用GPT架构自动分割脑白质束，兼顾形状与跨数据集泛化能力。
TractoGPT: A GPT architecture for White Matter Segmentation
- 基于GPT架构，分别处理流线、聚类和融合数据表示
- 在平均DICE、重叠率等指标上优于现有方法
- 适合脑连接组学研究与神经外科规划场景
白质束分割对研究脑结构连接、神经外科规划及神经系统疾病至关重要。由于纤维束间结构相似、个体差异大、双侧半球对称性等因素，该任务仍具挑战。为此，我们提出TractoGPT，一种基于GPT架构的方法，分别在流线、聚类和融合数据表示上进行训练。TractoGPT为全自动化方法，具备跨数据集泛化能力，并能保留白质束的形态信息。实验表明，TractoGPT在TractoInferno和105HCP数据集上的平均DICE、Overlap与Overreach得分均优于当前最优方法。
原文摘要 · Abstract (English)
White matter bundle segmentation is crucial for studying brain structural connectivity, neurosurgical planning, and neurological disorders. White Matter Segmentation remains challenging due to structural similarity in streamlines, subject variability, symmetry in 2 hemispheres, etc. To address these challenges, we propose TractoGPT, a GPT-based architecture trained on streamline, cluster, and fusion data representations separately. TractoGPT is a fully-automatic method that generalizes across datasets and retains shape information of the white matter bundles. Experiments also show that TractoGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores. We use TractoInferno and 105HCP datasets and validate generalization across dataset.
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。