MA‐ResUNet: Multi‐attention optic cup and optic disc segmentation based on improved U‐Net
Glaucoma poses a significant threat to vision, capable of causing irreversible damage and, in severe instances, leading to permanent blindness. Accurate optic cup (OC) and optic disc (OD) segmentation are essential in glaucoma screening. In this study, a novel OC and OD segmentation approach is prop...
Gespeichert in:
Veröffentlicht in: | IET image processing 2024-10, Vol.18 (12), p.3128-3142 |
---|---|
Hauptverfasser: | , , , , , , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Glaucoma poses a significant threat to vision, capable of causing irreversible damage and, in severe instances, leading to permanent blindness. Accurate optic cup (OC) and optic disc (OD) segmentation are essential in glaucoma screening. In this study, a novel OC and OD segmentation approach is proposed. Based on U‐Net, it is optimized by introducing cardinality dimensions. Moreover, attention gates are implemented to reinforce salient features while suppressing irrelevant information. Additionally, a convolutional block attention module (CBAM) is integrated into the decoder segment. This fusion hones in on effective information in both channel and spatial dimensions. Meanwhile, an image processing procedure is proposed for image normalization and enhancement. All of these increase the accuracy of the model. This model is evaluated on the ORIGA and REFUGE datasets, demonstrating the model's superiority in OC and OD segmentation compared to the state‐of‐the‐art methods. Additionally, after the proposed image processing, cup‐to‐disc ratio (CDR) prediction on a batch of 155 in‐house fundus images yields an absolute CDR error of 0.099, which is reduced by 0.04 compared to the case where only conventional processing was performed.
This study presents a groundbreaking deep learning model named MA‐ResUNet, which is built upon the U‐Net architecture but enhanced by integrating ResNeXt blocks inspired by aggregated residual transformations. Attention gates have been strategically incorporated to strengthen prominent features conveyed through the encoder's skip connection, simultaneously mitigating the influence of irrelevant information. Furthermore, a convolutional block attention module (CBAM) is seamlessly integrated into the decoder segment post‐concatenation, facilitating the fusion of salient features from the feature map with comprehensive global semantic information. Besides, a fundus image processing procedure is proposed to improve the model's accuracy. |
---|---|
ISSN: | 1751-9659 1751-9667 |
DOI: | 10.1049/ipr2.13160 |