Clinical validation of an AI-based motion correction reconstruction algorithm in cerebral CT
- 9 June 2022
- journal article
- research article
- Published by Springer Nature in European Radiology
- Vol. 32 (12) , 8550-8559
Abstract
Objectives To evaluate the clinical performance of an artificial intelligence (AI)–based motion correction (MC) reconstruction algorithm for cerebral CT. Methods A total of 53 cases, where motion artifacts were found in the first scan so that an immediate rescan was taken, were retrospectively enrolled. While the rescanned images were reconstructed with a hybrid iterative reconstruction (IR) algorithm (reference group), images of the first scan were reconstructed with both the hybrid IR (motion group) and the MC algorithm (MC group). Image quality was compared in terms of standard deviation (SD), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), the mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mutual information (MI), as well as subjective scores. The diagnostic performance for each case was evaluated accordingly by lesion detectability or the Alberta Stroke Program Early CT Score (ASPECTS) assessment. Results Compared with the motion group, the SNR and CNR of the MC group were significantly increased. The MSE, PSNR, SSIM, and MI with respect to the reference group were improved by 44.1%, 15.8%, 7.4%, and 18.3%, respectively (all p < 0.001). Subjective image quality indicators were scored higher for the MC than the motion group (p < 0.05). Improved lesion detectability and higher AUC (0.817 vs 0.614) in the ASPECTS assessment were found for the MC to the motion group. Conclusions The AI-based MC reconstruction algorithm has been clinically validated for reducing motion artifacts and improving diagnostic performance of cerebral CT. Key Points • An artificial intelligence–based motion correction (MC) reconstruction algorithm has been clinically validated in both qualitative and quantitative manner. • The MC algorithm reduces motion artifacts in cerebral CT and increases the diagnostic confidence for brain lesions. • The MC algorithm can help avoiding rescans caused by motion and improving the efficiency of cerebral CT in the emergency department.Keywords
Funding Information
- Jiangsu Provincial Special Program of Medical Science (BE2021604)
- Xinghuo Talent Program of Nanjing First Hospital
This publication has 28 references indexed in Scilit:
- Compensation of skull motion and breathing motion in CT using data-based and image-based metrics, respectively2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Head movement during CT brain perfusion acquisition of patients with suspected acute ischemic strokeEuropean Journal of Radiology, 2013
- Iterative reconstruction methods in X-ray CTPhysica Medica, 2012
- Computed tomography—old ideas and new technologyEuropean Radiology, 2011
- Effect of Tube Voltage on Image Quality in 64-Section Multidetector 3D CT Angiography: Evaluation with a Vascular Phantom with Superimposed Bone Skull StructuresAmerican Journal of Neuroradiology, 2009
- Low-Dose Nonenhanced Head CT Protocol for Follow-Up Evaluation of Children with Ventriculoperitoneal Shunt: Reduction of Radiation and Effect on Image QualityAmerican Journal of Neuroradiology, 2008
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Quantification and Clinical Relevance of Head Motion During Computed TomographyInvestigative Radiology, 2003
- Validity and reliability of a quantitative computed tomography score in predicting outcome of hyperacute stroke before thrombolytic therapyThe Lancet, 2000