Motion grading of high-resolution quantitative computed tomography supported by deep convolutional neural networks

• Published in: Bone (New York, N.Y.) Vol. 166; p. 116607
• Main Authors: Walle, Matthias, Eggemann, Dominic, Atkins, Penny R., Kendall, Jack J., Stock, Kerstin, Müller, Ralph, Collins, Caitlyn J.
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.01.2023
• Subjects: Artificial intelligence; Convolutional neural networks; Deep learning; High-resolution peripheral quantitative computed tomography; Machine learning; Motion-grading; Deep learning; Motion-grading; High-resolution peripheral quantitative computed tomography; Convolutional neural networks; Artificial intelligence; Machine learning
• DOI: 10.1016/j.bone.2022.116607
• ISSN: 8756-3282; 1873-2763

Image quality degradation due to subject motion confounds the precision and reproducibility of measurements of bone density, morphology and mechanical properties from high-resolution peripheral quantitative computed tomography (HR-pQCT). Time-consuming operator-based scoring of motion artefacts remains the gold standard to determine the degree of acceptable motion. However, due to the subjectiveness of manual grading, HR-pQCT scans of poor quality, which cannot be used for analysis, may be accepted upon initial review, leaving patients with incomplete or inaccurate imaging results. Convolutional Neural Networks (CNNs) enable fast image analysis with relatively few pre-processing requirements in an operator-independent and fully automated way for image classification tasks. This study aimed to develop a CNN that can predict motion scores from HR-pQCT images, while also being aware of uncertain predictions that require manual confirmation. The CNN calculated motion scores within seconds and achieved a high F1-score (86.8 ± 2.8 %), with good precision (87.5 ± 2.7 %), recall (86.7 ± 2.9 %) and a substantial agreement with the ground truth measured by Cohen's kappa (κ = 68.6 ± 6.2 %); motion scores of the test dataset were predicted by the algorithm with comparable accuracy, precision, sensitivity and agreement as by the operators (p > 0.05). This post-processing approach may be used to assess the effect of motion scores on microstructural analysis and can be immediately implemented into clinical protocols, significantly reducing the time for quality assessment and control of HR-pQCT scans. [Display omitted] •An accurate (F1 = 86.8 ± 2.8 %) convolutional neural network (CNN) for motion grading of HR-pQCT scans.•Uncertainty quantification to help human operators understand CNN predictions.•Assessment of patient motion in a sizeable HR-pQCT dataset.