Self-Attention Mechanisms-Based Laryngoscopy Image Classification Technique for Laryngeal Cancer Detection.

Abstract

The early diagnosis of laryngeal cancer (LCA) is crucial for prognosis, driving our search for an accurate, precise, and sensitive deep learning model to assist in LCA detection. We collected 5768 laryngoscopic images from 1462 patients and created the intelligent laryngeal cancer detection system (ILCDS) based on Swin-Transformer. Following training and validation, we assessed the ILCDS performance on the internal and external test sets and compared it with previous convolutional neural network (CNN) models and three professional laryngologists. The ILCDS outperformed the six CNNs, with the highest accuracy of 92.78% and an area under the curve (AUC) of 0.9732. Despite a slight drop in performance on external sets, the ILCDS maintained the best superiority, with 85.79% accuracy and an AUC of 0.9550. Surpassing professional laryngologists, the ILCDS achieved 92.00% accuracy. The ILCDS offers high accuracy and stability for LCA detection, reducing the burden on laryngologists.