A Deep Learning Network for Accurate Retinal Multidisease Diagnosis Using Multiview Fusion of En Face and B-Scan Images: A Multicenter Study
Chubin Ou, Xifei Wei, Lin An, Jia Qin, Min Zhu, Mei Jin, Xiangbin Kong · 2024
Read A Deep Learning Network for Accurate Retinal Multidisease Diagnosis Using Multiview Fusion of En Face and B-Scan Images: A Multicenter Study by Chubin Ou, Xifei Wei, Lin An, Jia Qin, Min Zhu, Mei Jin, Xiangbin Kong (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11668356.txt.
Description
Chubin Ou and co-authors build a deep learning system for eye disease diagnosis in a 2024 study. Scans of the retina come in two views: flat en face images and cross-section B-scans. Doctors read both, but most programs use only one. The team built a network that fuses the two views and tested it against five rival methods.
On a private data set from two centers, the fused model scored highest on a standard accuracy measure, well ahead of single-view and volume-based rivals. It also won on a public data set. Heat maps showed the model drawing on both views for hard cases. The authors say view fusion is a strong route to better automated eye diagnosis.
Catalog record
| CREATOR | Chubin Ou, Xifei Wei, Lin An, Jia Qin, Min Zhu, Mei Jin, Xiangbin Kong |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 24 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |