Pan-cancer image-based detection of clinically actionable genetic alterations
| Autor: | Peter Boor, Chiara Loeffler, Akash Patnaik, Heike I. Grabsch, Jefree J. Schulte, Piet A. van den Brandt, Kai A. J. Sommer, Alexander T. Pearson, Loes F. S. Kooreman, Lara R. Heij, Jakob Nikolas Kather, Amelie Echle, Nadina Ortiz-Brüchle, Jan M. Niehues, Andrew Srisuwananukorn, Hermann Brenner, Nicole A. Cipriani, Andrew M. Hanby, Peter Bankhead, Hannah Sophie Muti, Sara Kochanny, Valerie Speirs, Roman D. Buelow, Jeremias Krause, Michael Hoffmeister, Tom Luedde, Dirk Jäger, Christian Trautwein |
|---|---|
| Přispěvatelé: | RS: NUTRIM - R2 - Liver and digestive health, MUMC+: DA Pat AIOS (9), Pathologie, RS: GROW - R2 - Basic and Translational Cancer Biology, MUMC+: DA Pat Pathologie (9), Epidemiologie, RS: GROW - R1 - Prevention |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Cancer Research
medicine.medical_specialty H&E stain Computational biology Biology Article COLORECTAL-CANCER SUBTYPES 03 medical and health sciences Deep Learning 0302 clinical medicine Neoplasms medicine Humans HEAD Hematoxylin 030304 developmental biology 0303 health sciences Pan cancer MUTATIONS Spatially resolved fungi Cancer food and beverages Histology medicine.disease COMPREHENSIVE MOLECULAR CHARACTERIZATION 3. Good health Cancer treatment GENOMIC CHARACTERIZATION Oncology 030220 oncology & carcinogenesis Mutation Eosine Yellowish-(YS) Histopathology Image based |
| Zdroj: | Nature Cancer, 1(8), 789-799. Nature Publishing Group Nat Cancer Nature Cancer Kather, J N, Heij, L R, Grabsch, H, Loeffler, C, Echle, A, Muti, H S, Krause, J, Niehues, J M, Sommer, K A J, Bankhead, P, Kooreman, L F S, Schulte, J J, Cipriani, N A, Buelow, R D, Boor, P, Ortiz-Bruchle, N, Hanby, A M, Speirs, V, Kochanny, S, Patnaik, A, Srisuwananukorn, A, Brenner, H, Hoffmeister, M, Brandt, P A V D, Jäger, D, Trautwein, C, Pearson, A T & Luedde, T 2020, ' Pan-cancer image-based detection of clinically actionable genetic alterations ', nature cancer, vol. 1, no. 8, pp. 789–799 . https://doi.org/10.1038/s43018-020-0087-6 |
| ISSN: | 2662-1347 |
| DOI: | 10.1038/s43018-020-0087-6 |
| Popis: | Molecular alterations in cancer can cause phenotypic changes in tumor cells and their microenvironment. Routine histopathology tissue slides, which are ubiquitously available, can reflect such morphological changes. Here, we show that deep learning can consistently infer a wide range of genetic mutations, molecular tumor subtypes, gene expression signatures and standard pathology biomarkers directly from routine histology. We developed, optimized, validated and publicly released a one-stop-shop workflow and applied it to tissue slides of more than 5,000 patients across multiple solid tumors. Our findings show that a single deep learning algorithm can be trained to predict a wide range of molecular alterations from routine, paraffin-embedded histology slides stained with hematoxylin and eosin. These predictions generalize to other populations and are spatially resolved. Our method can be implemented on mobile hardware, potentially enabling point-of-care diagnostics for personalized cancer treatment. More generally, this approach could elucidate and quantify genotype-phenotype links in cancer. 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink