Automated detection of motion artifacts in brain MR images using deep learning

Quality assessment, including inspecting the images for artifacts, is a critical step during magnetic resonance imaging (MRI) data acquisition to ensure data quality and downstream analysis or interpretation success. This study demonstrates a deep learning (DL) model to detect rigid motion in T1‐weighted brain images. We leveraged a 2D convolutional neural network (CNN) trained on motion‐synthesized data for three‐class classification and tested it on publicly available retrospective and prospective datasets. Grad‐CAM heatmaps enabled the identification of failure modes and provided an interpretation of the model's results. The model achieved average precision and recall metrics of 85% and 80% on six motion‐simulated retrospective datasets. Additionally, the model's classifications on the prospective dataset showed 93% agreement with the labeling of a radiologist a strong inverse correlation (−0.84) compared to average edge strength, an image quality metric indicative of motion. This model is aimed at inline automatic detection of motion artifacts, accelerating part of the time‐consuming quality assessment (QA) process and augmenting expertise on‐site, particularly relevant in low‐resource settings where local MR knowledge is scarce. This study presents an explainable deep learning model for motion artifact detection in brain MRI, achieving high accuracies on motion‐simulated retrospective datasets and interpretable results in a prospective dataset. It is intended to assist the MR technician by automating part of the QA process, enhancing scan efficiency, and augmenting expertise.