Masked Image Modelling for retinal OCT understanding
This work addresses the challenge of medical image analysis for retinal OCT understanding, offering a scalable self-supervised method with public resources, though it is incremental as it adapts an existing technique to a new domain.
The authors tackled the problem of learning effective representations for retinal OCT images by applying Masked Autoencoders (MAE) to 700K images from 41K patients, achieving strong performance on 6 downstream tasks and improving multimodal applications with IR fundus images.
This work explores the effectiveness of masked image modelling for learning representations of retinal OCT images. To this end, we leverage Masked Autoencoders (MAE), a simple and scalable method for self-supervised learning, to obtain a powerful and general representation for OCT images by training on 700K OCT images from 41K patients collected under real world clinical settings. We also provide the first extensive evaluation for a model of OCT on a challenging battery of 6 downstream tasks. Our model achieves strong performance when fully finetuned but can also serve as a versatile frozen feature extractor for many tasks using lightweight adapters. Furthermore, we propose an extension of the MAE pretraining to fuse OCT with an auxiliary modality, namely, IR fundus images and learn a joint model for both. We demonstrate our approach improves performance on a multimodal downstream application. Our experiments utilize most publicly available OCT datasets, thus enabling future comparisons. Our code and model weights are publicly available https://github.com/TheoPis/MIM_OCT.