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

By Yu Fu, Alexander W. Jung, Ramón Viñas Torné, Santiago Gonzalez, Harald S. Vöhringer, Artem Shmatko, L. Yates, M. Jimenez-Linan, L. Moore, Moritz Gerstung. Nature Cancer, 2019

596 citations recorded by the source corpus.

We use deep transfer learning to quantify histopathological patterns across 17,355 hematoxylin and eosin-stained histopathology slide images from 28 cancer types and correlate these with matched genomic, transcriptomic and survival data. This approach accurately classifies cancer types and provides spatially resolved tumor and normal tissue distinction. Automatically learned computational histopathological features correlate with a large range of recurrent genetic aberrations across cancer types. This includes whole-genome duplications, which display universal features across cancer types, individual chromosomal aneuploidies, focal amplifications and deletions, as well as driver gene mutations. There are widespread associations between bulk gene expression levels and histopathology, which reflect tumor composition and enable the localization of transcriptomically defined tumor-infiltrating lymphocytes. Computational histopathology augments prognosis based on histopathological subtyping and grading, and highlights prognostically relevant areas such as necrosis or lymphocytic aggregates. These findings show the remarkable potential of computer vision in characterizing the molecular basis of tumor histopathology. Two papers by Kather and colleagues and Gerstung and colleagues develop workflows to predict a wide range of molecular alterations from pan-cancer digital pathology slides.

Subfields: Artificial Intelligence, Cancer Research, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/611759b0a8d8d05907e316b1ed3e9d52625b1562

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cancer Research

Moritz Gerstung

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Artificial intelligence in drug development (2025, unknown): “Robust validation and responsible data curation will facilitate biomarker identification and application, supporting future drug development and disease treatment.”
Clinical-grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning. (2020, result): “In contrast, computerbased image analysis by deep learning has enabled robust detection of MSI and dMMR status directly from routine H&E histology: we recently presented(16) and later refined(17) such a deep learning assay, which was independently validated by 2 other groups.(18,19) However, all of ”
Artificial intelligence for digital and computational pathology (2023, unknown): “Saliency maps, attention maps, etc.”
AI in health and medicine (2022, background): “Furthermore, AI has been shown to make more accurate survival predictions for a wide range of cancer types compared to conventional grading and histopathological subtyping 31 .”
Deep learning in cancer pathology: a new generation of clinical biomarkers (2020, unknown): “40 However, these studies have been largely based on one particular dataset, “ The Cancer Genome Atlas (TCGA) ” , provided by the National Cancer Institute (NCI), and so large-scale validation in genomically characterised cohorts beyond TCGA is needed to gauge the robustness of these methods in…”
A whole-slide foundation model for digital pathology from real-world data (2024, unknown): “Given the overall utility of pathology images in assigning tumour sub-types 2,9,10,49 , we next examined whether Prov-GigaPath can accurately predict cancer subtypes from images.”
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology (2022, methodology): “Some studies have employed a pan-cancer approach, training AI models to predict survival in multiple tumor types using end-to-end 39 or transfer learning 19 .”