Deep learning-based joint analysis of diabetic retinopathy and glaucoma in retinal fundus images
T Geetha, C Hema · 2025
Read Deep learning-based joint analysis of diabetic retinopathy and glaucoma in retinal fundus images by T Geetha, C Hema (2025) 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-12830750.txt.
Description
T Geetha and C Hema teach one network to read two eye diseases at once in a 2025 paper. Diabetic retinopathy and glaucoma both scar the retina, and when they coexist their signs tangle, fooling ordinary image networks. Each is a leading cause of blindness, so a joint reader has real clinical pull.
Their architecture pairs a vision transformer, which grasps global layout, with a two-way feature fusion module that keeps fine textures in play. A search algorithm borrowed from a foraging game tunes the model's settings and fusion weights. On open datasets the system classified over ninety-eight percent of images correctly, beating plain convolutional networks, lone transformers, and rival tuners on accuracy and sensitivity alike. The authors offer it as a fast, scalable screener for clinics facing tangled retinal images.
Catalog record
| CREATOR | T Geetha, C Hema |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 123 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |