Medical Imaging Fusing Vision Transformer: Laryngeal Cancer Screening with Explanation

2026-07-20

AI Summary

This study addresses the challenges in early laryngeal cancer screening—namely, reliance on expert experience, time-intensive evaluation, and inter-observer variability—by proposing a novel classification framework that integrates Vision Transformer with attention mechanisms. For the first time, this approach is combined with the MedSAM segmentation model to jointly discriminate between benign and malignant lesions and provide interpretable localization of pathological regions. Evaluated on narrow-band imaging endoscopic images, the framework achieves an accuracy of 82.33% and an F1 score of 82.72%. Beyond improving diagnostic consistency, the method enhances clinical trustworthiness through visual explanations of critical regions, establishing a new paradigm for AI-assisted laryngeal cancer screening that balances high performance with interpretability.

Abstract

Early and timely screening of laryngeal cancer is crucial for improving clinical outcomes. In recent years, NBI endoscopy has become a standard diagnostic tool for the detection of laryngeal lesions. However, its effective use requires well-trained clinicians and the procedure is time-consuming and subject to interobserver variability. In this context, the application of artificial intelligence (AI) offers a promising solution to support clinical decision-making. In this work, we proposed applying transformer and attention mechanism for analyzing the narrow band imaging and distinguish benign and malignant lesions. Results show it has good classification performance with F1 (82.72%), accuracy(82.33%). In addition, the result of laryngeal cancer screening is explainable for clinicians. The explainability is utilizing the state of art segmentation method (MedSAM) to provide the useful pathological information area for clinicians. The proposed methodology fusing classification and segmentation provides a translating on laryngeal cancer screening.

Problem

• laryngeal cancer screening
• NBI endoscopy
• interobserver variability
• clinical decision support
• medical imaging

Innovation

• Vision Transformer
• Attention Mechanism
• MedSAM
• Explainable AI
• Laryngeal Cancer Screening