Self-Supervised Multimodal Reconstruction Pre-training for Retinal Computer-Aided Diagnosis
Use this link to cite
http://hdl.handle.net/2183/28845
Except where otherwise noted, this item's license is described as Atribución-NoComercial-SinDerivadas 4.0 Internacional
Collections
- GI-VARPA - Artigos [54]
Metadata
Show full item recordTitle
Self-Supervised Multimodal Reconstruction Pre-training for Retinal Computer-Aided DiagnosisDate
2021Citation
Álvaro S. Hervella, José Rouco, Jorge Novo, Marcos Ortega, Self-supervised multimodal reconstruction pre-training for retinal computer-aided diagnosis, Expert Systems with Applications, Volume 185, 2021, 115598, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2021.115598. (https://www.sciencedirect.com/science/article/pii/S0957417421009982)
Abstract
[Abstract] Computer-aided diagnosis using retinal fundus images is crucial for the early detection of many ocular and systemic diseases. Nowadays, deep learning-based approaches are commonly used for this purpose. However, training deep neural networks usually requires a large amount of annotated data, which is not always available. In practice, this issue is commonly mitigated with different techniques, such as data augmentation or transfer learning. Nevertheless, the latter is typically faced using networks that were pre-trained on additional annotated data.
An emerging alternative to the traditional transfer learning source tasks is the use of self-supervised tasks that do not require manually annotated data for training. In that regard, we propose a novel self-supervised visual learning strategy for improving the retinal computer-aided diagnosis systems using unlabeled multimodal data. In particular, we explore the use of a multimodal reconstruction task between complementary retinal imaging modalities. This allows to take advantage of existent unlabeled multimodal data in the medical domain, improving the diagnosis of different ocular diseases with additional domain-specific knowledge that does not rely on manual annotation.
To validate and analyze the proposed approach, we performed several experiments aiming at the diagnosis of different diseases, including two of the most prevalent impairing ocular disorders: glaucoma and age-related macular degeneration. Additionally, the advantages of the proposed approach are clearly demonstrated in the comparisons that we perform against both the common fully-supervised approaches in the literature as well as current self-supervised alternatives for retinal computer-aided diagnosis. In general, the results show a satisfactory performance of our proposal, which improves existing alternatives by leveraging the unlabeled multimodal visual data that is commonly available in the medical field.
Keywords
Deep learning
Medical imaging
Self-supervised learning
Eye fundus
Transfer learning
Computer-aided diagnosis
Medical imaging
Self-supervised learning
Eye fundus
Transfer learning
Computer-aided diagnosis
Description
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
Editor version
Rights
Atribución-NoComercial-SinDerivadas 4.0 Internacional