Computational and Digital Pathology Fellowship Core Educational Areas

Digital Pathology

Fellows have access to a fully operational digital pathology environment, with high-throughput whole slide scanners, advanced image management and analysis software, and integrated clinical workflows. They learn scanner operations and image quality assessment, run quality assurance for digital diagnostic services, and are introduced to the regulatory and compliance requirements for bringing a digital workflow into practice. Graduates leave with the hands-on experience to lead digital transformation at their own institutions.

Computational Pathology

Fellows train in the development, validation, and deployment of machine learning models for histopathologic image analysis. They build foundational skills for image analysis, then progress to designing deep learning models for diagnostic, prognostic, and predictive applications, including large language models and multimodal approaches. Fellows learn to critically evaluate commercial AI solutions and the regulatory frameworks required to bring an algorithm into clinical use. Graduates leave able to bridge the gap between computational scientists and practicing pathologists.

Artificial Intelligence and Machine Learning

Fellows are introduced to the AI methods reshaping pathology, from neural networks and image segmentation to large language models, generative AI, foundation models, vision-language models, and multimodal integration. Training pairs hands-on model building with the methods needed to validate performance and the regulatory considerations for clinical implementation. Graduates leave able to build, evaluate, and explain AI tools with credibility to both clinicians and computational scientists.

Pathology Informatics

Fellows gain working knowledge of laboratory information systems, image management platforms, and data infrastructure to support their computational and digital work. Training covers how digital pathology integrates with existing clinical systems and how data moves from scanner to storage to analysis.

Clinical Image Analysis

Fellows learn to apply quantitative image analysis to the questions that matter in cancer diagnostics, from biomarker scoring and tumor grading to prognostic and predictive assessment. Training covers morphometrics, image segmentation, and object detection, and extends to multiplex immunofluorescence and spatial transcriptomics for comprehensive tissue analysis. Graduates leave able to design, validate, and interpret image analysis studies with clinical rigor.

Precision Oncology

Fellows learn how AI-derived biomarkers, spatial transcriptomics, and molecular data combine to refine diagnosis, predict treatment response, and support patient stratification for clinical trials. Through collaborative efforts, fellows witness how computational findings translate into actual treatment decisions for individual patients. Graduates leave positioned to drive the integration of computational tools into precision cancer care.