Transfer Learning for Retinal Vascular Disease Detection: A Pilot Study with Diabetic Retinopathy and Retinopathy of Prematurity
This work addresses the challenge of data scarcity in medical image analysis for retinal diseases, offering a potential solution for broader applications, though it appears incremental as it builds on existing transfer learning methods.
The authors tackled the problem of limited data for detecting retinal vascular diseases by proposing a transfer learning approach using diabetic retinopathy (DR) as a source task for retinopathy of prematurity (ROP) detection, resulting in their method outperforming conventional ImageNet-pretrained approaches across all metrics and showing greater robustness with reduced training samples.
Retinal vascular diseases affect the well-being of human body and sometimes provide vital signs of otherwise undetected bodily damage. Recently, deep learning techniques have been successfully applied for detection of diabetic retinopathy (DR). The main obstacle of applying deep learning techniques to detect most other retinal vascular diseases is the limited amount of data available. In this paper, we propose a transfer learning technique that aims to utilize the feature similarities for detecting retinal vascular diseases. We choose the well-studied DR detection as a source task and identify the early detection of retinopathy of prematurity (ROP) as the target task. Our experimental results demonstrate that our DR-pretrained approach dominates in all metrics the conventional ImageNet-pretrained transfer learning approach, currently adopted in medical image analysis. Moreover, our approach is more robust with respect to the stochasticity in the training process and with respect to reduced training samples. This study suggests the potential of our proposed transfer learning approach for a broad range of retinal vascular diseases or pathologies, where data is limited.