|Publisher DOI:||10.1117/12.2549251||Title:||Spatio-spectral deep learning methods for in-vivo hyperspectral laryngeal cancer detection||Language:||English||Authors:||Bengs, Marcel
Gessert, Nils Thorben
Gerstner, Andreas O. H.
Mueller, Nina A.
Betz, Christian Stephan
|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)||URI:||http://hdl.handle.net/11420/6237||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
checked on Jul 16, 2020
Add Files to Item
Note about this record
Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.