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

  • Dennis Eggert (Geteilte/r Erstautor/in)
  • Marcel Bengs (Geteilte/r Erstautor/in)
  • Stephan Westermann
  • Nils Gessert
  • Andreas O H Gerstner
  • Nina A Mueller
  • Julian Bewarder
  • Alexander Schlaefer
  • Christian Betz
  • Wiebke Laffers


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%.

Bibliografische Daten

StatusVeröffentlicht - 03.2022

Anmerkungen des Dekanats

© 2021 The Authors. Journal of Biophotonics published by Wiley-VCH GmbH.

PubMed 34889065