Transfer Learning based Detection of Diabetic Retinopathy from Small Dataset

TL;DR

This paper explores using transfer learning with Inception-V3 to effectively detect diabetic retinopathy from small datasets, addressing the challenge of limited labeled medical data for deep learning.

Contribution

The study demonstrates that transfer learning with Inception-V3 can improve diabetic retinopathy detection accuracy on small datasets, offering a solution for data scarcity in medical imaging.

Findings

Effective detection of diabetic retinopathy with small datasets

Transfer learning reduces training data requirements

Model generalizes well to unseen data

Abstract

Annotated training data insufficiency remains to be one of the challenges of applying deep learning in medical data classification problems. Transfer learning from an already trained deep convolutional network can be used to reduce the cost of training from scratch and to train with small training data for deep learning. This raises the question of whether we can use transfer learning to overcome the training data insufficiency problem in deep learning based medical data classifications. Deep convolutional networks have been achieving high performance results on the ImageNet Large Scale Visual Recognition Competition (ILSVRC) image classification challenge. One example is the Inception-V3 model that was the first runner up on the ILSVRC 2015 challenge. Inception modules that help to extract different sized features of input images in one level of convolution are the unique features of the Inception-V3. In this work, we have used a pretrained Inception-V3 model to take advantage of its Inception modules for Diabetic Retinopathy detection. In order to tackle the labelled data insufficiency problem, we sub-sampled a smaller version of the Kaggle Diabetic Retinopathy classification challenge dataset for model training, and tested the model's accuracy on a previously unseen data subset. Our technique could be used in other deep learning based medical image classification problems facing the challenge of labeled training data insufficiency.