用少样本提升医学影像生成质量，结构更准细节更真。
SRU-Pix2Pix: A Fusion-Driven Generator Network for Medical Image Translation with Few-Shot Learning
- 融合SEResNet与U-Net++增强特征表达和多尺度融合
- 少样本（<500图）下保持结构一致性和图像质量优势
- 适合数据稀缺的医疗影像翻译任务
磁共振成像（MRI）虽能提供精细组织信息，但受限于扫描时间长、成本高及分辨率低，临床应用受限。图像翻译近年成为缓解这些问题的有效策略。尽管Pix2Pix已在医学图像翻译中广泛应用，其潜力尚未充分挖掘。本文提出一种改进的Pix2Pix框架，融合挤压-激励残差网络（SEResNet）与U-Net++，以提升图像生成质量与结构保真度。SEResNet通过通道注意力强化关键特征表示，U-Net++则优化多尺度特征融合。同时采用简化版PatchGAN判别器，稳定训练并提升局部解剖真实性。实验表明，在少样本条件（少于500张图像）下，该方法在多个同模态MRI翻译任务中均实现一致的结构保真度与优越的图像质量，展现出强泛化能力。结果验证了对Pix2Pix的有效扩展，适用于医学图像翻译场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。