SRU-Pix2Pix: A Fusion-Driven Generator Network for Medical Image Translation with Few-Shot Learning

TL;DR

This paper introduces SRU-Pix2Pix, an advanced medical image translation network that combines SEResNet and U-Net++ to enhance image quality and structural accuracy, especially effective in few-shot MRI translation scenarios.

Contribution

The study presents a novel fusion-driven generator network that extends Pix2Pix with SEResNet and U-Net++, improving performance in few-shot medical image translation tasks.

Findings

Achieves high structural fidelity with fewer than 500 training images.

Demonstrates superior image quality across multiple MRI translation tasks.

Shows strong generalization ability in limited data scenarios.

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.