A lightweight progressive aggregation network for multi-contrast MRI super-resolution

2026/07/27 by Jiacong Chen, J Y Chen, Wenjing Chen +2
Computer Science · Engineering · #Advanced Image Processing Techniques #Generative Adversarial Networks and Image Synthesis #Sparse and Compressive Sensing Techniques

paper · doi:10.1007/s00530-026-02576-4

openalex created_date 2026/07/27 · openalex publication_date 2026/07/27 · openalex updated_date 2026/07/28

Abstract

Magnetic resonance imaging (MRI) provides diverse perspectives on anatomical structures, enabling multi-contrast super-resolution (SR) techniques that leverage complementary information across modalities to significantly enhance image quality. However, most existing multi-contrast SR methods are computationally intensive and lack lightweight solutions. In this study, we propose a novel lightweight progressive aggregation network (PAN) architecture for multi-contrast MRI SR. Our approach introduces multi-perception and residual feature aggregation mechanisms, which effectively capture and integrate anatomical details from low-resolution and reference images. Extensive experiments demonstrate that our lightweight method achieves superior efficiency, significantly outperforming other multi-contrast MRI SR methods in experiments, offering a promising solution for resource-constrained multi-contrast MRI super-resolution scenarios where computational efficiency is critical. The code can be found at https://github.com/Huaibei-normal-university-cv-laboratory/PAN .

Citations

• Omni Aggregation Networks for Lightweight Image Super-Resolution
• Residual Local Feature Network for Efficient Super-Resolution
• Activating More Pixels in Image Super-Resolution Transformer
• Multimodal Multi-Head Convolutional Attention with Various Kernel Sizes for Medical Image Super-Resolution
• Transformer-empowered Multi-scale Contextual Matching and Aggregation for Multi-contrast MRI Super-resolution
• Restormer: Efficient Transformer for High-Resolution Image Restoration
• Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution
• SwinIR: Image Restoration Using Swin Transformer
• Early Convolutions Help Transformers See Better
• Multi-Modal Transformer for Accelerated MR Imaging
• TransMed: Transformers Advance Multi-modal Medical Image Classification
• Joint multi-contrast Variational Network reconstruction (jVN) with application to rapid 2D and 3D imaging
• Time-Dependent Deep Image Prior for Dynamic MRI
• A multi-contrast MRI approach to thalamus segmentation
• Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)
• SwinIR: Image Restoration Using Swin Transformer
• Restormer: Efficient Transformer for High-Resolution Image Restoration