Computer-aided diagnosis of laryngeal cancer via deep learning based on laryngoscopic images

• Published in: EBioMedicine Vol. 48; pp. 92 - 99
• Main Authors: Xiong, Hao, Lin, Peiliang, Yu, Jin-Gang, Ye, Jin, Xiao, Lichao, Tao, Yuan, Jiang, Zebin, Lin, Wei, Liu, Mingyue, Xu, Jingjing, Hu, Wenjie, Lu, Yuewen, Liu, Huaifeng, Li, Yuanqing, Zheng, Yiqing, Yang, Haidi
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.10.2019; Elsevier
• Subjects: Advanced Basic Science; Deep Learning; Diagnosis, Computer-Assisted; Humans; Image Processing, Computer-Assisted; Internal Medicine; Laryngeal Neoplasms - diagnosis; Laryngoscopy - methods; Models, Theoretical; Reproducibility of Results; Research paper; Sensitivity and Specificity

To develop a deep convolutional neural network (DCNN) that can automatically detect laryngeal cancer (LCA) in laryngoscopic images. A DCNN-based diagnostic system was constructed and trained using 13,721 laryngoscopic images of LCA, precancerous laryngeal lesions (PRELCA), benign laryngeal tumors (B...