PulseAugur
实时 12:19:23

新的DD-INR框架加速fMRI重建

研究人员开发了DD-INR,一种用于重建加速采样的功能磁共振成像(fMRI)数据的新型框架。该方法专门解决了恢复细微的任务诱发大脑活动信号的挑战,而这些信号通常被优先考虑空间精度而非时间保真度的传统重建技术所忽略。通过将静态背景信息与动态变化分离,并对后者使用隐式神经表示(INR),DD-INR将计算资源集中在相关的激活上,从而可能提高fMRI研究的灵敏度和鲁棒性。 AI

影响 通过实现对加速扫描的大脑活动的更准确重建,这一新框架可以提高fMRI研究的灵敏度和鲁棒性。

排序理由 该集群包含一篇详细介绍fMRI重建新方法的学术论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Qiaoxin Li (MIND), Caini Pan (NEUROSPIN, MIND), Pierre-Antoine Comby (MIND, BAOBAB), Chaithya Giliyar (MIND), Philippe Ciuciu (MIND) ·

    DD-INR: Dynamics-Driven Implicit Neural Representation for Accelerated Whole-Brain Functional MRI Reconstruction

    arXiv:2606.10756v1 Announce Type: new Abstract: Accelerated acquisition of fMRI enables enhanced detection of neurovascular (BOLD) activity in the brain, but image reconstruction becomes challenging with high k-space undersampling: Task-evoked BOLD signals are small in magnitude,…

  2. arXiv cs.CV TIER_1 English(EN) · Philippe Ciuciu ·

    DD-INR: Dynamics-Driven Implicit Neural Representation for Accelerated Whole-Brain Functional MRI Reconstruction

    Accelerated acquisition of fMRI enables enhanced detection of neurovascular (BOLD) activity in the brain, but image reconstruction becomes challenging with high k-space undersampling: Task-evoked BOLD signals are small in magnitude, which traditional anatomical MRI reconstruction…