly, they explore the current landscape of clinical deployment, highlighting future opportunities for the integration of AI into clinical oncology routine practice.

PathChat, a multimodal generative AI copilot for human pathology, has been trained on a large dataset of visual-language instructions to interactively assist users with diverse pathology tasks.

This Review provides an introductory guide to artificial intelligence (AI)-based tools for non-computational cancer researchers. Here, Perez-Lopez et al. outline the general principles of AI for image analysis, natural language processing and drug discovery, as well as how researchers can get started with each of them.

Advances in digitizing human tissue slides and progress in artificial intelligence have boosted progress in the field of computational pathology. This Review consolidates recent methodological advances and provides future perspectives as the field expands to take on a broader range of clinical and research tasks.

Optimized AI models could transform cancer diagnostics, providing clinicians with faster, greener, and more precise tools for more informed treatment decisions.