Experimental and clinical validation of an artificial intelligence metal artifact correction algorithm for low-dose following up CT of percutaneous vertebroplasty.

Abstract

Low-dose following up computed tomography (CT) of percutaneous vertebroplasty (PVP) that involves the use of bone cement usually suffers from lightweight metal artifacts, where conventional techniques for CT metal artifact reduction are often not sufficiently effective. This study aimed to validate an artificial intelligence (AI)-based metal artifact correction (MAC) algorithm for use in low-dose following up CT for PVP. In experimental validation, an ovine vertebra phantom was designed to simulate the clinical scenario of PVP. With routine-dose images acquired prior to the cement introduction as the reference, low-dose CT scans were taken on the cemented phantom and processed with conventional MAC and AI-MAC. The resulting image quality was compared in CT attenuation, image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR), followed by a quantitative evaluation of the artifact correction accuracy based on adaptive segmentation of the paraspinal muscle. In clinical validation, ten cases of low-dose following up CT after PVP were enrolled to test the performance of diagnosing sarcopenia with measured CT attenuation per cemented vertebral segment, via receiver operating characteristic (ROC) analysis. With respect to the reference image, no significant difference was found for AI-MAC in CT attenuation, image noise, SNRs, and CNR (all P>0.05). The paraspinal muscle segmented on the AI-MAC image was 18.6% and 8.3% more complete to uncorrected and MAC images. Higher area under the curve (AUC) of the ROC analysis was found for AI-MAC (AUC =0.92) compared to the uncorrected (AUC =0.61) and MAC images (AUC =0.70). In low-dose following up CT for PVP, the AI-MAC has been fully validated for its superior ability compared to conventional MAC in suppressing artifacts and may be a reliable alternative for diagnosing sarcopenia.