Publisher DOI: 10.1117/12.2549251
Title: Spatio-spectral deep learning methods for in-vivo hyperspectral laryngeal cancer detection
Language: English
Authors: Bengs, Marcel 
Westermann, Stephan 
Gessert, Nils Thorben 
Eggert, Dennis 
Gerstner, Andreas O. H. 
Mueller, Nina A. 
Betz, Christian Stephan 
Laffers, Wiebke 
Schlaefer, Alexander 
Keywords: convolutional neural networks;head and neck cancer;hyperspectral imaging;intraoperative imaging;optical biopsy
Issue Date: Feb-2020
Source: Progress in Biomedical Optics and Imaging - Proceedings of SPIE (11314): 113141L (2020-02)
Journal or Series Name: Progress in Biomedical Optics and Imaging - Proceedings of SPIE 
Abstract (english): Early detection of head and neck tumors is crucial for patient survival. Often, diagnoses are made based on endoscopic examination of the larynx followed by biopsy and histological analysis, leading to a high interobserver variability due to subjective assessment. In this regard, early non-invasive diagnostics independent of the clinician would be a valuable tool. A recent study has shown that hyperspectral imaging (HSI) can be used for non-invasive detection of head and neck tumors, as precancerous or cancerous lesions show specific spectral signatures that distinguish them from healthy tissue. However, HSI data processing is challenging due to high spectral variations, various image interferences, and the high dimensionality of the data. Therefore, performance of automatic HSI analysis has been limited and so far, mostly ex-vivo studies have been presented with deep learning. In this work, we analyze deep learning techniques for in-vivo hyperspectral laryngeal cancer detection. For this purpose we design and evaluate convolutional neural networks (CNNs) with 2D spatial or 3D spatio-spectral convolutions combined with a state-of-the-art Densenet architecture. For evaluation, we use an in-vivo data set with HSI of the oral cavity or oropharynx. Overall, we present multiple deep learning techniques for in-vivo laryngeal cancer detection based on HSI and we show that jointly learning from the spatial and spectral domain improves classification accuracy notably. Our 3D spatio-spectral Densenet achieves an average accuracy of 81%.
Conference: Progress in Biomedical Optics and Imaging, SPIE (2020-02) 
ISBN: 978-151063395-7
ISSN: 1605-7422
Institute: Medizintechnische Systeme E-1 
Type: InProceedings (Aufsatz / Paper einer Konferenz etc.)
Appears in Collections:Publications without fulltext

Show full item record

Page view(s)

Last Week
Last month
checked on Jul 16, 2020

Google ScholarTM


Add Files to Item

Note about this record


Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.