Cancer Detection Using Hyperspectral Imaging and Evaluation of the Superficial Tumor Margin Variance with Depth

• Type of Material: Article
• Authors: Martin Halicek, University of Texas Dallas; Himar Fabelo, University of Texas Dallas; Samuel Ortega, University of Las Palmas Gran Canaria; James Little III, Emory University; Xu Wang, Emory University; Amy Chen, Emory University; Gustavo M. Callico, University of Las Palmas Gran Canaria; 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: 2019-01-01
• Publisher: SPIE-International
• Publication Version: Author Accepted Manuscript (After Peer Review)
• Copyright Statement: © (2019) Society of Photo-Optical Instrumentation Engineers (SPIE).
• Final Published Version (URL): http://dx.doi.org/10.1117/12.2512985
• Title of Journal or Parent Work: Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling
• Volume: 10951
• Grant/Funding Information: This research was supported in part by the U.S. National Institutes of Health (NIH) grants (R21CA176684, R01CA156775, R01CA204254, and R01HL140325).
• Keywords: Science & Technology; deep learning; Surgery; Technology; head and neck surgery; intraoperative imaging; Tongue; Optics; Engineering, Biomedical; convolutional neural network; optical biopsy; head and neck cancer; Imaging Science & Photographic Technology; Hyperspectral imaging; Physical Sciences; Head; Squamous cell carcinoma; Engineering
• Research Categories: Health Sciences, Oncology; Health Sciences, Pathology; Engineering, Biomedical; Physics, Optics

Abstract

Head and neck squamous cell carcinoma (SCCa) is primarily managed by surgical resection. Recurrence rates after surgery can be as high as 55% if residual cancer is present. In this study, hyperspectral imaging (HSI) is evaluated for detection of SCCa in ex-vivo surgical specimens. Several methods are investigated, including convolutional neural networks (CNNs) and a spectral-spatial variant of support vector machines. Quantitative results demonstrate that additional processing and unsupervised filtering can improve CNN results to achieve optimal performance. Classifying regions that include specular glare, the average AUC is increased from 0.73 [0.71, 0.75 (95% confidence interval)] to 0.81 [0.80, 0.83] through an unsupervised filtering and majority voting method described. The wavelengths of light used in HSI can penetrate different depths into biological tissue, while the cancer margin may change with depth and create uncertainty in the ground-truth. Through serial histological sectioning, the variance in cancer-margin with depth is also investigated and paired with qualitative classification heat maps using the methods proposed for the testing group SCC patients.