In vivo detection of head and neck tumors by hyperspectral imaging combined with deep learning methods

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%.

Subjects

MLE@TUHH

DDC Class

600: Technik

610: Medizin

More Funding Information

This work was supported by the Deutsche Krebshilfe as part of the project “Early Detection of Laryngeal Cancer EGGERT ET AL. 7 of 8
by Hyperspectral Imaging” (project numbers 109825 and 110275). This work was also supported by the Forschungszentrum Medizintechnik Hamburg (fmthh) Förderlinie 2019 (project: Verbesserte Diagnostik von Tumoren des oberen Luft-Speisewegs durch Kombination von hyperspektraler Bildgebung mit Methoden der KI). Open access funding enabled and organized by Projekt DEAL.

Publication version

publishedVersion

Lizenz

https://creativecommons.org/licenses/by-nc/4.0/

Name

Journal of Biophotonics - 2021 - Eggert - In vivo detection of head and neck tumors by hyperspectral imaging combined with.pdf

Size

820.9 KB

Format

Adobe PDF

Options

In vivo detection of head and neck tumors by hyperspectral imaging combined with deep learning methods