Artificial Intelligence in Laryngeal Endoscopy: Systematic Review and Meta-Analysis

Abstract

Background: Early diagnosis of laryngeal lesions is necessary to begin treatment of patients as soon as possible to preserve optimal organ functions. Imaging examinations are often aided by artificial intelligence (AI) to improve quality and facilitate appropriate diagnosis. The aim of this study is to investigate diagnostic utility of AI in laryngeal endoscopy. Methods: Five databases were searched for studies implementing artificial intelligence (AI) enhanced models assessing images of laryngeal lesions taken during laryngeal endoscopy. Outcomes were analyzed in terms of accuracy, sensitivity, and specificity. Results: All 11 studies included presented an overall low risk of bias. The overall accuracy of AI models was very high (from 0.806 to 0.997). The accuracy was significantly higher in studies using a larger database. The pooled sensitivity and specificity for identification of healthy laryngeal tissue were 0.91 and 0.97, respectively. The same values for differentiation between benign and malignant lesions were 0.91 and 0.94, respectively. The comparison of the effectiveness of AI models assessing narrow band imaging and white light endoscopy images revealed no statistically significant differences (p = 0.409 and 0.914). Conclusion: In assessing images of laryngeal lesions, AI demonstrates extraordinarily high accuracy, sensitivity, and specificity.

Solitary Extramedullary Plasmacytoma of the Larynx and Secondary Laryngeal Involvement in Plasma Cell Myeloma: Single-Centre Retrospective Analysis and Systematic Literature Review

“…For extramedullary plasmacytomas, ESMO guidelines recommend either whole-body magnetic resonance imaging (MRI) or a positron emission tomography/computed tomography (PET/CT) ([ 155 ]. Although not supported by the guidelines, it seems reasonable to additionally incorporate image-enhanced endoscopy techniques in cases of a suspected laryngeal involvement, which are widely used in other laryngeal disorders [ 156 , 157 ].…”

Where do we stand in AI for endoscopic image analysis? Deciphering gaps and future directions

“…Some other types of endoscopic images-based deep learning applications include (a) detection of nasopharyngeal malignancies 73 , and segmentation of granulomas and ulcerations on images acquired by laryngoscopy 74 , (b) an end-to-end deep learning algorithm to segment and measure laryngeal nerves during thyroidectomy (a surgical procedure) 75 , and (c) deep-learning-based anatomical interpretation of video bronchoscopy images 76 . A recent review and meta-analysis paper on laryngeal endoscopy 77 suggested the AI models presented high overall accuracy between 0.806 and 0.997. However, this review did not show details on any AI model and used sample sizes.…”

Künstliche Intelligenz in der laryngealen Endoskopie

“…Die laryngeale Endoskopie liefert eine große Menge an diagnostisch wertvollem Bildmaterial. Unterstützende Methoden wie die Erkennung von organisch veränderten Schleimhäuten, sowie analysierende Verfahren [8] wie die Bestimmung des zeitlichen Schwingungsverhalten der Stimmlippen sind KI-Ansätze, die sich in der laryngealen Endoskopie etabliert haben [9]. Ein zusätzliches Anwendungsgebiet kann die Auswertung von Schluckprozessen sein, indem KI-Systeme die Muskelbewegungen im Kehlkopf und Rachen analysieren und dadurch Anomalien erkennen können.…”

“…Eine kürzlich veröffentlichte Studie hat sich damit beschäftigt, inwieweit KI-Methoden, insbesondere tiefe neuronale Netze, in der Lage sind laryngeale Läsionen zu identifizieren [8]. Die Autoren konnten durch die Analyse von 11 Veröffentlichungen zeigten, dass KI-Algorithmen sowohl im Weißlicht als auch im NBI-Modus eine hohe Spezifität von 95 % aufweisen.…”

“…In den 11 Veröffentlichungen waren die Aussagen auf verschieden großen, teils nicht öffentlich einsehbaren Datensätzen gestützt. Die Bandbreite betrug 120-24667 Bilder, eine Spanne über mehrere Größenordnungen [8]. KI-Methoden benötigen in der Regel spezialisierte Hardware, damit zeitnah Resultate zur Verfügung stehen.…”