Articles

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.

Artificial intelligence relies heavily on algorithms – a set of computer instructions to accomplish a task. But the power actually comes from the data. Here’s why.

To recognize the advantages of AI tools and rely on their results in your everyday work, you need to understand how these tools are developed for pathology. With this understanding, you can make informed decisions about their use.

Four reasons why you might need to build your own computer vision solution.

Large vision models may seem attractive, but domain-specific models can get you farther.

A reading list for anyone looking to adapt their machine learning expertise to computational pathology.

The benefits of a self-supervised vision model for generalizability, adaptability, and more.

Machine learning projects are complex and iterative with uncertain outcomes. These are some ways to improve the efficacy of ML development.

The episodes that I highlight below are the 10 most downloaded. The common themes are food and disease: farming, climate risks, food waste, cancer, and medical imaging.

Common challenges in machine learning for pathology.

The core components to successful machine learning project.

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