Rigid and affine registrations to a common template are the essential steps during pre-processing of brain structural magnetic resonance imaging (MRI) data. Manual quality check (QC) of these registrations is quite tedious if the data contains several thousands of images. Therefore, we propose a machine learning (ML) framework for fully automatic QC of these registrations via local computation of the similarity functions such as normalized cross-correlation, normalized mutual-information, and correlation ratio, and using these as features for training of different ML classifiers. To facilitate supervised learning, misaligned images are generated. A structural MRI dataset consisting of 215 subjects from autism brain imaging data exchange is used for 5-fold cross-validation and testing. Few classifiers such as kNN, AdaBoost, and random forest reached testing F1-scores of 0.98 for QC of both rigid and affine registrations. These tested ML models could be deployed for practical use.

中文翻译：

---

大数据脑MRI中刚性和仿射注册的全自动质量检查的机器学习框架

在预处理脑结构磁共振成像（MRI）数据期间，将硬性和仿射性配准到通用模板是必不可少的步骤。如果数据包含数千张图像，则对这些注册进行手动质量检查（QC）会非常繁琐。因此，我们提出了一种机器学习（ML）框架，用于通过对相似函数（例如归一化互相关，归一化互信息和相关比）进行局部计算来对这些注册进行全自动质量控制，并将它们用作针对不同训练的特征ML分类器。为了促进监督学习，会生成未对齐的图像。结构MRI数据集由来自自闭症脑成像数据交换的215位受试者组成，用于5倍交叉验证和测试。很少有分类器，例如kNN，AdaBoost，随机森林的刚性和仿射配准的QC测试F1分数均达到0.98。这些经过测试的ML模型可以部署为实际使用。