Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study

To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL). The AI system was developed, trained and validated on 5362 images of 551 patients from three hospi...

Full description

Saved in:
Bibliographic Details
Published in:American journal of otolaryngology 2024-07, Vol.45 (4), p.104342, Article 104342
Main Authors: Wang, Mei-Ling, Tie, Cheng-Wei, Wang, Jian-Hui, Zhu, Ji-Qing, Chen, Bing-Hong, Li, Ying, Zhang, Sen, Liu, Lin, Guo, Li, Yang, Long, Yang, Li-Qun, Wei, Jiao, Jiang, Feng, Zhao, Zhi-Qiang, Wang, Gui-Qi, Zhang, Wei, Zhang, Quan-Mao, Ni, Xiao-Guang
Format: Article
Language:English
Subjects:
Adult
Aged
Algorithms
Artificial Intelligence
Diagnosis, Computer-Assisted - methods
Diagnosis, Differential
Female
Humans
Laryngeal Neoplasms - diagnosis
Laryngeal Neoplasms - diagnostic imaging
Laryngeal Neoplasms - pathology
Laryngoscopy
Laryngoscopy - methods
Leukoplakia - diagnosis
Leukoplakia - pathology
Machine Learning
Male
Middle Aged
Multi-instance learning
Segmentation
Vocal Cords - diagnostic imaging
Vocal Cords - pathology
Vocal fold leukoplakia
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL). The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance. In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740–0.811) and 0.720 (95 % CI 0.684–0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798–0.940) and 0.851 (95 % CI 0.756–0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743–0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682–0.755) to 0.808 (95 % CI 0.775–0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608–0.686) to 0.807 (95 % CI 0.773–0.837) for junior otolaryngologists. The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.
ISSN:0196-0709
1532-818X
1532-818X
DOI:10.1016/j.amjoto.2024.104342