arXiv 2503.071042025-03-10eess.IVcs.CVcs.LGq-bio.QM

全局上下文即所需：面向并行高效纤维束成像分割的全新方法

Global Context Is All You Need for Parallel Efficient Tractography Parcellation

University of Bonn（波恩大学）；Center for X-ray and Nano Science CXNS, DESY（欧洲同步辐射中心X射线与纳米科学中心）；University Hospital Bonn（波恩大学医院）；German Center for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病中心）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究院）

Valentin von Bornhaupt, Johannes Grün, and Justus Bisten, Tobias Bauer, Theodor Rüber, Thomas Schultz

备注：: 8 pages, 2 pages references, 3 figures, 2 tables

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 PETParc，一种基于 Transformer 的并行高效纤维束成像分割方法，通过随机划分子纤维束图并互为全局上下文，在去除局部上下文的同时实现最高两个数量级加速，并保持或提升分割准确率。

摘要：

扩散 MRI 的全脑纤维束成像（tractography）之后通常需要进行分割（parcellation），即把每条流线（streamline）归类为属于某个特定白质纤维束，或作为假阳性予以剔除。高效的分割在大规模研究中至关重要，因为这类研究需要处理海量数据；在计算资源往往有限的临床环境中同样重要。TractCloud 是一种当前最先进的方法，旨在通过局部-全局表示来最大化准确率。我们证明，局部上下文对该方法的准确率没有贡献，在处理病理案例时甚至会产生不利影响。基于这一观察，我们提出 PETParc，一种新的并行高效纤维束成像分割方法。PETParc 采用基于 Transformer 的架构，将全脑纤维束图（tractogram）随机划分为多个子纤维束图，这些子纤维束图中的流线被并行分类，同时互为全局上下文。与 TractCloud 相比，该方法实现了最高达两个数量级的加速，并且即使在没有 GPU 的临床工作站上也能进行推理。PETParc 通过一种新颖的翻转不变嵌入（flip-invariant embedding）来应对流线方向缺失的问题，或者直接将翻转作为数据增强的一部分。尽管实现了加速，其结果往往甚至优于先前的方法。代码和预训练模型将在论文被接收后公开。

英文摘要：

Whole-brain tractography in diffusion MRI is often followed by a parcellation in which each streamline is classified as belonging to a specific white matter bundle, or discarded as a false positive. Efficient parcellation is important both in large-scale studies, which have to process huge amounts of data, and in the clinic, where computational resources are often limited. TractCloud is a state-of-the-art approach that aims to maximize accuracy with a local-global representation. We demonstrate that the local context does not contribute to the accuracy of that approach, and is even detrimental when dealing with pathological cases. Based on this observation, we propose PETParc, a new method for Parallel Efficient Tractography Parcellation. PETParc is a transformer-based architecture in which the whole-brain tractogram is randomly partitioned into sub-tractograms whose streamlines are classified in parallel, while serving as global context for each other. This leads to a speedup of up to two orders of magnitude relative to TractCloud, and permits inference even on clinical workstations without a GPU. PETParc accounts for the lack of streamline orientation either via a novel flip-invariant embedding, or by simply using flips as part of data augmentation. Despite the speedup, results are often even better than those of prior methods. The code and pretrained model will be made public upon acceptance.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。