Multi-Disease Detection in Retinal Imaging using Modified EfficientNetB4

Participation at the Retinal Image Analysis for multi-Disease Detection Challenge (RIADD):

Link: https://riadd.grand-challenge.org/

Reproducibility

Requirements:

Ubuntu 18.04
Python 3.7
Tensorflow 2.2.0
NVIDIA P100 GPU or a GPU with equivalent performance

Sample Images from Dataset

Classwise distribution of diseases

Dataset

The new Retinal Fundus Multi-Disease Image Dataset (RFMiD) consists of 3200 fundus images and contains 46 retinal conditions including various rare and challenging to detect diseases. The dataset was published associated to the Retinal Image Analysis for Multi-Disease Classification (RIADD) challenge from the ISBI 2021. The aim was to multi-label classify different sized retinal microscrope images.

Reference: https://riadd.grand-challenge.org/

Pachade S, Porwal P, Thulkar D, Kokare M, Deshmukh G, Sahasrabuddhe V, Giancardo L, Quellec G, Mériaudeau F.
Retinal Fundus Multi-Disease Image Dataset (RFMiD): A Dataset for Multi-Disease Detection Research.
Data. 2021; 6(2):14.
https://doi.org/10.3390/data6020014

Download Git repository:

  git clone https://github.com/sandesh001/Multi-Disease-Detection-in-Retinal-Imaging.git
  cd Multi-Disease-Detection-in-Retinal-Imaging/

sandesh001 / Multi-Disease-Detection-in-Retinal-Imaging