2026
doi: 10.12720/jait.17.3.465-476
Dual Metric Learning for Few-Shot Weakly-Supervised Optic Disc and Cup Segmentation on Fundus Images
Pandega Abyan Zumarsyah1
,
Igi Ardiyanto1 ,
Kazuhiko Hamamoto2 ,
Hanung Adi Nugroho1,*
- 1Department of Electrical and Information Engineering, Faculty of Engineering, Universitas Gadjah Mada, Yogyakarta, Indonesia
- 2Department of Information Media Technology, School of Information Science and Technology, Tokai University, Kanagawa, Japan
- Manuscript receivedOctober 19, 2025
- revisedOctober 27, 2025
- acceptedDecember 29, 2025
- publishedMarch 10, 2026
Abstract
Segmentation of the Optic Disc (OD) and Optic Cup (OC) on fundus images is vital for glaucoma diagnosis. Deep learning has been utilized to automate this segmentation task. However, it typically requires a large number of labeled images. To address this issue, we propose Dual Metric Learning for OD and OC Segmentation (DMLOS), which requires only a few images with some of their pixels labeled. It consists of a neural network for embedding extraction, followed by dual branches to obtain prototypes and predictions. The Omni Training algorithm is used to improve data utilization and use a diverse number of shots. Meanwhile, DeepLabv3+ and miniUNet are the neural network used. We extensively evaluated DMLOS on the DRISHTI-GS, REFUGE, and RIM-ONE r3 datasets using various numbers of shots and label densities. Using 15 shots with 0.1 grid density, DMLOS achieved an Intersection over Union of 92.56% for OD and 73.08% for OC on DRISHTI-GS, surpassing other less-supervised methods. The results demonstrate the potential of DMLOS as an effective approach in low-label scenarios.
Keywords
- few-shot
- weakly-supervised
- prototypes
- sparse label
- fundus image
- segmentation
- glaucoma
How to Cite
Pandega Abyan Zumarsyah, Igi Ardiyanto, Kazuhiko Hamamoto, and Hanung Adi Nugroho, "Dual Metric Learning for Few-Shot Weakly-Supervised Optic Disc and Cup Segmentation on Fundus Images," Journal of Advances in Information Technology, vol. 17, no. 3, pp. 465-476, 2026. https://doi.org/10.12720/jait.17.3.465-476
Copyright & License
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
