Degeneration of articular cartilage (AC) is actively studied in knee osteoarthritis (OA) research via magnetic resonance imaging (MRI). Segmentation of AC tissues from MRI data is an essential step in quantification of their damage. Deep learning (DL) based methods have shown potential in this realm and are the current state-of-the-art, however, their robustness to heterogeneity of MRI acquisition settings remains an open problem. In this study, we investigated two modern regularization techniques -mixup and adversarial unsupervised domain adaptation (UDA) -to improve the robustness of DL-based knee cartilage segmentation to new MRI acquisition settings. Our validation setup included two datasets produced by different MRI scanners and using distinct data acquisition protocols. We assessed the robustness of automatic segmentation by comparing mixup and UDA approaches to a strong baseline method at different OA severity stages and, additionally, in relation to anatomical locations. Our results showed that for moderate changes in knee MRI data acquisition settings both approaches may provide notable improvements in the robustness, which are consistent for all stages of the disease and affect the clinically important areas of the knee joint. However, mixup may be considered as a recommended approach, since it is more computationally efficient and does not require additional data from the target acquisition setup.
This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Morphological changes in knee cartilage subregions are valuable imaging‐based biomarkers for understanding progression of osteoarthritis, and they are typically detected from magnetic resonance imaging (MRI). So far, accurate segmentation of cartilage has been done manually. Deep learning approaches show high promise in automating the task; however, they lack clinically relevant evaluation. We introduce a fully automatic method for segmentation and subregional assessment of articular cartilage, and evaluate its predictive power in context of radiographic osteoarthritis progression. Two data sets of 3D double‐echo steady‐state (DESS) MRI derived from the Osteoarthritis Initiative were used: first, n = 88; second, n = 600, 0‐/12‐/24‐month visits. Our method performed deep learning‐based segmentation of knee cartilage tissues, their subregional division via multi‐atlas registration, and extraction of subregional volume and thickness. The segmentation model was developed and assessed on the first data set. Subsequently, on the second data set, the morphological measurements from our and the prior methods were analyzed in correlation and agreement, and, eventually, by their discriminative power of radiographic osteoarthritis progression over 12 and 24 months, retrospectively. The segmentation model showed very high correlation (r > 0.934) and agreement (mean difference < 116 mm3) in volumetric measurements with the reference segmentations. Comparison of our and manual segmentation methods yielded r = 0.845–0.973 and mean differences = 262–501 mm3 for weight‐bearing cartilage volume, and r = 0.770–0.962 and mean differences = 0.513–1.138 mm for subregional cartilage thickness. With regard to osteoarthritis progression, our method found most of the significant associations identified using the manual segmentation method, for both 12‐ and 24‐month subregional cartilage changes. The method may be effectively applied in osteoarthritis progression studies to extract cartilage‐related imaging biomarkers.
Results:We found 4616 subjects with V00 MRI for both left and right knees. Due to missing WOMAC pain score, three subjects were excluded.The table includes the compartment markers with highest correlation to pain (rho > 0.15). These included cartilage quantity in the patello-femoral compartment and cartilage surface integrity markers in the tibio-femoral compartments. Also, internal structure markers for patellar cartilage and lateral meniscus were included. Finally, all Shape modes were included. Compartment abbreviations in the table: Lateral L, Medial M, Tibial T, Femoral F, anterior Femoral Fa, Patellar P, Meniscus M, Cartilage C.Conclusions: This study confirmed that bi-lateral difference analysis is appropriate when numerous inter-person confounding factors would otherwise potentially obscure the interpretation of the results. Even this very simple linear statistical analysis using the difference between left and right knee markers showed clear correlations with bi-lateral pain differences. Due to the inherent intra-person normalization, these correlations are more reliable than any single-knee, cross-sectional analysis where pain correlations will be challenged by numerous confounding factors such as central sensitization, demographics, mood, socio-economics, or even climate. For the individual difference markers, the strongest correlations with pain were for Shape modes, cartilage quantity markers (thickness/vol-
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.