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

TLDR

Head and neck cancers are primarily treated with surgical resection, and pathologists identify cancer on histology slides to guide surgeons. The study trains an inception‑v4 convolutional neural network on 381 whole‑slide images from 156 patients to detect head and neck squamous cell carcinoma. An inception‑v4 CNN was trained, validated, and tested on head and neck cancer WSI, and its performance was compared on the CAMELYON 2016 breast cancer dataset for patch‑level localization and slide‑level diagnosis. The network achieved AUCs of 0.916 (SCC) and 0.954 (thyroid carcinoma) for localization, and 0.944 (SCC) and 0.995 (thyroid carcinoma) for diagnosis, demonstrating robust performance that could improve pathologists’ efficiency and accuracy.

Abstract

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.