SPNet: A novel deep neural network for retinal vessel segmentation based on shared decoder and pyramid-like loss

Xu, Geng-Xin; Ren, Chuan-Xian

doi:10.1016/j.neucom.2022.12.039

Cited by 5 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A robust Orientation and Context Entangled Network having the ability of getting intricate orientation and context data of the retinal vasculature is used in OCE-Net [22] whereas a combination of multitask segmentation network and fusion network were used to segment retinal vasculature [23]. SPNet [24] introduced a shared decoder and pyramid-like loss for superior segmentation of vessels. A directed graph search-based multi-attentive neural network approach is used for automatic segmentation of vascular network [25].…”

Section: Introductionmentioning

confidence: 99%

MSR U-Net: An Improved U-Net Model for Retinal Blood Vessel Segmentation

Kande,

Ravi,

Kande

et al. 2024

IEEE Access

View full text Add to dashboard Cite

For proper diagnosis and treatment of various retinal conditions, retinal blood vessel segmentation is crucial. Delineation of vessels with varying thicknesses is critical for detecting disease symptoms. However, this task is challenging due to inadequate contextual information, complex vessel morphology, and lesion confusion. Many recent works employed several variations of CNNs with U-Net as baseline model for segmenting blood vessels from the fundus images. However, the existing methods still lack in generalizing the vessels well enough, indicating scope for improvement in this challenging problem of vessel segmentation. We introduce a novel Multi-Scale Residual (MSR) U-Net model in this study replacing convolution block and skip connections with an improved Multi-Scale Residual (MSR) convolution block and Bottleneck residual paths (B-Res paths) respectively. Specifically, STARE, DRIVE, and CHASE_DB1 datasets of fundus images are used to validate the proposed segmentation method. Our experimental results consistently showcase better/comparable performances when compared with current approaches, achieving higher area under receiver operator characteristic (AUC), accuracy, and F1 score. in segmenting blood vessels of varying thicknesses, even in scenarios with diverse contextual information, the presence of coexisting lesions, and complex vessel morphologies.

show abstract