A Comprehensive CNN Model for Age-Related Macular Degeneration Classification Using OCT: Integrating Inception Modules, SE Blocks, and ConvMixer
Elif Yusufoğlu, Hüseyin Fırat, Hüseyin Üzen, Salih Taha Alperen Özçelik, İpek Balıkçı Çiçek, Abdulkadir Şengür, Orhan Atila, Numan Halit Guldemir · 2024
Read A Comprehensive CNN Model for Age-Related Macular Degeneration Classification Using OCT: Integrating Inception Modules, SE Blocks, and ConvMixer by Elif Yusufoğlu, Hüseyin Fırat, Hüseyin Üzen, Salih Taha Alperen Özçelik, İpek Balıkçı Çiçek, Abdulkadir Şengür, Orhan Atila, Numan Halit Guldemir (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-11674915.txt.
Description
Elif Yusufoğlu leads a team of eight authors assembling a hybrid neural network to grade age-related macular degeneration from retinal scans. The disease blinds older adults and progresses silently early, so automated reading of optical coherence tomography images matters. Their architecture fuses modified Inception modules, depthwise squeeze-and-excitation blocks, and a ConvMixer design, aiming for accuracy with computational efficiency.
On a private set of over twenty-three hundred images it reached about ninety-eight percent accuracy, with matching precision, recall, and F1 scores. On the public Noor dataset it scored a perfect one hundred percent across metrics, beating existing approaches in their comparison. The authors present the model as ready evidence that combined architectures outperform single-design networks for this task.
Catalog record
| CREATOR | Elif Yusufoğlu, Hüseyin Fırat, Hüseyin Üzen, Salih Taha Alperen Özçelik, İpek Balıkçı Çiçek, Abdulkadir Şengür, Orhan Atila, Numan Halit Guldemir |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 54 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |