MorphoITH: A Framework for Deconvolving Intra-Tumor Heterogeneity Using Tissue Morphology

The ability of tumors to evolve and adapt by developing subclones in different genetic and epigenetic states is a major challenge in oncology. Traditional tools like multi-regional sequencing used to study tumor evolution and the resultant intra-tumor heterogeneity (ITH) are often impractical because of their resource-intensiveness and limited scalability. Here, we present MorphoITH, a novel framework that leverages histopathology slides to deconvolve molecular ITH through tissue morphology. MorphoITH integrates a self-supervised deep learning similarity measure to capture phenotypic variation across multiple dimensions (cytology, architecture, and microenvironment) with rigorous methods to eliminate spurious sources of variation. Using a prototype of ITH, clear cell renal cell carcinoma (ccRCC), we show that MorphoITH captures clinically-significant biological features, such as vascular architecture and nuclear grades. Furthermore, we find that MorphoITH recognizes differential biological states corresponding to subclonal changes in key driver genes (BAP1/PBRM1/SETD2). Finally, by applying MorphoITH to a multi-regional sequencing experiment, we postulate evolutionary trajectories that largely recapitulate genetic evolution. In summary, MorphoITH provides a scalable phenotypic lens that bridges the gap between histopathology and genomics, advancing precision oncology.