用于单被试扩散MRI超分辨率的先验引导隐式神经表示
Prior-Guided Implicit Neural Representations for Single-Subject Diffusion MRI Super-Resolution
另 1 家 · 查看机构详情
- Brigham and Women’s Hospital（布莱根妇女医院）
- Harvard Medical School（哈佛医学院）
- Technical University of Munich（慕尼黑工业大学）
- University of South Carolina（南卡罗来纳大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文提出一种先在高分辨率模板预训练、再经配准微调适配被试扫描的迁移学习框架，用于单被试扩散MRI超分辨率，在HCP数据上的4倍超分辨率任务中性能优于基线及其他INR方法。
中文摘要 AI 辅助
解析脑白质中复杂的纤维几何结构需要高分辨率扩散MRI，但这会导致采集时间过长，因此许多临床方案选择低分辨率扫描，给下游的微观结构估计和纤维束成像带来挑战。隐式神经表示（INR）可对扩散信号进行连续建模，通过在任意空间坐标查询网络实现原生单被试超分辨率，但现有方法常存在训练时间长的问题，且缺乏整合解剖学先验以通过约束合理重建空间来正则化超分辨率的机制。为解决这些局限，本文提出一种新型迁移学习框架：先在高分辨率模板上预训练INR，再通过配准和微调使其适配被试特异性扫描。针对Human Connectome Project（HCP）数据中从5mm到1.25mm的4倍层内超分辨率任务，与近期基线方法相比，本文方法将归一化均方根误差（NRMSE）降低36%-49%，特征相似性指数（FSIM）提升24%-43%，训练速度快6倍，在图像质量和特定领域指标上均优于基于INR的竞争方法。代码可在项目页面获取，链接为this https URL。
英文摘要
Resolving complex fiber geometries in brain white matter requires high-resolution diffusion MRI at the cost of long acquisition times. This leads many clinical protocols to opt for low-resolution scans, making downstream microstructure estimation and tractography challenging. Implicit neural representations (INRs) can model the diffusion signal continuously, enabling native single-subject super-resolution by querying the network at arbitrary spatial coordinates, yet existing methods often suffer from long training times and lack a mechanism to incorporate anatomical priors to regularize super-resolution by constraining the space of plausible reconstructions. To address these limitations, we propose a novel transfer-learning framework that pre-trains an INR on a high-resolution template and then adapts it to subject-specific scans via registration and fine-tuning. For $4\times$ through-plane super-resolution from 5 mm to 1.25 mm on Human Connectome Project (HCP) data, our method reduces NRMSE by 36-49% and increases FSIM by 24-43% over a recent baseline with $6\times$ faster training, outperforming competing INR-based methods across both image quality and domain-specific metrics. Code is available on the project page at https://abdulkaderghandoura.github.io/research/msc-thesis/ .
