Skip to main content

Malaviya National Institute of Technology Jaipur

2 related articles

Subscribe to updates

Scientific Reports Oct 17, 2026
Retinal grading stops reading one raw photo: separate lesion and vessel paths reach 93.32% on five-grade diabetic retinopathy staging
Retinal disease grading has mostly relied on raw color fundus photographs, where low-contrast lesions and thin vessels are easily lost to illumination and noise. F2D-RetinaNet sends an enhanced green channel and a vessel map through two separate branches and fuses them into one grading decision. On APTOS 2019 five-grade diabetic retinopathy staging it reaches 93.32% accuracy, 3.25 points above the RGB-only baseline, and 87.14% on the external DREAM-RFI set after overlapping images were excluded.
Retinal disease grading has mostly relied on raw color fundus photographs, where low-contrast lesions and thin vessels are easily lost to illumination and noise. F2D-RetinaNet sends an enhanced green channel and a vessel map through two separate branches and fuses them into one grading decision. On APTOS 2019 five-grade diabetic retinopathy staging it reaches 93.32% accuracy, 3.25 points above the RGB-only baseline, and 87.14% on the external DREAM-RFI set after overlapping images were excluded.
Malaviya National Institute of Technology Jaipur University of Johannesburg
Mukesh Delu（First author）Pilani Nkomozepi（Corresponding author）Priyanka Harjule（Corresponding author）
F2D-RetinaNet FADHE FHAU-Net Retinal Vessel Segmentation Diabetic Retinopathy Grading
arXiv Sep 24, 2026
SRMA-Mamba lifts cirrhotic liver MRI segmentation to 92.95% mDSC on T1W and 86.25% on T2W in CirrMRI600+ while cutting compute
The work introduces SRMA-Mamba, a Mamba-based network that uses the Spatial Anatomy-Based Mamba (SABMamba) module to perform selective scans across sagittal, coronal, and axial anatomical planes for a global spatial context, and the Spatial Reverse Mamba Attention (SRMA) module to progressively refine boundaries from a coarse segmentation map and hierarchical encoder features, reporting better segmentation metrics than SegResNet, UX-Net, MedNeXt, SwinUNETR, SwinUNETRv2, and SegMamba on CirrMRI600+ T1W and T2W, with fewer parameters and GFLOPs than SegMamba.
The work introduces SRMA-Mamba, a Mamba-based network that uses the Spatial Anatomy-Based Mamba (SABMamba) module to perform selective scans across sagittal, coronal, and axial anatomical planes for a global spatial context, and the Spatial Reverse Mamba Attention (SRMA) module to progressively refine boundaries from a coarse segmentation map and hierarchical encoder features, reporting better segmentation metrics than SegResNet, UX-Net, MedNeXt, SwinUNETR, SwinUNETRv2, and SegMamba on CirrMRI600+ T1W and T2W, with fewer parameters and GFLOPs than SegMamba.
Northwestern University University of South Dakota Malaviya National Institute of Technology Jaipur Aalto University Chongqing University of Posts and Telecommunications
Jun Zeng（First author）Debesh Jha（Corresponding author）
SRMA-Mamba Pathological Liver Segmentation Spatial Anatomy-Based Mamba (SABMamba)Spatial Reverse Mamba Attention (SRMA)Anatomy-Based Selective Scan (ABSS)

You’re all caught up