Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks

• Published in: Scientific reports Vol. 9; no. 1; p. 3358
• Main Authors: Wei, Jason W., Tafe, Laura J., Linnik, Yevgeniy A., Vaickus, Louis J., Tomita, Naofumi, Hassanpour, Saeed
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 04.03.2019; Nature Publishing Group
• Subjects: 14/63; 631/114/1305; 631/114/1564; 692/4028/67/1612/1350; Adenocarcinoma; Adenocarcinoma of Lung - classification; Adenocarcinoma of Lung - pathology; Adenocarcinoma of Lung - surgery; Automation; Classification; Deep Learning; Histological Techniques - methods; Humanities and Social Sciences; Humans; Lung cancer; Lung Neoplasms - classification; Lung Neoplasms - pathology; Lungs; multidisciplinary; Neural networks; Neural Networks, Computer; Pathologists; Science; Science (multidisciplinary)
• DOI: 10.1038/s41598-019-40041-7
• ISSN: 2045-2322

Classification of histologic patterns in lung adenocarcinoma is critical for determining tumor grade and treatment for patients. However, this task is often challenging due to the heterogeneous nature of lung adenocarcinoma and the subjective criteria for evaluation. In this study, we propose a deep learning model that automatically classifies the histologic patterns of lung adenocarcinoma on surgical resection slides. Our model uses a convolutional neural network to identify regions of neoplastic cells, then aggregates those classifications to infer predominant and minor histologic patterns for any given whole-slide image. We evaluated our model on an independent set of 143 whole-slide images. It achieved a kappa score of 0.525 and an agreement of 66.6% with three pathologists for classifying the predominant patterns, slightly higher than the inter-pathologist kappa score of 0.485 and agreement of 62.7% on this test set. All evaluation metrics for our model and the three pathologists were within 95% confidence intervals of agreement. If confirmed in clinical practice, our model can assist pathologists in improving classification of lung adenocarcinoma patterns by automatically pre-screening and highlighting cancerous regions prior to review. Our approach can be generalized to any whole-slide image classification task, and code is made publicly available at https://github.com/BMIRDS/deepslide .