SSMD-UNet: semi-supervised multi-task decoders network for diabetic retinopathy segmentation
Article
Ullah, Zahid, Akram, Muhammad, Latif, Siddique, Khan, Asifullah and Gwak, Jeonghwan. 2023. "SSMD-UNet: semi-supervised multi-task decoders network for diabetic retinopathy segmentation." Scientific Reports. 13 (1). https://doi.org/10.1038/s41598-023-36311-0
Article Title | SSMD-UNet: semi-supervised multi-task decoders network for diabetic retinopathy segmentation |
---|---|
ERA Journal ID | 201487 |
Article Category | Article |
Authors | Ullah, Zahid, Akram, Muhammad, Latif, Siddique, Khan, Asifullah and Gwak, Jeonghwan |
Journal Title | Scientific Reports |
Journal Citation | 13 (1) |
Article Number | 9087 |
Number of Pages | 16 |
Year | 2023 |
Publisher | Nature Publishing Group |
Place of Publication | United Kingdom |
ISSN | 2045-2322 |
Digital Object Identifier (DOI) | https://doi.org/10.1038/s41598-023-36311-0 |
Web Address (URL) | https://www.nature.com/articles/s41598-023-36311-0 |
Abstract | Diabetic retinopathy (DR) is a diabetes complication that can cause vision loss among patients due to damage to blood vessels in the retina. Early retinal screening can avoid the severe consequences of DR and enable timely treatment. Nowadays, researchers are trying to develop automated deep learning-based DR segmentation tools using retinal fundus images to help Ophthalmologists with DR screening and early diagnosis. However, recent studies are unable to design accurate models due to the unavailability of larger training data with consistent and fine-grained annotations. To address this problem, we propose a semi-supervised multitask learning approach that exploits widely available unlabelled data (i.e., Kaggle-EyePACS) to improve DR segmentation performance. The proposed model consists of novel multi-decoder architecture and involves both unsupervised and supervised learning phases. The model is trained for the unsupervised auxiliary task to effectively learn from additional unlabelled data and improve the performance of the primary task of DR segmentation. The proposed technique is rigorously evaluated on two publicly available datasets (i.e., FGADR and IDRiD) and results show that the proposed technique not only outperforms existing state-of-the-art techniques but also exhibits improved generalisation and robustness for cross-data evaluation. |
Keywords | SSMD‑UNet; Diabetic retinopathy |
ANZSRC Field of Research 2020 | 4206. Public health |
Byline Affiliations | Korea National University of Transportation, South Korea |
Seoul National University, Korea | |
University of Southern Queensland | |
Pakistan Institute of Engineering and Applied Sciences (PIEAS), Pakistan |
Permalink -
https://research.usq.edu.au/item/z2701/ssmd-unet-semi-supervised-multi-task-decoders-network-for-diabetic-retinopathy-segmentation
Download files
54
total views31
total downloads5
views this month1
downloads this month