Compositional and interpretable representation of histology using AI foundation models and sparse autoencoders
Ziyuan Zhao, Zoltan Maliga, Emmanuel C. Ogbonna, Soheil Rastgou Talemi, Shannon Coy, Andréanne Gagné, Kapongo D. Lumamba, Isaac H. Solomon, Sandro Santagata, Adrie J. C. Steyn, Threnesan Naidoo, Peter Karl Sorger
This paper introduces a human-in-the-loop framework using AI foundation models and sparse autoencoders to interpret H&E histology images and integrate them with molecular spatial profiling.
bioRxiv · Jun 6, 2026 · PreprintBioinformatics