Head and Neck Cancer Detection in Digitized Whole-Slide Histology Using Convolutional Neural Networks

• Type of Material: Article
• Authors: Martin Halicek, University of Texas Dallas; Maysam Shahedi, University of Texas Dallas; James V Little III, Emory University; Amy Chen, Emory University; Larry L. Myers, University of Texas Southwestern Medical Center; Baran D. Sumer, University of Texas Southwestern Medical Center; Baowei Fei, Emory University
• Language: English
• Date: 2019-10-01
• Publisher: Nature Research (part of Springer Nature): Fully open access journals
• Publication Version: Final Published Version
• Copyright Statement: © The Author(s) 2019
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.1038/s41598-019-50313-x
• Title of Journal or Parent Work: Scientific Reports
• ISSN: 2045-2322
• Volume: 9
• Issue: 1
• Start Page: 14043
• End Page: 14043
• Grant/Funding Information: This research was supported in part by the U.S. National Institutes of Health (NIH) grants (R21CA231911, R01CA156775, R01CA204254, and R01HL140325).; The project was also supported in part by an Early Translational Research Award (RP190588) from the Cancer Prevention and Research Institute of Texas (CPRIT).
• Keywords: BENIGN; Science & Technology - Other Topics; Multidisciplinary Sciences; SYSTEM; MARGINS; THYROID FOLLICULAR LESIONS; SQUAMOUS-CELL CARCINOMA; Science & Technology; DIAGNOSIS; PATHOLOGY; NODULES; CLASSIFICATION
• Research Categories: Health Sciences, Oncology; Engineering, Biomedical; Health Sciences, Pathology

Abstract

Primary management for head and neck cancers, including squamous cell carcinoma (SCC), involves surgical resection with negative cancer margins. Pathologists guide surgeons during these operations by detecting cancer in histology slides made from the excised tissue. In this study, 381 digitized, histological whole-slide images (WSI) from 156 patients with head and neck cancer were used to train, validate, and test an inception-v4 convolutional neural network. The proposed method is able to detect and localize primary head and neck SCC on WSI with an AUC of 0.916 for patients in the SCC testing group and 0.954 for patients in the thyroid carcinoma testing group. Moreover, the proposed method is able to diagnose WSI with cancer versus normal slides with an AUC of 0.944 and 0.995 for the SCC and thyroid carcinoma testing groups, respectively. For comparison, we tested the proposed, diagnostic method on an open-source dataset of WSI from sentinel lymph nodes with breast cancer metastases, CAMELYON 2016, to obtain patch-based cancer localization and slide-level cancer diagnoses. The experimental design yields a robust method with potential to help create a tool to increase efficiency and accuracy of pathologists detecting head and neck cancers in histological images.