Open research software by Faramarz Kowsari

Computational Pathology AI Lab

From CNN Baselines to Foundation Models, Explainable AI, and Production MLOps

View source Software DOI Companion book
Research and educational use only. This project is not a medical device and has not been clinically validated.

Project overview

Computational Pathology AI Lab is a production-oriented, research-first platform for histopathology image analysis, cancer-detection research, explainable deep learning, uncertainty estimation, whole-slide workflows, model evaluation, and reproducible MLOps. It began as a University of Colorado Boulder graduate-course project and has been expanded into a maintainable engineering and academic portfolio.

Four professional pillars

Medical AI Research

Leakage controls, calibration, uncertainty, confidence intervals, error analysis, domain shifts, and external-validation readiness.

ML Engineering and MLOps

Typed Python package, tests, CI, Docker, DVC, MLflow hooks, model-registry structure, API serving, and monitoring.

Computer Vision Engineering

CNNs, transfer learning, Vision Transformers, foundation-model adapters, tissue patches, WSI utilities, MIL, and explainability.

Academic Teaching and Authorship

Teaching notebooks, methodology, model and data cards, research questions, a technical report, and a companion book.

Permanent identifiers

Software — all versions

10.5281/zenodo.21445854

Archived software — version 1.0.0

10.5281/zenodo.21445855

Companion book

10.5281/zenodo.21444837
GGKEY:8ZWNQ7NFGBL

Evidence status

CPU smoke tests, synthetic-data workflows, automated tests, CI, Docker build, and GitHub Pages deployment are operational. Real histopathology benchmarks, external validation, foundation-model comparisons, and clinical validation are explicitly Not Yet Benchmarked or Not Performed.

Companion book

Computational Pathology Engineering
From Histology Patches and CNNs to Whole-Slide Foundation Models, Explainable AI, and Production MLOps
Author: Faramarz Kowsari
DOI: 10.5281/zenodo.21444837
Google Books Key: GGKEY:8ZWNQ7NFGBL

About the author

Faramarz Kowsari

Faramarz Kowsari

Faramarz Kowsari is an author, Software Engineer and AI researcher based in Istanbul. Focusing on the intersection of technology, education, and personal growth, he has published over 80 digital titles on international platforms. His areas of expertise span Artificial Intelligence, prompt engineering, modern trading strategies (Smart Money Concepts & algorithmic trading), as well as classical literature and mindfulness. In addition to writing, he develops web-based educational tools and creates specialized instructional video content.

Official Profiles & Repositories