Self-supervised retinal thickness prediction enables deep learning from unlabeled data to boost classification of diabetic retinopathy
Creators
- 1. Helmholtz Zentrum, Munich, Germany
- 2. Federal University of Sao Paulo (UNIFESP), University Eye Hospital Munich, Ludwig-Maximilian-University, Munich Germany
- 3. University Eye Hospital Munich, Ludwig-Maximilian-University, Munich Germany
Description
This data repository contains the OCT images and binary annotations for segmentation of retinal tissue using deep learning. To use, please refer to the Github repository https://github.com/theislab/DeepRT.
#######
Access to large, annotated samples represents a considerable challenge for training accurate deep-learning models in medical imaging. While current leading-edge transfer learning from pre-trained models can help with cases lacking data, it limits design choices, and generally results in the use of unnecessarily large models. We propose a novel, self-supervised training scheme for obtaining high-quality, pre-trained networks from unlabeled, cross-modal medical imaging data, which will allow for creating accurate and efficient models. We demonstrate this by accurately predicting optical coherence tomography (OCT)-based retinal thickness measurements from simple infrared (IR) fundus images. Subsequently, learned representations outperformed advanced classifiers on a separate diabetic retinopathy classification task in a scenario of scarce training data. Our cross-modal, three-staged scheme effectively replaced 26,343 diabetic retinopathy annotations with 1,009 semantic segmentations on OCT and reached the same classification accuracy using only 25% of fundus images, without any drawbacks, since OCT is not required for predictions. We expect this concept will also apply to other multimodal clinical data-imaging, health records, and genomics data, and be applicable to corresponding sample-starved learning problems.
#######
Files
Files
(789.9 MB)
Name | Size | Download all |
---|---|---|
md5:3ce642b7770bd71853affe0008b4ae02
|
119.7 MB | Download |
md5:cfcd6e0ade03988cab7ff02d7c1c8445
|
129.5 MB | Download |
md5:88390809d408d781df5fc37a2d8993c0
|
468.4 MB | Download |
md5:2ba05c9f35e6b3bbe95644d57c0bc602
|
72.3 MB | Download |