This interdisciplinary course introduces the fundamentals of computational pathology, AI-based image analysis, and the deployment of advanced models to address real-world challenges in pathology. Students will begin by exploring pathology slide types, digital workflows, color image representation, basic image processing techniques, and common analytical hurdles. The course then surveys key deep learning methods, including convolutional neural networks, transformer architectures, and large language models as applied to pathology imaging. Finally, students will examine AI-driven tools that enhance diagnostic workflows and discuss ethical and technical considerations such as data requirements, storage needs, computational planning, and human-in-the-loop integration for responsible AI adoption in clinical practice.
1 units · Medical Satisfactory/No Credit
This interdisciplinary course introduces the fundamentals of computational pathology, AI-based image analysis, and the deployment of advanced models to address real-world challenges in pathology. Students will begin by exploring pathology slide types, digital workflows, color image representation, basic image processing techniques, and common analytical hurdles. The course then surveys key deep learning methods, including convolutional neural networks, transformer architectures, and large language models as applied to pathology imaging. Finally, students will examine AI-driven tools that enhance diagnostic workflows and discuss ethical and technical considerations such as data requirements, storage needs, computational planning, and human-in-the-loop integration for responsible AI adoption in clinical practice.
Offered in Autumn 2026 at Stanford University.