Predicting semantic segmentation quality in laryngeal endoscopy images

Kist A, Razi S, Groh R, Gritsch F, Schützenberger A (2025)

Publication Type: Journal article

Publication year: 2025

Journal

PLoS ONE Public Library of Science

Book Volume: 20

Article Number: e0314573

Journal Issue: 7 July

DOI: 10.1371/journal.pone.0314573

Abstract

Endoscopy is a major tool for assessing the physiology of inner organs. Contemporary artificial intelligence methods are used to fully automatically label medical important classes on a pixel-by-pixel level. This so-called semantic segmentation is for example used to detect cancer tissue or to assess laryngeal physiology. However, due to the diversity of patients presenting, it is necessary to judge the segmentation quality. In this study, we present a fully automatic system to evaluate the segmentation performance in laryngeal endoscopy images. We showcase on glottal area segmentation that the predicted segmentation quality represented by the intersection over union metric is on par with human raters. Using a traffic light system, we are able to identify problematic segmentation frames to allow human-in-the-loop improvements, important for the clinical adaptation of automatic analysis procedures.

Authors with CRIS profile

Andreas Kist Juniorprofessur für Artificial Intelligence in Communication Disorders René Groh Juniorprofessur für Artificial Intelligence in Communication Disorders Florian Gritsch Graduiertenzentrum der FAU Anne Schützenberger Department of Otorhinolaryngology – Head and Neck Surgery (HNO-Klinik)

How to cite

APA:

Kist, A., Razi, S., Groh, R., Gritsch, F., & Schützenberger, A. (2025). Predicting semantic segmentation quality in laryngeal endoscopy images. PLoS ONE, 20(7 July). https://doi.org/10.1371/journal.pone.0314573

MLA:

Kist, Andreas, et al. "Predicting semantic segmentation quality in laryngeal endoscopy images." PLoS ONE 20.7 July (2025).

BibTeX: Download