# Deep Retinal Image Segmentation with Regularization Under Geometric Priors

arXiv: https://arxiv.org/abs/1909.09175 · HTML: https://mlsanity.com/paper/1909.09175/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2019.

## Built on by (most cited first, 13 of 13)

- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Local Intensity Order Transformation for Robust Curvilinear Object Segmentation](https://mlsanity.com/paper/2202.12587/) (2022)
- [Recent Progress in Transformer-based Medical Image Analysis](https://mlsanity.com/paper/2208.06643/) (2022)
- [Orientation and Context Entangled Network for Retinal Vessel Segmentation](https://mlsanity.com/paper/2207.11396/) (2022)
- [RSF-Conv: Rotation-and-Scale Equivariant Fourier Parameterized Convolution for Retinal Vessel Segmentation](https://mlsanity.com/paper/2309.15638/) (2023)
- [Supervision by Denoising for Medical Image Segmentation](https://mlsanity.com/paper/2202.02952/) (2022)
- [SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss](https://mlsanity.com/paper/2202.09515/) (2022)
- [Retinal Vessel Segmentation with Deep Graph and Capsule Reasoning](https://mlsanity.com/paper/2409.11508/) (2024)
- [UCS: A Universal Model for Curvilinear Structure Segmentation](https://mlsanity.com/paper/2504.04034/) (2025)
- [CurvSegFlow: Time-Conditioned Flow Matching for Robust Segmentation of Curvilinear Structures in Noisy Biomedical Images](https://mlsanity.com/paper/2606.21608/) (2026)
- [Multi-Class Micro-CT Image Segmentation Using Sparse Regularized Deep Networks](https://mlsanity.com/paper/2104.10705/) (2021)
- [Overview of Deep Learning Methods for Retinal Vessel Segmentation](https://mlsanity.com/paper/2306.06116/) (2023)
- [TransUNext: towards a more advanced U-shaped framework for automatic vessel segmentation in the fundus image](https://mlsanity.com/paper/2411.02724/) (2024)

## Abstract (arXiv)

Vessel segmentation of retinal images is a key diagnostic capability in ophthalmology. This problem faces several challenges including low contrast, variable vessel size and thickness, and presence of interfering pathology such as micro-aneurysms and hemorrhages. Early approaches addressing this problem employed hand-crafted filters to capture vessel structures, accompanied by morphological post-processing. More recently, deep learning techniques have been employed with significantly enhanced segmentation accuracy. We propose a novel domain enriched deep network that consists of two components: 1) a representation network that learns geometric features specific to retinal images, and 2) a custom designed computationally efficient residual task network that utilizes the features obtained from the representation layer to perform pixel-level segmentation. The representation and task networks are em jointly learned for any given training set. To obtain physically meaningful and practically effective representation filters, we propose two new constraints that are inspired by expected prior structure on these filters: 1) orientation constraint that promotes geometric diversity of curvilinear features, and 2) a data adaptive noise regularizer that penalizes false positives. Multi-scale extensions are developed to enable accurate detection of thin vessels. Experiments performed on three challenging benchmark databases under a variety of training scenarios show that the proposed prior guided deep network outperforms state of the art alternatives as measured by common evaluation metrics, while being more economical in network size and inference time.