arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.15464cs.CVcs.AI
收藏

TractoGPT:一种用于白质分割的GPT架构

TractoGPT: A GPT architecture for White Matter Segmentation

School of Computing and Electrical Engineering, Indian Institute of Technology Mandi(印度理工大学曼迪分校计算与电气工程学院);Department of Mathematics, Indian Institute of Technology Patna(印度理工大学巴特那分校数学系);Post Graduate Institute of Medical Education Research, Chandigarh(昌迪加尔医学教育与研究研究生院)

Anoushkrit Goel, Simroop Singh, Ankita Joshi, Ranjeet Ranjan Jha, Chirag Ahuja, Aditya Nigam, Arnav Bhavsar

AI总结:

针对白质分割中流线结构相似、个体差异等挑战,提出基于GPT架构的全自动分割方法TractoGPT,经多数据集训练与验证,在多项指标上优于现有最优方法且具备跨数据集泛化能力。

摘要:

白质束分割对研究大脑结构连接性、神经外科规划及神经系统疾病至关重要。由于流线的结构相似性、受试者个体差异、双侧大脑半球对称性等因素,白质分割仍然具有挑战性。为应对这些挑战,我们提出TractoGPT,这是一种基于GPT的架构,分别在流线、簇和融合数据表示上进行训练。TractoGPT是一种全自动方法,可跨数据集泛化并保留白质束的形状信息。实验还表明,TractoGPT在平均DICE、重叠度(Overlap)和过伸度(Overreach)指标上优于当前最优方法。我们使用TractoInferno和105HCP数据集,并验证了其跨数据集的泛化能力。

英文摘要:

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.

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。

↑