SAGCNet: Spatial-Aware Graph Completion Network for Missing Slice Imputation in Population CMR Imaging

2025-08-09

AI Summary

Missing slices in cardiac MRI severely compromise diagnostic accuracy. Existing volumetric reconstruction methods struggle to model local inter-slice dependencies and inadequately capture 3D spatial structure and global contextual information. To address this, we propose the Spatially Aware Graph-based Completion Network (SGCN), which introduces two novel components: a voxel-wise slice graph completion module and a voxel-space adapter. These explicitly encode slice relationships as dynamic graphs and integrate 3D spatial attention with adaptive contextual modeling—thereby eliminating reliance on complete input volumes. Built upon an end-to-end graph neural network framework, SGCN achieves high-fidelity volumetric reconstruction from sparse slice acquisitions. Evaluated on multiple public cardiac MRI benchmarks, it significantly outperforms state-of-the-art methods, maintaining both high anatomical fidelity and structural consistency even when only 3–5 slices are available.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Magnetic resonance imaging (MRI) provides detailed soft-tissue characteristics that assist in disease diagnosis and screening. However, the accuracy of clinical practice is often hindered by missing or unusable slices due to various factors. Volumetric MRI synthesis methods have been developed to address this issue by imputing missing slices from available ones. The inherent 3D nature of volumetric MRI data, such as cardiac magnetic resonance (CMR), poses significant challenges for missing slice imputation approaches, including (1) the difficulty of modeling local inter-slice correlations and dependencies of volumetric slices, and (2) the limited exploration of crucial 3D spatial information and global context. In this study, to mitigate these issues, we present Spatial-Aware Graph Completion Network (SAGCNet) to overcome the dependency on complete volumetric data, featuring two main innovations: (1) a volumetric slice graph completion module that incorporates the inter-slice relationships into a graph structure, and (2) a volumetric spatial adapter component that enables our model to effectively capture and utilize various forms of 3D spatial context. Extensive experiments on cardiac MRI datasets demonstrate that SAGCNet is capable of synthesizing absent CMR slices, outperforming competitive state-of-the-art MRI synthesis methods both quantitatively and qualitatively. Notably, our model maintains superior performance even with limited slice data.

Problem

• Imputing missing MRI slices in volumetric cardiac imaging
• Modeling inter-slice correlations in 3D CMR data
• Capturing 3D spatial context for accurate slice synthesis

Innovation

• Uses graph structure for inter-slice relationships
• Incorporates 3D spatial context adaptively
• Performs well with limited slice data