用深度学习提升前列腺MRI切片分辨率，关键在问题怎么设计。
Deep Learning for MRI Slice Interpolation: The Critical Role of Problem Formulation
- 改用邻近切片（i-1, i+1）替代远距离切片（i-2, i+2）进行插值
- U-Net模型达到PSNR 30.08 dB、SSIM 0.898，较线性插值提升10.1%
- 问题设定比网络结构更重要，影响可达架构复杂度的290倍
临床MRI的跨平面分辨率通常远低于平面内分辨率，限制了诊断价值。本文研究深度学习在前列腺成像中插值中间切片的方法，有效将跨平面分辨率提升一倍。评估了五种架构（CNN、U-Net、两种GAN变体、DDPM），发现问题设定的影响远超模型复杂度。通过将插值任务改为利用相邻切片（i-1, i+1）而非远距离切片（i-2, i+2），所有确定性架构的SSIM性能提升58%。U-Net表现最佳，PSNR达30.08 dB，SSIM为0.898，较线性插值基准提升10.1%。DDPM因随机生成与确定性重建需求不匹配，重建质量较差。结果表明，在医学图像任务中，问题设定的影响可达模型复杂度的290倍。
原文摘要 · Abstract (English)
Through-plane resolution in clinical MRI is typically much coarser than in-plane resolution, limiting diagnostic utility. This work investigates deep learning approaches to interpolate intermediate MRI slices in prostate imaging, effectively doubling through-plane resolution. I evaluated five architectures (CNN, U-Net, two GAN variants, and DDPM) and discovered that problem formulation has dramatically more impact than architectural complexity. By reformulating the interpolation task to use adjacent slices (i-1, i+1) rather than distant slices (i-2, i+2), I achieved a 58% improvement in SSIM performance across all deterministic architectures. The U-Net model achieved the best results with PSNR of 30.08 dB and SSIM of 0.898, representing a 10.1% improvement over linear interpolation baseline. A DDPM was also evaluated but showed poor reconstruction quality due to fundamental mismatch between stochastic generation and deterministic reconstruction requirements. These findings demonstrate that problem formulation can have 290x more impact than architectural sophistication in medical imaging tasks.
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。