arXiv Computer Vision
Bayesian-Optimized Superpixel-GrabCut for Traceable Optic Disc Segmentation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 30
Hybrid Approach for Enhancing Lesion Segmentation in Fundus Images
arXiv:2509.25549v3 Announce Type: replace-cross Abstract: Choroidal nevi are common benign pigmented lesions in the eye, with a small risk of transforming into melanoma. Early detection is critical t...
arXiv AI
Jul 20
Spatial Normalization for Cross-Domain Retinal Layer Segmentation in Optical Coherence Tomography
arXiv:2607. 16065v1 Announce Type: cross Abstract: Retinal layer segmentation in Optical Coherence Tomography (OCT) is a fundamental step for extracting quantitative biomarkers of retinal structure.
arXiv Computer Vision
Aug 28
Automated 2D and 3D Segmentation of AMD and DME Lesions in OCT
This study presents four deep‑learning pipelines—two‑dimensional and three‑dimensional—for segmenting age‑related macular degeneration (AMD) and diabetic macular edema (DME) lesions in optical coherence tomography (OCT) images. The models achieve Dice scores between 0.76 and 0.82 and demonstrate strong volumetric and surface calibration (r_vol, r_surf ≥ 0.97) on an in‑domain validation set. Generalization was assessed on the OLIVES clinical cohort using proxy metrics such as biomarker AUROC, central subfield thickness correlation, and longitudinal concordance, showing that the predictions still track clinical biomarkers outside the training distribution, albeit with reduced strength.
arXiv Computer Vision
Oct 16
FPG-Seg: Annotation-free Retinal Vessel Topology Segmentation
FPG-Seg is an annotation‑free pipeline for retinal vessel segmentation that combines classical vesselness filtering, Bayesian deep learning, and topology‑aware graph reconstruction. It achieves a clDice score of 0.74–0.78, which is 86–98% of the performance of a fully‑supervised baseline, across four benchmark datasets. The work also presents the first performance benchmark of an annotation‑free vessel segmentation method on the FIVES dataset.
arXiv Computer Vision
Sep 1
retinalysis-vascx: An explainable software toolbox for the extraction of retinal vascular biomarkers
arXiv:2602.08580v4 Announce Type: replace-cross Abstract: Automatic extraction of retinal vascular biomarkers from color fundus images (CFI) is crucial for large-scale studies of the retinal vasculat...
arXiv AI
Aug 20
OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation
OptiModNet is a lightweight UNet‑Transformer hybrid designed for optic disc and cup segmentation. It incorporates grouped‑query and channel attention across multiple stages, along with an Aggregated Pyramid Loss to improve gradient flow and structural consistency. Evaluated on the REFUGE2 dataset, it surpasses existing methods by over 2.5 % while using only 3.73 GFLOPs and 1.93 M parameters.