Classifying non-small cell lung cancer types and transcriptomic subtypes using convolutional neural networks

• Published in: Journal of the American Medical Informatics Association : JAMIA Vol. 27; no. 5; pp. 757 - 769
• Main Authors: Yu, Kun-Hsing, Wang, Feiran, Berry, Gerald J, Ré, Christopher, Altman, Russ B, Snyder, Michael, Kohane, Isaac S
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 01.05.2020
• Subjects: Adenocarcinoma of Lung - genetics; Adenocarcinoma of Lung - pathology; Carcinoma, Non-Small-Cell Lung - genetics; Carcinoma, Non-Small-Cell Lung - pathology; Carcinoma, Squamous Cell - genetics; Carcinoma, Squamous Cell - pathology; Humans; Lung Neoplasms - genetics; Lung Neoplasms - pathology; Machine Learning; Neural Networks, Computer; Research and Applications; ROC Curve; Transcriptome; non-small cell lung cancer; quantitative pathology; convolutional neural networks; machine learning; transcriptomic subtypes
• DOI: 10.1093/jamia/ocz230
• ISSN: 1527-974X; 1067-5027

Abstract Objective Non-small cell lung cancer is a leading cause of cancer death worldwide, and histopathological evaluation plays the primary role in its diagnosis. However, the morphological patterns associated with the molecular subtypes have not been systematically studied. To bridge this gap, we developed a quantitative histopathology analytic framework to identify the types and gene expression subtypes of non-small cell lung cancer objectively. Materials and Methods We processed whole-slide histopathology images of lung adenocarcinoma (n = 427) and lung squamous cell carcinoma patients (n = 457) in the Cancer Genome Atlas. We built convolutional neural networks to classify histopathology images, evaluated their performance by the areas under the receiver-operating characteristic curves (AUCs), and validated the results in an independent cohort (n = 125). Results To establish neural networks for quantitative image analyses, we first built convolutional neural network models to identify tumor regions from adjacent dense benign tissues (AUCs > 0.935) and recapitulated expert pathologists’ diagnosis (AUCs > 0.877), with the results validated in an independent cohort (AUCs = 0.726-0.864). We further demonstrated that quantitative histopathology morphology features identified the major transcriptomic subtypes of both adenocarcinoma and squamous cell carcinoma (P < .01). Discussion Our study is the first to classify the transcriptomic subtypes of non-small cell lung cancer using fully automated machine learning methods. Our approach does not rely on prior pathology knowledge and can discover novel clinically relevant histopathology patterns objectively. The developed procedure is generalizable to other tumor types or diseases.