Artificial neural network for suppression of metal artifacts with slice encoding for metal artifact correction (SEMAC) MRI

Abstract

Even though anatomical MR imaging for diagnostic purposes has become more readily available, imaging body regions with metal transplants suffer from severe metal artifacts. Lu et al. introduced Slice Encoding for Metal Artifact Correction in MRI (SEMAC) to suppress metal artifacts using extra z-phase encoding steps (SEMAC factor) combining with the View-Angle-Tilting (VAT) technique developed by Cho, et al.[1, 2]. However, prolonged scan time for higher SEMAC factor imaging remains as the technique’s inherent problem. In our study, we introduce artificial neural network to accelerate SEMAC imaging to suppress metal artifacts in a shorter scan time with comparable image quality. Multilayer Perceptron (MLP) is one of the most commonly used artificial neural network architectures, through which a fully connected hidden layer maps input values into output values. MLP has proven to be useful for suppressing artifacts in MRI data [3]. For SEMAC technique, low and high SEMAC factor images were categorized into input and ground truth, respectively, and were trained with MLP, through which output images were produced and compared with label images. Normalized root mean square error (NRMSE) from the ground truth was quantified for the analysis of the tested images. MLP showed smaller NRMSE than that of the input partitions, a trend observable regardless of SEMAC factor. The reduction in NRMSE using MLP was statistically significant (p < 0.01), and the artifact suppressions were visibly significant for low input SEMAC factors. Our study introduces a new effective way to reduce the scan time necessary for imaging with high SEMAC factor while maintaining the comparable quality of metal artifact suppression.