脑部解剖异常的MRI全头细分:模型和数据发布
Andrew M Birnbaum1, Adam Buchwald2, Peter Turkeltaub3
1The City College of New York, Department of Biomedical Engineering, New York, United States.
Journal of medical imaging (Bellingham, Wash.)
|September 19, 2025
概括
我们开发了一种全新的深度学习网络,用于整体头部MRI细分,在各种数据集上取得最先进的结果,包括异常解剖学. 这项工作引入了这项任务的第一个公共基准数据集,有助于未来的神经成像研究.
科学领域:
- 神经成像和医学图像分析
- 深度学习和人工智能
- 计算神经科学是一种神经科学.
背景情况:
- 全头磁共振成像 (MRI) 的精确细分对于各种神经成像应用至关重要.
- 现有的方法经常与异常解剖学作斗争,并且需要基于地图的注册,从而限制了它们的稳定性.
- 需要先进的细分工具和全面的数据集来应对这些挑战.
研究的目的:
- 开发一个深度学习网络,用于临床MRI的全头细分,包括异常解剖的病例.
- 创建第一个全头MRI细分的公开基准数据集,包括98个MRI和详细的体积标签.
- 评估网络的性能与现有工具相比,并评估其在下游应用中的实用性.
主要方法:
- 一个小说 一个小说
- 多轴的 多轴的
- 开发了深度学习网络,利用三种2D U-Nets在斜面,轴面和冠状面上运行.
- 该网络在一个定制的98个MRI数据集上进行了训练和验证,并对皮肤,头骨,脑脊液,灰质和白质等结构进行了手动校正.
- 这种方法避免了亚特拉斯的联合注册,提高了稳定性,特别是在异常解剖的区域.
主要成果:
- 多轴网络在整个头部细分方面取得了0.88 ± 0.04的高测试盘子得分,超过了Multipriors (0.86 ± 0.04) 和SPM12 (0.79 ± 0.10) 等已有的工具.
- 该网络在异常解剖图像和非识别扫描图像上表现出强度.
- 改进的细分精度促进了在ROAST工具箱内更强大的电流流量建模,用于跨电刺激.
结论:
- 这项研究介绍了一种最先进的深度学习工具,用于全头MRI细分,在异常解剖的病例中尤其有效.
- 包括非大脑结构在内的最大数量的标记临床头部MRI的发布为该领域建立了新的基准.
- 预计开发的模型和数据集将推动神经影像分析和计算建模方面的研究.
相关概念视频
01:14Imaging Studies I: CT and MRI
Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...
01:14Brain Imaging
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).