Search

Objective: To establish an automated pipeline for post-processing of quantitative spin-lattice relaxation time constant in the rotating frame ($T_{1\rho}$) imaging of knee articular cartilage. Design: The proposed post-processing pipeline commences with an image standardisation procedure, followed by deep learning-based segmentation to generate cartilage masks. The articular cartilage is then automatically parcellated into 20 subregions, where $T_{1\rho}$ quantification is performed. The proposed pipeline was retrospectively validated on a dataset comprising knee $T_{1\rho}$ images of 10 healthy volunteers and 30 patients with knee osteoarthritis. Three experiments were conducted, namely an assessment of segmentation model performance (using Dice similarity coefficients, DSCs); an evaluation of the impact of standardisation; and a test of $T_{1\rho}$ quantification accuracy (using paired t-tests; root-mean-square deviations, RMSDs; and coefficients of variance of RMSDs, $CV_{RMSD}$). Statistical significance was set as p<0.05. Results: There was a substantial agreement between the subregional $T_{1\rho}$ quantification from the model-predicted masks and those from the manual segmentation labels. In patients, 17 of 20 subregions, and in healthy volunteers, 18 out of 20 subregions, demonstrated no significant difference between predicted and reference $T_{1\rho}$ quantifications. Average RMSDs were 0.79 ms for patients and 0.56 ms for healthy volunteers, while average $CV_{RMSD}$ were 1.97% and 1.38% for patients and healthy volunteers. Bland-Altman plots showed negligible bias across all subregions for patients and healthy volunteers. Conclusion: The proposed pipeline can perform automatic and reliable post-processing of quantitative $T_{1\rho}$ images of knee articular cartilage., Comment: Junru Zhong and Yongcheng Yao share the same contribution. Work was partially done when Yongcheng Yao and Siyue Li was with CUHK

Purpose: The aim of this study was to demonstrate the utility of unsupervised domain adaptation (UDA) in automated knee osteoarthritis (OA) phenotype classification using a small dataset (n=50). Materials and Methods: For this retrospective study, we collected 3,166 three-dimensional (3D) double-echo steady-state magnetic resonance (MR) images from the Osteoarthritis Initiative dataset and 50 3D turbo/fast spin-echo MR images from our institute (in 2020 and 2021) as the source and target datasets, respectively. For each patient, the degree of knee OA was initially graded according to the MRI Osteoarthritis Knee Score (MOAKS) before being converted to binary OA phenotype labels. The proposed UDA pipeline included (a) pre-processing, which involved automatic segmentation and region-of-interest cropping; (b) source classifier training, which involved pre-training phenotype classifiers on the source dataset; (c) target encoder adaptation, which involved unsupervised adaption of the source encoder to the target encoder and (d) target classifier validation, which involved statistical analysis of the target classification performance evaluated by the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity and accuracy. Additionally, a classifier was trained without UDA for comparison. Results: The target classifier trained with UDA achieved improved AUROC, sensitivity, specificity and accuracy for both knee OA phenotypes compared with the classifier trained without UDA. Conclusion: The proposed UDA approach improves the performance of automated knee OA phenotype classification for small target datasets by utilising a large, high-quality source dataset for training. The results successfully demonstrated the advantages of the UDA approach in classification on small datasets., Comment: Junru Zhong and Yongcheng Yao share the same contribution. 17 pages, 4 figures, 4 tables

Two-dimensional (2D) fast spin echo (FSE) techniques play a central role in the clinical magnetic resonance imaging (MRI) of knee joints. Moreover, three-dimensional (3D) FSE provides high-isotropic-resolution magnetic resonance (MR) images of knee joints, but it has a reduced signal-to-noise ratio compared to 2D FSE. Deep-learning denoising methods are a promising approach for denoising MR images, but they are often trained using synthetic noise due to challenges in obtaining true noise distributions for MR images. In this study, inherent true noise information from 2-NEX acquisition was used to develop a deep-learning model based on residual learning of convolutional neural network (CNN), and this model was used to suppress the noise in 3D FSE MR images of knee joints. The proposed CNN used two-step residual learning over parallel transporting and residual blocks and was designed to comprehensively learn real noise features from 2-NEX training data. The results of an ablation study validated the network design. The new method achieved improved denoising performance of 3D FSE knee MR images compared with current state-of-the-art methods, based on the peak signal-to-noise ratio and structural similarity index measure. The improved image quality after denoising using the new method was verified by radiological evaluation. A deep CNN using the inherent spatial-varying noise information in 2-NEX acquisitions was developed. This method showed promise for clinical MRI assessments of the knee, and has potential applications for the assessment of other anatomical structures., Comment: 6 figures, abstract accepted by Joint Annual Meeting ISMRM-ESMRMB & ISMRT 31st Annual Meeting

Introduction: This study evaluated algorithm-based qualitative (ABQ) method for vertebral fracture (VF) evaluation with reference to semi-quantitative (SQ) method and bone mineral density (BMD) measurement. Methods: Mr. OS (Hong Kong) and Ms. OS (Hong Kong) represent the first large-scale cohort studies on bone health in elderly Chinese men and women. The current study compared Genant's SQ method and ABQ method in these two cohorts. Based on quantitative measurement, the severity of ABQ method detected fractures was additionally classified into grade-1, grad-2, and grade-3 according to SQ's deformity criteria. The radiographs of 1,954 elderly Chinese men (mean: 72.3 years) and 1,953 elderly Chinese women (mean: 72.5 years) were evaluated. Results: according to ABQ, grade-1,-2,-3 VFs accounted for 1.89%, 1.74%, 2.25% in men, and 3.33%, 3.07%, and 5.53% in women. In men and women, 15.7% (35/223) and 34.5% (48/139) of vertebrae with SQ grade-1 deformity were ABQ(+, with fracture) respectively. In men and women, 89.7% (35/39) and 66.7% (48/72) of vertebrae with ABQ grade-1 fracture had SQ grade-1 deformity. For grade-1 change, SQ (-, negative without fracture) & ABQ (+, positive with vertebral cortex line fracture) subjects tend to have a lower BMD than the SQ(+)& ABQ(-) subjects. In subjects with SQ grade-2 deformity, those were also ABQ(+) tended to have a lower BMD than those were ABQ(-). In all grades, SQ(-)&ABQ(-) subjects tended to have highest BMD, while SQ(+)&ABQ(+)subjects tended to have lowest BMD. Conclusion: ABQ method may be more sensitive to VF associated mild lower BMD than SQ method., Comment: 26 pages,4 figures, 6 tables