Dynamic graph convolutional autoencoder with node-attribute-wise attention for kidney and tumor segmentation from CT volumes

Extraction and integration of semantic connections, spatial relations and dependencies are critical in volumetric image segmentation. This is a challenging issue, especially when there are long-distance objects with close semantic relations and neighboring objects with indistinct boundaries. We prop...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Knowledge-based systems Jg. 236; S. 107360
Hauptverfasser: Xuan, Ping, Cui, Hui, Zhang, Hongda, Zhang, Tiangang, Wang, Linlin, Nakaguchi, Toshiya, Duh, Henry B.L.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 25.01.2022
Elsevier Science Ltd
Schlagworte:
Ablation
Attention
Attributes
Boundaries
Computed tomography
Computerization
Dynamic graph convolutional autoencoder
Extraction
Graph node attributes
Image segmentation
Inference
Innovations
Kidney and tumor segmentation
Kidneys
Long-distance relationship between nodes
Medical imaging
Node-attribute-wise attention
Nodes
Segmentation
Semantic relations
Semantics
Tomography
Topology
Tumors
Node-attribute-wise attention
Kidney and tumor segmentation
Long-distance relationship between nodes
Graph node attributes
Dynamic graph convolutional autoencoder
ISSN:0950-7051, 1872-7409
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Extraction and integration of semantic connections, spatial relations and dependencies are critical in volumetric image segmentation. This is a challenging issue, especially when there are long-distance objects with close semantic relations and neighboring objects with indistinct boundaries. We propose a novel dynamic graph convolution (DGC) autoencoder with node-attribute-wise attention (NodeAttri-Attention) for relation inference and reasoning, with applications on kidney and tumor segmentation from computerized tomography (CT) volumes. We first introduce a new graph construction strategy for 3D volumetric image data, where graph node attributes and connections represent topological relations and high-level correlations. Then NodeAttri-Attention mechanism is proposed to obtain attention-enhanced node attributes by discriminating adaptive contributions of various features. Finally, the DGC strategy is designed to learn and integrate the complex and underlying correlations across image regions. Our DGC dynamically updates graph topology and node attributes as the graph convolutional layer gradually deepens. Experimental results and ablation studies demonstrated the effectiveness of each of our major innovations in NodeAttri-Attention DGC, especially when objects are with weak boundaries, irregular shapes, and various sizes. The improved segmentation results of embedding NodeAttri-Attention DGC to different segmentation backbones show the generality of DGC autoencoder.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2021.107360