Automated segmentation of chronic stroke lesions using LINDA: Lesion identification with neighborhood data analysis.
Automated segmentation of chronic stroke lesions using LINDA: Lesion identification with neighborhood data analysis.
复制标题
DOI：
10.1002/hbm.23110
复制
发表时间：
2016-04
影响因子：
4.8
通讯作者：
Avants B
中科院分区：
文献类型：
--
作者：
Pustina D;Coslett HB;Turkeltaub PE;Tustison N;Schwartz MF;Avants B
识别中风病变的金标准是手动追踪，这种方法依赖于观察者并且耗时，因此对于大数据研究来说是不切实际的。我们提出了琳达（邻近数据分析的病变识别），一种自动分割算法，能够学习现有手动分割和单个T1加权MRI之间的关系。60个左半球慢性中风患者的数据集被用来建立该方法，并测试它与k-折叠和留一法程序。关于手动描记，预测病变标测图显示平均骰子重叠为0.696±0.16，Hausdorff距离为17.9± 9.8 mm，平均位移为2.54± 1.38 mm。手动和预测病变体积相关性为r=0.961。另外一个45例患者的数据集被用来测试琳达与独立的数据，实现了高准确率，并确认其跨机构的适用性。为了调查从手动描记到自动分割的成本，我们对五个行为评分进行了比较性病变-症状映射（LSM）。预测和手动损伤产生了类似的神经认知图，尽管存在一些讨论过的差异。值得注意的是，逐区域LSM比逐体素LSM对预测误差更鲁棒。我们的研究结果表明，虽然存在一些限制，但我们目前的结果与最先进的技术竞争或超过最先进的技术，产生一致的预测，非常低的失败率，以及实验室之间的可转移知识。这项工作也建立了一个新的观点，评估自动化方法不仅与分割精度，而且与大脑行为的关系。琳达在线提供来自100多名患者的训练模型。
The gold standard for identifying stroke lesions is manual tracing, a method that is known to be observer dependent and time consuming, thus impractical for big data studies. We propose LINDA (Lesion Identification with Neighborhood Data Analysis), an automated segmentation algorithm capable of learning the relationship between existing manual segmentations and a single T1-weighted MRI. A dataset of 60 left hemispheric chronic stroke patients is used to build the method and test it with k-fold and leave-one-out procedures. With respect to manual tracings, predicted lesion maps showed a mean dice overlap of 0.696±0.16, Hausdorff distance of 17.9±9.8mm, and average displacement of 2.54±1.38mm. The manual and predicted lesion volumes correlated at r=0.961. An additional dataset of 45 patients was utilized to test LINDA with independent data, achieving high accuracy rates and confirming its cross-institutional applicability. To investigate the cost of moving from manual tracings to automated segmentation, we performed comparative lesion-to-symptom mapping (LSM) on five behavioral scores. Predicted and manual lesions produced similar neuro-cognitive maps, albeit with some discussed discrepancies. Of note, region-wise LSM was more robust to the prediction error than voxel-wise LSM. Our results show that, while several limitations exist, our current results compete with or exceed the state-of-the-art, producing consistent predictions, very low failure rates, and transferable knowledge between labs. This work also establishes a new viewpoint on evaluating automated methods not only with segmentation accuracy but also with brain-behavior relationships. LINDA is made available online with trained models from over 100 patients.