提出统一框架，评估多模态医学图像超分辨率模型表现。
MedSR-Vision: Deep Learning Framework for Multi-Domain Medical Image Super-Resolution
- 构建跨五种模态的统一评估框架，支持×2至×4放大。
- Real-ESRGAN在高倍率下边缘恢复最好，SwinIR更保结构，SRCNN低倍率最稳。
- 为临床部署提供选型指南，推动医学超分辨研究标准化。
医学图像超分辨率（MedSR）对提升MRI、CT、X光、超声和眼底成像等多模态诊断精度至关重要。尽管深度学习发展迅速，但在保持解剖准确性、感知质量及跨域泛化方面仍面临挑战。本文提出MedSR-Vision，一个统一的深度学习框架，用于评估和比较五种模态（脑MRI、胸部X光、肾超声、肾结石CT、脊柱MRI）在×2、×3、×4放大尺度下的超分辨率模型表现。选用SRCNN、SwinIR和Real-ESRGAN三类代表性模型，通过保真度、感知真实性和锐利度等多指标进行基准测试。实验表明：Real-ESRGAN在高倍放大下具有最优感知质量和边缘恢复能力；SwinIR在结构与诊断特征保持上表现突出；SRCNN在低倍放大时兼具高效与稳定。研究结果揭示了各模态的性能差异，为临床影像工作流中的模型选型提供实用指导，并建立标准化评估体系，助力未来医学超分辨率研究与应用。
原文摘要 · Abstract (English)
Medical image super-resolution (MedSR) is essential for improving diagnostic precision across diverse imaging modalities such as MRI, CT, X-ray, Ultrasound, and Fundus imaging. Despite rapid advances in deep learning, challenges remain in preserving anatomical accuracy, maintaining perceptual quality, and generalizing across medical domains. This paper presents MedSR-Vision, a novel unified deep learning framework for evaluating and comparing super-resolution models across five modalities: Brain MRI, Chest X-ray, Renal Ultrasound, Nephrolithiasis CT, and Spine MRI, at magnification scales of $\times2$, $\times3$, and $\times4$. Three representative models namely SRCNN, SwinIR, and Real-ESRGAN are benchmarked using multiple quantitative metrics encompassing fidelity, perceptual realism, and sharpness. Experimental analysis demonstrates that Real-ESRGAN achieves superior perceptual quality and edge recovery at higher scales, SwinIR excels in preserving structural and diagnostic features, and SRCNN provides efficient and stable performance at lower magnifications. The results establish domain-specific insights and practical guidelines for model selection in clinical imaging workflows, offering a standardized evaluation framework for future medical image super-resolution research and deployment.
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。