Articles: Histopathology

Most pathology AI models fail outside the lab. They’re brittle, data-hungry, and take too long to build. But that’s starting to change—thanks to foundation models trained specifically on histology.

AI is revolutionizing many fields, and the analysis of H&E histology is no exception. This classic method, used for over a century by pathologists, has now entered the digital age. It offers new opportunities for AI to assist in diagnostics and research. However, adapting these advances to histology in a point-of-care setting brings new challenges like scarce labeled data and variations across devices and facilities.

Common challenges in machine learning for pathology.

Some of the key components for robust models: quality control, generalizable, and properly validated.

New deep learning technology using H&E images has created an alternative path for molecular diagnostics

Exploring a variety of approaches: stain normalization, color augmentation, adversarial domain adaptation, model adaptation, and finetuning.

Advances in AI applying deep learning to digital pathology images can stratify patients by risk.

A review of machine learning techniques for predicting patient outcomes from whole slide images.

A review of techniques for modeling whole slide histology images and recommendations for different situations.

New advancements in using deep learning to decipher histological signatures

New AI technology using H&E images creates an alternative path for molecular diagnostics

Artificial intelligence finds new insights into molecular tumor properties using a different view – images of cells and tissue.