RT Journal Article
SR Electronic
T1 Self-supervised retinal thickness prediction enables deep learning from unlabeled data to boost classification of diabetic retinopathy
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 861757
DO 10.1101/861757
A1 Olle G. Holmberg
A1 Niklas D. Köhler
A1 Thiago Martins
A1 Jakob Siedlecki
A1 Tina Herold
A1 Leonie Keidel
A1 Ben Asani
A1 Johannes Schiefelbein
A1 Siegfried Priglinger
A1 Karsten U. Kortuem
A1 Fabian J. Theis
YR 2019
UL http://biorxiv.org/content/early/2019/12/02/861757.abstract
AB 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.