Pan-cancer computational histopathology reveals mutations, tumor composition and prognosis

Abstract

Key points• Pan-cancer computational histopathology analysis with deep learning extracts histopathological patterns and accurately discriminates 28 cancer and 14 normal tissue types • Computational histopathology predicts whole genome duplications, focal amplifications and deletions, as well as driver gene mutations • Wide-spread correlations with gene expression indicative of immune infiltration and proliferation • Prognostic information augments conventional grading and histopathology subtyping in the majority of cancers AbstractHere we use deep transfer learning to quantify histopathological patterns across 17,396 H&E stained histopathology image slides from 28 cancer types and correlate these with underlying genomic and transcriptomic data. Pan-cancer computational histopathology (PC-CHiP) classifies the tissue origin across organ sites and provides highly accurate, spatially resolved tumor and normal distinction within a given slide. The learned computational histopathological features correlate with a large range of recurrent genetic aberrations, including whole genome duplications (WGDs), arm-level copy number gains and losses, focal amplifications and deletions as well as driver gene mutations within a range of cancer types. WGDs can be predicted in 25/27 cancer types (mean AUC=0.79) including those that were not part of model training. Similarly, we observe associations with 25% of mRNA transcript levels, which enables to learn and localise histopathological patterns of molecularly defined cell types on each slide. Lastly, we find that computational histopathology provides prognostic information augmenting histopathological subtyping and grading in the majority of cancers assessed, which pinpoints prognostically relevant areas such as necrosis or infiltrating lymphocytes on each tumour section. Taken together, these findings highlight the large potential of PC-CHiP to discover new molecular and prognostic associations, which can augment diagnostic workflows and lay out a rationale for integrating molecular and histopathological data.

Interpretable deep learning of label-free live cell images uncovers functional hallmarks of highly-metastatic melanoma

“…Recent advances in medical imaging explicitly identified local image sub-regions that determine the training of classifier deep neural networks (Courtiol et al, 2019;Fu et al, 2019;Pan et al, 2019;Shamai et al, 2019). Localization of sub-regions that were particularly important for the classifier result permitted a visual assessment and pathological interpretation of distinctive image properties.…”

Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images

“…While other recent works have investigated image-based cancer classification (Fu et al 2019;Kather et al 2019), cross-classification has until now been little studied. Comparisons of classifiers support the existence of morphological features shared across cancer types, as many cross-cancer predictors achieve high AUCs.…”

“…It is worth noting that such analyses would not be possible without mixtures of tumor and normal regions together within images. Thus it will be important to analyze regions with spatial diversity rather than only regions of high purity, which has been the focus of some recent works (Fu et al 2019). Finally, the field would be advanced if fine-grained spatial pathological annotations can be generated at scale by the community, e.g.…”

Histopathological Landscape of Molecular Genetics and Clinical Determinants in MDS Patients

“…Here, we demonstrate how the intricate and heterogeneous BM morphological landscape can be decomposed and associated with clinical data using multilevel computer vision. Remarkably, highest prediction accuracy of deep BM morphology was noted for mutation and cytogenetic aberrations, which even outweighed reported inference in solid tumors 5,9,17,18 . We suspect homogenous BM tissue consistency and lower mutation burden of MDS to account for the improved results.…”