FSE-Net: Rethinking the up-sampling operation in encoder-decoder structure for retinal vessel segmentation

•We present an efficient medical image segmentation framework called FSE-Net for retinal vessel segmentation, which eliminates the up-sampling operation.•To enhance the feature extraction capability in the encoder stage, we introduce the Residual Feature Separable Block (RFSB) module, which effectiv...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Biomedical signal processing and control Jg. 90; S. 105861
Hauptverfasser: Ni, Jiajia, Mu, Wei, Pan, An, Chen, Zhengming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.04.2024
Schlagworte:
Convolutional neural network
Feature fusion
Retinal vessel segmentation
U-Net
Retinal vessel segmentation
Feature fusion
Convolutional neural network
U-Net
ISSN:1746-8094, 1746-8108
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•We present an efficient medical image segmentation framework called FSE-Net for retinal vessel segmentation, which eliminates the up-sampling operation.•To enhance the feature extraction capability in the encoder stage, we introduce the Residual Feature Separable Block (RFSB) module, which effectively extracts and refines low-level features, increasing the receptive field of the network.•We introduce the Multi-Head Feature Fusion (MFF) module, which effectively merges low-level and high-level features, streamlining encoder-decoder structure. Automatic retinal vessel segmentation plays a crucial role in the diagnosis and assessment of various ophthalmologic diseases. Currently, the primary retinal vessel segmentation algorithms are based on the encoder-decoder structure. However, these U-Net analogs suffer from the loss of both spatial and semantic information, caused by continuous up-sampling operations in the decoder structure. In this paper, we rethink the above problem and build a novel deep neural network for retinal vessel segmentation, called FSE-Net. Specifically, to address the issue of feature information loss and enhance the performance of retinal vessel segmentation, we eliminate the decoder structure. In particular, we introduced a multi-head feature fusion block (MFF) as a substitute for the continuous up-sampling operation. Additionally, the encoder stage of FSE-Net incorporates a residual feature separable block (RFSB) to further refine and distill features, thereby enhancing the capability of feature extraction. Subsequently, we employ a residual atrous spatial feature aggregate module (RASF) to expand the network's receptive field by incorporating multi-scale feature information. We conducted experiments on five widely recognized databases for retinal vessel segmentation, namely DRIVE, CHASEDB1, STARE, IOSTAR, and LES-AV. The results demonstrate that our proposed FSE-Net outperforms state-of-the-art approaches in terms of segmentation performance. Moreover, we demonstrate the feasibility of achieving superior segmentation performance without employing the traditional U-Net analog network structure.
ISSN:1746-8094
1746-8108
DOI:10.1016/j.bspc.2023.105861