This study evaluates the performance of conventional SyN ANTs and learning-based registration methods in the context of pediatric neuroimaging, specifically focusing on intrasubject deformable registration. The comparison involves three approaches: without (NR), with rigid (RR), and with rigid and affine (RAR) initializations. In addition to initialization, performances are evaluated in terms of accuracy, speed, and the impact of age intervals and sex per pair. Data consists of the publicly available MRI scans from the Calgary Preschool dataset, which includes 63 children aged 2-7 years, allowing for 431 registration pairs. We implemented the unsupervised DL framework with a U-Net architecture using DeepReg and it was 5-fold cross-validated. Evaluation includes Dice scores for tissue segmentation from 18 smaller regions obtained by SynthSeg, analysis of log Jacobian determinants, and registration pro-rated training and inference times. Learning-based approaches, with or without linear initializations, exhibit slight superiority over SyN ANTs in terms of Dice scores. Indeed, DL-based implementations with RR and RAR initializations significantly outperform SyN ANTs. Both SyN ANTs and DL-based registration involve parameter optimization, but the choice between these methods depends on the scale of registration: network-based for broader coverage or SyN ANTs for specific structures. Both methods face challenges with larger age intervals due to greater growth changes. The main takeaway is that while DL-based methods show promise with faster and more accurate registrations, SyN ANTs remains robust and generalizable without the need for extensive training, highlighting the importance of method selection based on specific registration needs in the pediatric context. Our code is available at https://github.com/neuropoly/pediatric-DL-registration

翻译：本研究评估了传统SyN ANTs与基于学习的配准方法在儿童神经影像学中的性能，特别关注个体内部的可变形配准。比较涉及三种初始化方式：无初始化（NR）、刚性初始化（RR）以及刚性加仿射初始化（RAR）。除初始化外，还从准确性、速度、年龄间隔及性别配对影响等方面评估性能。数据来源于公开的卡尔加里学龄前儿童数据集，包含63名2-7岁儿童的磁共振扫描，共构成431个配准对。我们采用DeepReg框架的U-Net架构实现了无监督深度学习模型，并进行了5折交叉验证。评估指标包括：通过SynthSeg获得的18个较小脑区组织分割的Dice分数、对数雅可比行列式分析，以及按比例折算的配准训练与推理时间。无论是否采用线性初始化，基于学习的方法在Dice分数上均略优于SyN ANTs。实际上，采用RR和RAR初始化的深度学习实现显著超越了SyN ANTs。SyN ANTs与基于深度学习的配准均涉及参数优化，但方法选择取决于配准尺度：网络方法适用于更广泛的覆盖范围，而SyN ANTs更适合特定结构。两种方法在较大年龄间隔下都面临因生长变化加剧而带来的挑战。主要结论是：虽然基于深度学习的方法展现出更快、更准确的配准潜力，但SyN ANTs仍具有稳健性和泛化能力，且无需大量训练，这凸显了在儿童影像配准中根据具体需求选择方法的重要性。我们的代码公开于：https://github.com/neuropoly/pediatric-DL-registration