Motion estimation and correction in cardiac CT angiography images using convolutional neural networks.

Cardiac motion artifacts frequently reduce the interpretability of coronary computed tomography angiography (CCTA) images and potentially lead to misinterpretations or preclude the diagnosis of coronary artery disease (CAD). In this paper, a novel motion compensation approach dealing with Coronary Motion estimation by Patch Analysis in CT data (CoMPACT) is presented. First, the required data for supervised learning is generated by the Coronary Motion Forward Artifact model for CT data (CoMoFACT) which introduces simulated motion to 19 artifact-free clinical CT cases with step-and-shoot acquisition protocol. Second, convolutional neural networks (CNNs) are trained to estimate underlying 2D motion vectors from 2.5D image patches based on the coronary artifact appearance. In a phantom study with computer-simulated vessels, CNNs predict the motion direction and the motion magnitude with average test accuracies of 13.37°±1.21° and 0.77 ±â€¯0.09 mm, respectively. On clinical data with simulated motion, average test accuracies of 34.85°±2.09° and 1.86 ±â€¯0.11 mm are achieved, whereby the precision of the motion direction prediction increases with the motion magnitude. The trained CNNs are integrated into an iterative motion compensation pipeline which includes distance-weighted motion vector extrapolation. Alternating motion estimation and compensation in twelve clinical cases with real cardiac motion artifacts leads to significantly reduced artifact levels, especially in image data with severe artifacts. In four observer studies, mean artifact levels of 3.08 ±â€¯0.24 without MC and 2.28 ±â€¯0.29 with CoMPACT MC are rated in a five point Likert scale.

Motion artifact recognition and quantification in coronary CT angiography using convolutional neural networks.

Excellent image quality is a primary prerequisite for diagnostic non-invasive coronary CT angiography. Artifacts due to cardiac motion may interfere with detection and diagnosis of coronary artery disease and render subsequent treatment decisions more difficult. We propose deep-learning-based measures for coronary motion artifact recognition and quantification in order to assess the diagnostic reliability and image quality of coronary CT angiography images. More specifically, the application, steering and evaluation of motion compensation algorithms can be triggered by these measures. A Coronary Motion Forward Artifact model for CT data (CoMoFACT) is developed and applied to clinical cases with excellent image quality to introduce motion artifacts using simulated motion vector fields. The data required for supervised learning is generated by the CoMoFACT from 17 prospectively ECG-triggered clinical cases with controlled motion levels on a scale of 0-10. Convolutional neural networks achieve an accuracy of 93.3% ±â€¯1.8% for the classification task of separating motion-free from motion-perturbed coronary cross-sectional image patches. The target motion level is predicted by a corresponding regression network with a mean absolute error of 1.12 ±â€¯0.07. Transferability and generalization capabilities are demonstrated by motion artifact measurements on eight additional CCTA cases with real motion artifacts.

Effects of virtual tube current reduction and sparse sampling on MDCT-based femoral BMD measurements.

This study investigates the impact of tube current reduction and sparse sampling on femoral bone mineral density (BMD) measurements derived from multi-detector computed tomography (MDCT). The application of sparse sampling led to robust and clinically acceptable BMD measurements. In contrast, BMD measurements derived from MDCT with virtually reduced tube currents showed a considerable increase when compared to original data. INTRODUCTION: The study aims to evaluate the effects of radiation dose reduction by using virtual reduction of tube current or sparse sampling combined with standard filtered back projection (FBP) and statistical iterative reconstruction (SIR) on femoral bone mineral density (BMD) measurements derived from multi-detector computed tomography (MDCT). METHODS: In routine MDCT scans of 41 subjects (65.9% men; age 69.3 ± 10.1 years), reduced radiation doses were simulated by lowering tube currents and applying sparse sampling (50, 25, and 10% of the original tube current and projections, respectively). Images were reconstructed using FBP and SIR. BMD values were assessed in the femoral neck and compared between the different dose levels, numbers of projections, and image reconstruction approaches. RESULTS: Compared to full-dose MDCT, virtual lowering of the tube current by applying our simulation algorithm resulted in increases in BMD values for both FBP (up to a relative change of 32.5%) and SIR (up to a relative change of 32.3%). In contrast, the application of sparse sampling with a reduction down to 10% of projections showed robust BMD values, with clinically acceptable relative changes of up to 0.5% (FBP) and 0.7% (SIR). CONCLUSIONS: Our simulations, which still require clinical validation, indicate that reductions down to ultra-low tube currents have a significant impact on MDCT-based femoral BMD measurements. In contrast, the application of sparse-sampled MDCT seems a promising future clinical option that may enable a significant reduction of the radiation dose without considerable changes of BMD values.