An Anisotropic Cross-View Texture Transfer with Multi-Reference Non-Local Attention for CT Slice Interpolation

2025-09-24

AI Summary

CT volumes often exhibit severe anisotropy due to clinically acquired large slice thicknesses, resulting in substantially lower through-plane resolution compared to in-plane resolution—degrading diagnostic accuracy. To address this, we propose a cross-view texture transfer method that systematically exploits the inherent anisotropic prior of CT data. Specifically, we design a multi-reference non-local attention mechanism to extract and aggregate high-frequency texture features from multiple high-resolution in-plane slices, thereby guiding super-resolution reconstruction of low-resolution through-plane slices. Unlike conventional single-image super-resolution or interpolation-based approaches, our method establishes an end-to-end cross-view texture propagation network. Evaluated on multiple public CT datasets—including real-world paired benchmarks—our approach consistently outperforms state-of-the-art methods, effectively restoring isotropic, high-resolution CT volumes with improved structural fidelity and diagnostic utility.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Computed tomography (CT) is one of the most widely used non-invasive imaging modalities for medical diagnosis. In clinical practice, CT images are usually acquired with large slice thicknesses due to the high cost of memory storage and operation time, resulting in an anisotropic CT volume with much lower inter-slice resolution than in-plane resolution. Since such inconsistent resolution may lead to difficulties in disease diagnosis, deep learning-based volumetric super-resolution methods have been developed to improve inter-slice resolution. Most existing methods conduct single-image super-resolution on the through-plane or synthesize intermediate slices from adjacent slices; however, the anisotropic characteristic of 3D CT volume has not been well explored. In this paper, we propose a novel cross-view texture transfer approach for CT slice interpolation by fully utilizing the anisotropic nature of 3D CT volume. Specifically, we design a unique framework that takes high-resolution in-plane texture details as a reference and transfers them to low-resolution through-plane images. To this end, we introduce a multi-reference non-local attention module that extracts meaningful features for reconstructing through-plane high-frequency details from multiple in-plane images. Through extensive experiments, we demonstrate that our method performs significantly better in CT slice interpolation than existing competing methods on public CT datasets including a real-paired benchmark, verifying the effectiveness of the proposed framework. The source code of this work is available at https://github.com/khuhm/ACVTT.

Problem

• Improving anisotropic CT volume resolution with inconsistent slice thickness
• Transferring high-resolution in-plane textures to low-resolution through-plane images
• Reconstructing through-plane high-frequency details using multi-reference attention

Innovation

• Cross-view texture transfer for slice interpolation
• Multi-reference non-local attention module
• Utilizes high-resolution in-plane as reference