A single latent channel is sufficient for biomedical glottis segmentation.

Autor: Kist AM; Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University Erlangen-Nürnberg, 91052, Erlangen, Germany. andreas.kist@fau.de., Breininger K; Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University Erlangen-Nürnberg, 91052, Erlangen, Germany., Dörrich M; Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University Erlangen-Nürnberg, 91052, Erlangen, Germany., Dürr S; Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology, Head and Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-Nürnberg, 91054, Erlangen, Germany., Schützenberger A; Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology, Head and Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-Nürnberg, 91054, Erlangen, Germany., Semmler M; Division of Phoniatrics and Pediatric Audiology at the Department of Otorhinolaryngology, Head and Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-Nürnberg, 91054, Erlangen, Germany.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2022 Aug 22; Vol. 12 (1), pp. 14292. Date of Electronic Publication: 2022 Aug 22.
DOI: 10.1038/s41598-022-17764-1
Abstrakt: Glottis segmentation is a crucial step to quantify endoscopic footage in laryngeal high-speed videoendoscopy. Recent advances in deep neural networks for glottis segmentation allow for a fully automatic workflow. However, exact knowledge of integral parts of these deep segmentation networks remains unknown, and understanding the inner workings is crucial for acceptance in clinical practice. Here, we show that a single latent channel as a bottleneck layer is sufficient for glottal area segmentation using systematic ablations. We further demonstrate that the latent space is an abstraction of the glottal area segmentation relying on three spatially defined pixel subtypes allowing for a transparent interpretation. We further provide evidence that the latent space is highly correlated with the glottal area waveform, can be encoded with four bits, and decoded using lean decoders while maintaining a high reconstruction accuracy. Our findings suggest that glottis segmentation is a task that can be highly optimized to gain very efficient and explainable deep neural networks, important for application in the clinic. In the future, we believe that online deep learning-assisted monitoring is a game-changer in laryngeal examinations.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje