In vivo detection of head and neck tumors by hyperspectral imaging combined with deep learning methods. Issue 3 (28th December 2021)

• Record Type: Journal Article
• Authors: Eggert, Dennis; Bengs, Marcel; Westermann, Stephan; Gessert, Nils; Gerstner, Andreas O. H.; Mueller, Nina A.; Bewarder, Julian; Schlaefer, Alexander; Betz, Christian; Laffers, Wiebke
• Is Part Of: Journal of biophotonics. Volume 15:Issue 3(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-12-28
• Subjects: convolutional neural network -- head and neck cancer -- hyperspectral imaging -- intraoperative imaging -- optical biopsy; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.202100167
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract: Currently, there are no fast and accurate screening methods available for head and neck cancer, the eighth most common tumor entity. For this study, we used hyperspectral imaging, an imaging technique for quantitative and objective surface analysis, combined with deep learning methods for automated tissue classification. As part of a prospective clinical observational study, hyperspectral datasets of laryngeal, hypopharyngeal and oropharyngeal mucosa were recorded in 98 patients before surgery in vivo. We established an automated data interpretation pathway that can classify the tissue into healthy and tumorous using convolutional neural networks with 2D spatial or 3D spatio‐spectral convolutions combined with a state‐of‐the‐art Densenet architecture. Using 24 patients for testing, our 3D spatio‐spectral Densenet classification method achieves an average accuracy of 81%, a sensitivity of 83% and a specificity of 79%. Abstract : Currently, there are no fast and accurate screening methods available for head and neck cancer. In this study, hyperspectral imaging, a technique for quantitative and objective surface analysis, was used in 98 patients before surgery in vivo and combined with deep learning methods for automated tissue classification. Our data interpretation pathway was able to classify laryngeal, hypopharyngeal and oropharyngeal mucosa into healthy and tumorous with high sensitivity and specificity.