Vocal cord lesions classification based on deep convolutional neural network and transfer learning.

Researchers

Journal

Modalities

Models

Abstract

Laryngoscopy, the most common diagnostic method for vocal cord lesions (VCLs), is based mainly on the visual subjective inspection of otolaryngologists. This study aimed to establish a highly objective computer-aided VCLs diagnosis system based on deep convolutional neural network (DCNN) and transfer learning.To classify VCLs, our method combined DCNN backbone with transfer learning on a system specifically finetuned for a laryngoscopy image dataset. Laryngoscopy image database was collected to train the proposed system. The diagnostic performance was compared with other DCNN based model. Analysis of F1 score and receiver operating characteristic (ROC) curves were conducted to evaluate the performance of the system.Beyond existing VCLs diagnosis method, the proposed system achieved an overall accuracy of 80.23%, an F1 score of 0.7836, and an AUC of 0.9557 for four fine-grained classes of VCLs, namely normal, polyp, keratinization, and carcinoma. It also demonstrated robust classification capacity for detecting urgent (keratinization, carcinoma) and non-urgent (normal, polyp), with an overall accuracy of 0.939, a sensitivity of 0.887, a specificity of 0.993, and an AUC of 0.9828. The proposed method also outperformed clinicians in the classification of normal, polyps, and carcinoma at an extremely low time cost.The VCLs diagnosis system succeeded in using DCNN to distinguish the most common VCLs and normal cases, holding a practical potential for improving the overall diagnostic efficacy in VCLs examinations. The proposed VCLs diagnosis system could be appropriately integrated into the conventional work-flow of VCLs laryngoscopy as a highly objective auxiliary method. This article is protected by copyright. All rights reserved.This article is protected by copyright. All rights reserved.