cs.CVAug 19, 2026

OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation

Authors: Soumili Ghosh, Debapriya Roy, Aryan Das, Bikash Santra

Organizations: IEM Saltlake,India · Techno Main Salt Lake, India · VIT Bhopal University, India · IIT Jodhpur, India

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Precise segmentation of the optic disc and cup is critical for the early detection and diagnosis of glaucoma. However, achieving consistently high performance across datasets while maintaining low computational requirements remains a significant challenge. In glaucoma detection, low-computation methods are crucial for enabling rapid, large-scale screening and facilitating deployment in resource-limited clinical environments. While deep learning models such as UNets, Vision Transformers (ViTs), and Diffusion models have demonstrated strong segmentation performance but these methods often come with substantial computational overhead. UNets are efficient at capturing local features but are limited in modeling global contextual information. Conversely, ViTs excel at long-range dependency modeling but are computationally intensive. Hybrid architectures, such as UNetR, which combine transformer-based encoders with UNet-style decoders, have shown improved performance but while incurring additional complexity. Considering these, in this work, we propose OptiModNet, a light weight novel hybrid architecture tailored for optic disc and cup segmentation. The model integrates diverse attention mechanisms at multiple stages of the network to enhance both local and global feature representation. We include an Aggregated Pyramid Loss that supervises predictions at multiple decoder depths, to promote better gradient flow and structural consistency. We evaluate OptiModNet on the REFUGE2 dataset for both optic disc and cup segmentation tasks. Our method achieves state-of-the-art performance, exceeding existing approaches by over 2.5%, while maintaining high efficiency with only 3.73 GFLOPs and 1.93M parameters. The code is available at https://github.com/SG1947/OptiModNet.

Figures & tables

Figure 1: Overview of the proposed OptiModNet.
Figure 2: (Left) Block diagram of the proposed model OptiModNet. (Right) Details of the grouped query attention module.
MethodREFUGE2-DiscREFUGE2-Cup
 DiceIoUDiceIoU
ResUNet [ 6 ]92.9085.5080.1072.30
BEAL [ 23 ]93.7086.1083.5074.10
TransBTS [ 25 ]92.3085.8083.7075.90
SwinBTS [ 13 ]95.2087.7086.3075.70
BAT [ 22 ]92.3085.8082.0073.20
Table 1: Comparative study using Dice and IoU on REFUGE2 dataset.
ModelIoUDice
U-Net [ 20 ]91.5892.76
Attention U-Net [ 17 ]92.3995.39
DeepLabV3+ [ 5 ]95.1096.29
TransUNet [ 4 ]96.2996.29
Swin-UNet [ 15 ]96.0098.79
Wang et al. [ 24 ]97.6098.79
Table 2: Segmentation performance on ORIGA dataset for 3 class classification, optic cup, optic disc and background.
Figure 3: Training and validation curves for Dice, IoU, and loss on the REFUGE2 (optic disc) dataset show increasing metric values over epochs, and decreasing loss indicating convergence.
Figure 6
Figure 7: Comparative study of our result with that of UNETR 2D model on REFUGE-2 disc dataset. For better visual comparability, we have extracted the boundary of the mask and overlaid on the input image. It can be observed that the boundary of our predicted mask (blue) aligns comparatively better with the ground truth (red).
Table 8
More in this topic

Optic Disc Segmentation

See all 8 papers

Explore similar work

CardsList
Mar 15, 2026

Joint Segmentation and Grading with Iterative Optimization for Multimodal Glaucoma Diagnosis

Accurate diagnosis of glaucoma is challenging, as early-stage changes are subtle and often lack clear structural or appearance cues. Most existing approaches rely on a single modality, such as fundus or optical coherence tomography (OCT), capturing only partial pathological information and often missing early disease progression. In this paper, we propose an iterative multimodal optimization model (IMO) for joint segmentation and grading. IMO integrates fundus and OCT features through a mid-level fusion strategy, enhanced by a cross-modal feature alignment (CMFA) module to reduce modality discrepancies. An iterative refinement decoder progressively optimizes the multimodal features through a denoising diffusion mechanism, enabling fine-grained segmentation of the optic disc and cup while supporting accurate glaucoma grading. Extensive experiments show that our method effectively integrates multimodal features, providing a comprehensive and clinically significant approach to glaucoma assessment. Source codes are available at https://github.com/warren-wzw/IMO.git.

