Automatic Recognition of Laryngoscopic Images Using a Deep‐Learning Technique
Jianjun Ren, Xueping Jing, Jing Wang, Xue Ren, Xu Yang, Qiuyun Yang, Lanzhi Ma, Yi Sun, Wei Xu, Ning Yang, Jian Zou, Yongbo Zheng, Min Chen, Weigang Gan, Ting Xiang, Junnan An, Ruiqing Liu, Cao Lv, Ken Lin, Zheng Xianfeng, Fan Lou, Yufang Rao, Hui Yang, Kai Liu, Geoffrey Liu, Tao Lü, Xiujuan Zheng, Yu Zhao
Abstract
OBJECTIVES/HYPOTHESIS: To develop a deep-learning-based computer-aided diagnosis system for distinguishing laryngeal neoplasms (benign, precancerous lesions, and cancer) and improve the clinician-based accuracy of diagnostic assessments of laryngoscopy findings. STUDY DESIGN: Retrospective study. METHODS: A total of 24,667 laryngoscopy images (normal, vocal nodule, polyps, leukoplakia and malignancy) were collected to develop and test a convolutional neural network (CNN)-based classifier. A comparison between the proposed CNN-based classifier and the clinical visual assessments (CVAs) by 12 otolaryngologists was conducted. RESULTS: In the independent testing dataset, an overall accuracy of 96.24% was achieved; for leukoplakia, benign, malignancy, normal, and vocal nodule, the sensitivity and specificity were 92.8% vs. 98.9%, 97% vs. 99.7%, 89% vs. 99.3%, 99.0% vs. 99.4%, and 97.2% vs. 99.1%, respectively. Furthermore, when compared with CVAs on the randomly selected test dataset, the CNN-based classifier outperformed physicians for most laryngeal conditions, with striking improvements in the ability to distinguish nodules (98% vs. 45%, P < .001), polyps (91% vs. 86%, P < .001), leukoplakia (91% vs. 65%, P < .001), and malignancy (90% vs. 54%, P < .001). CONCLUSIONS: The CNN-based classifier can provide a valuable reference for the diagnosis of laryngeal neoplasms during laryngoscopy, especially for distinguishing benign, precancerous, and cancer lesions. LEVEL OF EVIDENCE: NA Laryngoscope, 130:E686-E693, 2020.