MRI Quality Control Algorithm Based on Image Analysis Using Convolutional and Recurrent Neural Networks

Abstract

MRI quality control plays a significant role in ensuring safety and quality of examinations. Most of the work in the area is devoted to the development of no-reference quality metrics. Some recent works use 2D or 3D convolutional neural networks. For this study, we collected a dataset of 363 clinical MRI sequences with known results of quality control as well as 1295 clinical MRI sequences without known results of quality control. We propose a method based on neural networks that takes into account the three-dimensional context through the use of bidirectional LSTM, as well as a pre-training method based on a prediction of no-reference quality metrics using EfficientNet convolutional neural network that allows the use of unlabeled data. The proposed method makes it possible to predict the result of quality control with ROC-AUC of almost 0.94.