A Deep Learning Network for Accurate Retinal Multidisease Diagnosis Using Multiview Fusion of En Face and B-Scan Images: A Multicenter Study
Translational Vision Science & Technology · 18.12.2024 · 13 (12) · 31
DOI: 10.1167/tvst.13.12.31 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Translational Vision Science & Technology, erschienen am 18.12.2024. Verfasst von Chubin Ou und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Chin…. Hauptthemen laut MEDLINE: Deep Learning, Tomography, Optical Coherence, Retinal Diseases. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Purpose
Accurate diagnosis of retinal disease based on optical coherence tomography (OCT) requires scrutiny of both B-scan and en face images. The aim of this study was to investigate the effectiveness of fusing en face and B-scan images for better diagnostic performance of deep learning models.
Methods
A multiview fusion network (MVFN) with a decision fusion module to integrate fast-axis and slow-axis B-scans and en face information was proposed and compared with five state-of-the-art methods: a model using B-scans, a model using en face imaging, a model using three-dimensional volume, and two other relevant methods. They were evaluated using the OCTA-500 public dataset and a private multicenter dataset with 2330 cases; cases from the first center were used for training and cases from the second center were used for external validation. Performance was assessed by averaged area under the curve (AUC), accuracy, sensitivity, specificity, and precision.
Results
In the private external test set, our MVFN achieved the highest AUC of 0.994, significantly outperforming the other models (P < 0.01). Similarly, for the OCTA-500 public dataset, our proposed method also outperformed the other methods with the highest AUC of 0.976, further demonstrating its effectiveness. Typical cases were demonstrated using activation heatmaps to illustrate the synergy of combining en face and B-scan images.
Conclusions
The fusion of en face and B-scan information is an effective strategy for improving the diagnostic accuracy of deep learning models. Translational Relevance: Multiview fusion models combining B-scan and en face images demonstrate great potential in improving AI performance for retina disease diagnosis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
- Guangdong Eye Intelligent Medical Imaging Equipment Engineering Technology Research Center, Foshan, China.
- Hangzhou Dianzi University, Hangzhou, China.
- Department of Ophthalmology, The First People's Hospital of Foshan, Foshan, China.
- Department of Ophthalmology, Guangdong Provincial Hospital of Integrated Chinese and Western Medicine, Foshan, China.
- Department of Ophthalmology, The Second People's Hospital of Foshan, Foshan, China.
Zitieren
APA
Ou, C., Wei, X., An, L., Qin, J., Zhu, M., Jin, M., & Kong, X. (2024). A Deep Learning Network for Accurate Retinal Multidisease Diagnosis Using Multiview Fusion of En Face and B-Scan Images: A Multicenter Study. Translational Vision Science & Technology, 13(12), 31. https://doi.org/10.1167/tvst.13.12.31
Vancouver
Ou C, Wei X, An L, Qin J, Zhu M, Jin M, et al. A Deep Learning Network for Accurate Retinal Multidisease Diagnosis Using Multiview Fusion of En Face and B-Scan Images: A Multicenter Study. Translational Vision Science & Technology. 2024;13(12):31. doi:10.1167/tvst.13.12.31
BibTeX
@article{Ou2024,
author = {Ou, Chubin and Wei, Xifei and An, Lin and Qin, Jia and Zhu, Min and Jin, Mei and Kong, Xiangbin},
title = {A Deep Learning Network for Accurate Retinal Multidisease Diagnosis Using Multiview Fusion of En Face and B-Scan Images: A Multicenter Study},
journal = {Translational Vision Science & Technology},
year = {2024},
volume = {13},
number = {12},
pages = {31},
doi = {10.1167/tvst.13.12.31}
}
EUVIMED