cs.CVNov 10, 2026

Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation

Authors: Chang Yu, Siqing Li, Yuanchen Liu, Zhenyu Bu, Luming Yang, Alper Yilmaz

Organizations: The Ohio State University, Columbus, OH, USA

Abstract

Diabetic retinopathy (DR) lesions vary widely in shape, and microaneurysms (MAs) span only a few pixels. We hypothesize that modeling the spatial organization of lesion regions, with global context and shape-adaptive scanning, improves the segmentation of such small and irregular lesions. To test this, we propose D2^2Mamba, which couples non-causal state space duality with deformable Mamba scanning. We evaluate it with five-fold cross-validation on the DDR dataset, comparing against representative segmentation baselines under an identical training protocol, and conduct ablations on each component. D2^2Mamba achieved the best overall performance, with 33.87% mIoU, 2.99 percentage points above the strongest baseline. The largest gain appeared on MAs, the smallest and most easily missed lesions, where Dice improved by 10.06 percentage points. These results confirm our hypothesis that spatially adaptive state space modeling benefits tiny-lesion segmentation. Code and pretrained weights are available at https://github.com/PUREPANEL1/D2Mamba.

Figures & tables

Explore similar work

CardsList
  1. PRISM-DR: Per-lesion Retinal Inference with Specialist Models for Diabetic Retinopathy

    Jul 22, 2026Zübeyr Özeren, Tansel UyarMedical Image Object DetectionDiabetic Retinopathy Grading

  2. Weakly Supervised Patch Annotation for Improved Screening of Diabetic Retinopathy

    Mar 4, 2026Shramana Dey, Abhirup Banerjee, B. Uma Shankar +2Weakly Supervised LearningDiabetic Retinopathy Grading

  3. HierarchiRetina: A Diabetic Retinopathy Screening and Grading Cascade with Heterogeneous Mixture-of-Experts Lesion Segmentation

    Oct 13, 2026Md Asif Uddin, Niloy Farhan, Rafeed Rahman +1Diabetic Retinopathy GradingRetinal Disease Classification