Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning
- 17 September 2018
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Medicine
- Vol. 24 (10), 1559-1567
- https://doi.org/10.1038/s41591-018-0177-5
Abstract
Visual inspection of histopathology slides is one of the main methods used by pathologists to assess the stage, type and subtype of lung tumors. Adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) are the most prevalent subtypes of lung cancer, and their distinction requires visual inspection by an experienced pathologist. In this study, we trained a deep convolutional neural network (inception v3) on whole-slide images obtained from The Cancer Genome Atlas to accurately and automatically classify them into LUAD, LUSC or normal lung tissue. The performance of our method is comparable to that of pathologists, with an average area under the curve (AUC) of 0.97. Our model was validated on independent datasets of frozen tissues, formalin-fixed paraffin-embedded tissues and biopsies. Furthermore, we trained the network to predict the ten most commonly mutated genes in LUAD. We found that six of them—STK11, EGFR, FAT1, SETBP1, KRAS and TP53—can be predicted from pathology images, with AUCs from 0.733 to 0.856 as measured on a held-out population. These findings suggest that deep-learning models can assist pathologists in the detection of cancer subtype or gene mutations. Our approach can be applied to any cancer type, and the code is available at https://github.com/ncoudray/DeepPATH.This publication has 67 references indexed in Scilit:
- Mutation incidence and coincidence in non small-cell lung cancer: meta-analyses by ethnicity and histology (mutMap)Annals of Oncology, 2013
- LKB1 Inactivation Dictates Therapeutic Response of Non-Small Cell Lung Cancer to the Metabolism Drug PhenforminCancer Cell, 2013
- Comprehensive genomic characterization of squamous cell lung cancersNature, 2012
- Standardization of Epidermal Growth Factor Receptor (EGFR) Measurement by Quantitative Immunofluorescence and Impact on Antibody-Based Mutation Detection in Non–Small Cell Lung CancerThe American Journal of Pathology, 2011
- Genotypic and Histological Evolution of Lung Cancers Acquiring Resistance to EGFR InhibitorsScience Translational Medicine, 2011
- Unique Clinicopathologic Features Characterize ALK-Rearranged Lung Adenocarcinoma in the Western PopulationClinical Cancer Research, 2009
- Mutation-Specific Antibodies for the Detection of EGFR Mutations in Non–Small-Cell Lung CancerClinical Cancer Research, 2009
- Role of LKB1 in lung cancer developmentBritish Journal of Cancer, 2008
- Determinants of Tumor Response and Survival With Erlotinib in Patients With Non—Small-Cell Lung CancerJournal of Clinical Oncology, 2004
- A Coefficient of Agreement for Nominal ScalesEducational and Psychological Measurement, 1960