Memory-efficient 2.5D convolutional transformer networks for multi-modal deformable registration with weak label supervision applied to whole-heart CT and MRI scans
Memory-efficient 2.5D convolutional transformer networks for multi-modal deformable registration with weak label supervision applied to whole-heart CT and MRI scans
复制标题
DOI：
10.1007/s11548-019-02068-z
复制
发表时间：
2019-11-01
影响因子：
3
通讯作者：
Heinrich, Mattias P.
中科院分区：
文献类型：
--
作者：
Hering, Alessa;Kuckertz, Sven;Heinrich, Mattias P.
尽管基于深度学习的配准方法具有通过监督进行改进的潜力，但由于内存需求过大，很难针对3D扫描中的大变形进行训练。我们提出了一种新的2.5D卷积Transformer架构，使我们能够学习一种用于多模态图像配准的内存高效的弱监督深度学习模型。此外，我们首先将体积变化控制项集成到基于深度学习的配准方法的损失函数中，以惩罚变形场内发生的折叠。结果我们的方法成功地学习了多模态图像的大变形。我们在100对CT和MRI全心脏扫描配准上评估了我们的方法，并证明了与最先进的无监督离散配准框架（Dice为0.71）相比，Dice评分（0.74）要高得多。结论我们提出的内存有效的配准方法比最先进的传统配准方法性能更好。通过在损失函数中使用体积变化控制项，可以在新配准情况下显著减少出现折叠的数量。
Purpose Despite its potential for improvements through supervision, deep learning-based registration approaches are difficult to train for large deformations in 3D scans due to excessive memory requirements. Methods We propose a new 2.5D convolutional transformer architecture that enables us to learn a memory-efficient weakly supervised deep learning model for multi-modal image registration. Furthermore, we firstly integrate a volume change control term into the loss function of a deep learning-based registration method to penalize occurring foldings inside the deformation field. Results Our approach succeeds at learning large deformations across multi-modal images. We evaluate our approach on 100 pair-wise registrations of CT and MRI whole-heart scans and demonstrate considerably higher Dice Scores (of 0.74) compared to a state-of-the-art unsupervised discrete registration framework (deeds with Dice of 0.71). Conclusion Our proposed memory-efficient registration method performs better than state-of-the-art conventional registration methods. By using a volume change control term in the loss function, the number of occurring foldings can be considerably reduced on new registration cases.