Accepted for/Published in: JMIR Formative Research
Date Submitted: Sep 23, 2024
Date Accepted: Aug 5, 2025
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
A Preliminary Efficient AI-Driven Laryngeal Cancer Triage Framework for Low-resource Settings
ABSTRACT
Background:
A Preliminary Efficient AI-Driven Laryngeal Cancer Triage Framework for Low-resource Settings
Objective:
Early-stage diagnosis of laryngeal cancer can significantly enhance patient survival rates and quality of life. However, the scarcity of specialists in low-resource settings constrains the timely review of endoscopy videos, which is essential for accurately triaging at-risk patients.
Methods:
The system includes an image quality model (IQM) to identify high-quality endoscopic images fed into a disease classification model (DCM) trained on efficient Ghost modules. To validate our approach, we curated a real-world dataset from 132 patients at a leading academic tertiary care center.
Results:
Based on this dataset, we demonstrated that the IQM achieved 0.895 AUC and 0.878 AUPRC to select high-quality images. Given the high-quality images from the IQM, the DCM improved its performance by 38% in AUPRC (from 0.600 to 0.833) and 8% in AUPRC (from 0.840 to 0.912). In addition, the AI model achieved a 2.5 times faster inference time than the ResNet50.
Conclusions:
This study validated an AI-based screening system designed for low-resource settings, demonstrating its capability to triage patients accurately and efficiently. This approach promises substantial benefits for healthcare accessibility and patient outcomes in regions with limited specialist care.
Citation