Zhiwei Wang, Yuxing Li, Meilu Zhu +2

Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China · College of Information Engineering, Zhejiang University of Technology, Hangzhou, China

Optic Disc SegmentationGlaucoma DetectionMedical Image SegmentationCross-Modality Medical Image SegmentationMultimodal Optimization
AskPDF
Apr 10, 2026

Nested Radially Monotone Polar Occupancy Estimation: Clinically-Grounded Optic Disc and Cup Segmentation for Glaucoma Screening

Valid segmentation of the optic disc (OD) and optic cup (OC) from fundus photographs is essential for glaucoma screening. Unfortunately, existing deep learning methods do not guarantee clinical validness including star-convexity and nested structure of OD and OC, resulting corruption in diagnostic metric, especially under cross-dataset domain shift. To adress this issue, this paper proposed NPS-Net (Nested Polar Shape Network), the first framework that formulates the OD/OC segmentation as nested radially monotone polar occupancy estimation.This output representation can guarantee the aforementioned clinical validness and achieve high accuracy. Evaluated across seven public datasets, NPS-Net shows strong zero-shot generalization. On RIM-ONE, it maintains 100% anatomical validity and improves Cup Dice by 12.8% absolute over the best baseline, reducing vCDR MAE by over 56%. On PAPILA, it achieves Disc Dice of 0.9438 and Disc HD95 of 2.78 px, an 83% reduction over the best competing method.

Rimsa Goperma, Rojan Basnet, Liang Zhao

Graduate School of Advanced Integrated Studies in Human Survivability (GSAIS), Kyoto University, Kyoto 606-8306, Japan

Optic Disc SegmentationGlaucoma DetectionMedical Image SegmentationOphthalmic Image AnalysisFundus ImagingMedical Diagnosis+1
AskPDF
Sep 6, 2026

Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detection

Glaucoma is a progressive optic neuropathy characterized by irreversible damage to the optic nerve, making timely diagnosis critical to prevent permanent vision loss. Although deep learning has demonstrated promising performance in automated glaucoma detection, existing approaches often overlook feature refinement, suffer from class imbalance, and rely on individual classifiers that limit prediction robustness. To address these challenges, this paper proposes a hybrid glaucoma detection framework that integrates attention-enhanced deep feature extraction with heterogeneous ensemble learning. Specifically, deep representations are extracted using InceptionV3 and subsequently refined by incorporating the Convolutional Block Attention Module (CBAM) to enhance discriminative retinal features. To improve classification robustness, the extracted features are classified using multiple machine learning models together with Single-Level Ensemble (SLE) and Double-Level Ensemble (DLE) strategies, while SMOTE combined with Tomek Links (SMOTE+TL) is employed to alleviate class imbalance. Furthermore, a systematic comparison of handcrafted, deep, and attention-enhanced deep feature representations is conducted. Experimental evaluation on two public retinal fundus datasets demonstrates that deep feature-based methods consistently outperform handcrafted feature-based methods, while the proposed attention-enhanced framework achieves the best overall performance. Furthermore, Grad-CAM visualizations confirm that the proposed model focuses on clinically relevant retinal regions, providing interpretable evidence on the model's prediction process.

Abdullah Al Shafi, Nishat Sadaf Lira, Abrar Hasan +2

Department of CSE, Khulna University of Engineering & Technology, Bangladesh · Department of CSE, Daffodil International University, Bangladesh · Department of SWE, Green University of Bangladesh

Glaucoma DetectionEnsemble LearningDeep Ensembles
AskPDF