SRU-Pix2Pix: A Fusion-Driven Generator Network for Medical Image Translation with Few-Shot Learning
Authors:
- Xihe QiuXQXihe Qiu
- Yang DaiYDYang Dai
- Xiaoyu TanXTXiaoyu Tan
- Sijia LiSLSijia Li
- Fenghao SunFSFenghao Sun
- Lu GanLGLu Gan
- Liang LiuLLLiang Liu
Preprint
Abstract
Magnetic Resonance Imaging (MRI) provides detailed tissue information, but its clinical application is limited by long acquisition time, high cost, and restricted resolution. Image translation has recently gained attention as a strategy to address these limitations. Although Pix2Pix has been widely applied in medical image translation, its potential has not been fully explored. In this study, we propose an enhanced Pix2Pix framework that integrates Squeeze-and-Excitation Residual Networks (SEResNet) and U-Net++ to improve image generation quality and structural fidelity. SEResNet strengthens critical feature representation through channel attention, while U-Net++ enhances multi-scale feature fusion. A simplified PatchGAN discriminator further stabilizes training and refines local anatomical realism. Experimental results demonstrate that under few-shot conditions with fewer than 500 images, the proposed method achieves consistent structural fidelity and superior image quality across multiple intra-modality MRI translation tasks, showing strong generalization ability. These results suggest an effective extension of Pix2Pix for medical image translation.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image GenerationIEEE Journal of Biomedical and Health Informatics, 2025
- LFDT-Fusion: A latent feature-guided diffusion Transformer model for general image fusionInformation Fusion, 2024
- GAN review: Models and medical image fusion applicationsInformation Fusion, 2022
- Bridging 2D and 3D segmentation networks for computation-efficient volumetric medical image segmentation: An empirical study of 2.5D solutionsComputerized Medical Imaging and Graphics, 2022
- DiCyc: GAN-based deformation invariant cross-domain information fusion for medical image synthesisInformation Fusion, 2021
- Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural networkJapanese Journal of Radiology, 2018
- A digital 3D atlas of the marmoset brain based on multi-modal MRINeuroImage, 2018
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic featuresScientific Data, 2017
- The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)IEEE Transactions on Medical Imaging, 2015