Detection of Squamous Cell Carcinoma in Digitized Histological Images from the Head and Neck Using Convolutional Neural Networks

摘要

Primary management for head and neck squamous cell carcinoma (SCC) involves surgical resection with negativecancer margins. Pathologists guide surgeons during these operations by detecting SCC in histology slides madefrom the excised tissue. In this study, 192 digitized histological images from 84 head and neck SCC patients wereused to train, validate, and test an inception-v4 convolutional neural network. The proposed method performswith an AUC of 0.91 and 0.92 for the validation and testing group. The careful experimental design yields arobust method with potential to help create a tool to increase effciency and accuracy of pathologists for detectingSCC in histological images.