Predicting semantic segmentation quality in laryngeal endoscopy images

• Published in: PloS one Vol. 20; no. 7; p. e0314573
• Main Authors: Kist, Andreas M., Razi, Sina, Groh, René, Gritsch, Florian, Schützenberger, Anne
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 03.07.2025; Public Library of Science (PLoS)
• Subjects: Algorithms; Analysis; Artificial Intelligence; Biology and Life Sciences; Computer and Information Sciences; Datasets; Deep learning; Endoscopy; Engineering and Technology; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image quality; Image segmentation; Laryngoscopy; Laryngoscopy - methods; Larynx - diagnostic imaging; Masks; Medical imaging; Medicine and Health Sciences; Methods; Neural networks; Physiology; Pixels; Semantic segmentation; Semantics; Social Sciences; Subject specialists; Traffic signals; Germany
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0314573

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.