arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2005.06926eess.IV
收藏

扩散张量驱动的图像配准:一种深度学习方法

Diffusion tensor driven image registration: a deep learning approach

Irina Grigorescu, Alena Uus, Daan Christiaens, Lucilio Cordero-Grande, Jana Hutter, A. David Edwards, Joseph V. Hajnal, Marc Modat, Maria Deprez

摘要:

跟踪发育中的大脑中的微结构变化依赖于准确的受试者间图像配准。然而,大多数方法依赖于结构或扩散数据来学习两个或多个图像之间的空间对应关系,而不考虑使用两者提供的互补信息。在这里,我们提出了一个深度学习配准框架,该框架将T2加权(T2 w)图像提供的结构信息与扩散张量成像(DTI)扫描提供的丰富微观结构信息相结合。我们进行了一项留一交叉验证研究,在该研究中,我们将我们的多模态配准模型的性能与仅在结构数据上训练的基线模型进行了比较,包括Dice评分和分数各向异性(FA)图的差异。我们的研究结果表明,在平均骰子分数方面,我们的模型在皮层下区域的表现更好,相比只使用结构数据。此外,变形和固定FA图之间的平均平方和差异表明,我们提出的模型在对齐扩散数据方面表现更好。

英文摘要:

Tracking microsctructural changes in the developing brain relies on accurate inter-subject image registration. However, most methods rely on either structural or diffusion data to learn the spatial correspondences between two or more images, without taking into account the complementary information provided by using both. Here we propose a deep learning registration framework which combines the structural information provided by T2-weighted (T2w) images with the rich microstructural information offered by diffusion tensor imaging (DTI) scans. We perform a leave-one-out cross-validation study where we compare the performance of our multi-modality registration model with a baseline model trained on structural data only, in terms of Dice scores and differences in fractional anisotropy (FA) maps. Our results show that in terms of average Dice scores our model performs better in subcortical regions when compared to using structural data only. Moreover, average sum-of-squared differences between warped and fixed FA maps show that our proposed model performs better at aligning the diffusion data.

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。

↑