File size: 627 Bytes
9cd29e8
 
 
 
 
 
 
 
034e218
c6649f6
 
da23e87
1
2
3
4
5
6
7
8
9
10
11
12
13
---
tags:
- image-classification
- timm
library_name: timm
license: apache-2.0
---
# Model card for RETFound_MAE_oct_dru_cnv_dme_nor

A model fine-tuned on the [Kermany dataset of retinal OCT images](http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5), initialised from the base [open-eye/RETFound_MAE](https://huggingface.co/open-eye/RETFound_MAE) model for OCT images.

This model achieves 85% accuracy in the task of classifying Retinal OCT images as either showing signs of Drusen, Choroidal Neovascularization (CNV), Diabetic Macular Oedema (DME), or alternatively showing none of these and being otherwise "Normal".