Rytky, S.J.O., Huang, L., Tanska, P., Tiulpin, A., Panfilov, E., Herzog, W., Korhonen, R.K., Saarakkala, S. and Finnilä, M.A.J. (2021), Automated analysis of rabbit knee calcified cartilage morphology using micro-computed tomography and deep learning. J Anat, 239: 251-263. https://doi.org/10.1111/joa.13435
Automated analysis of rabbit knee calcified cartilage morphology using micro-computed tomography and deep learning
|Author:||Rytky, Santeri J. O.1; Huang, Lingwei2; Tanska, Petri2;|
1Research Unit of Medical Imaging, Physics and Technology, University of Oulu, Oulu, Finland
2Department of Applied Physics, University of Eastern Finland, Kuopio, Finland
3Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland
4Ailean Technologies Oy, Oulu, Finland
5Human Performance Laboratory, Faculty of Kinesiology, University of Calgary, Calgary, AB, Canada
|Online Access:||PDF Full Text (PDF, 1.9 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2021101451072
John Wiley & Sons,
|Publish Date:|| 2021-10-14
Structural dynamics of calcified cartilage (CC) are poorly understood. Conventionally, CC structure is analyzed using histological sections. Micro-computed tomography (µCT) allows for three-dimensional (3D) imaging of mineralized tissues; however, the segmentation between bone and mineralized cartilage is challenging. Here, we present state-of-the-art deep learning segmentation for µCT images to assess 3D CC morphology. The sample includes 16 knees from 12 New Zealand White rabbits dissected into osteochondral samples from six anatomical regions: lateral and medial femoral condyles, lateral and medial tibial plateaus, femoral groove, and patella (n = 96). The samples were imaged with µCT and processed for conventional histology. Manually segmented CC from the images was used to train segmentation models with different encoder–decoder architectures. The models with the greatest out-of-fold evaluation Dice score were selected. CC thickness was compared across 24 regions, co-registered between the imaging modalities using Pearson correlation and Bland–Altman analyses. Finally, the anatomical CC thickness variation was assessed via a Linear Mixed Model analysis. The best segmentation models yielded average Dice of 0.891 and 0.807 for histology and µCT segmentation, respectively. The correlation between the co-registered regions was strong (r = 0.897, bias = 21.9 µm, standard deviation = 21.5 µm). Finally, both methods could separate the CC thickness between the patella, femoral, and tibial regions (p < 0.001). As a conclusion, the proposed µCT analysis allows for ex vivo 3D assessment of CC morphology. We demonstrated the biomedical relevance of the method by quantifying CC thickness in different anatomical regions with a varying mean thickness. CC was thickest in the patella and thinnest in the tibial plateau. Our method is relatively straightforward to implement into standard µCT analysis pipelines, allowing the analysis of CC morphology. In future research, µCT imaging might be preferable to histology, especially when analyzing dynamic changes in cartilage mineralization. It could also provide further understanding of 3D morphological changes that may occur in mineralized cartilage, such as thickening of the subchondral plate in osteoarthritis and other joint diseases.
Journal of anatomy
|Pages:||251 - 263|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
3126 Surgery, anesthesiology, intensive care, radiology
The full source code of the project is openly available on our research unit’s GitHub page (https://github.com/MIPT-Oulu/RabbitCCS). S.J.O.R was supported by Intrumentarium Science Foundation (Grant No. 200058). P.T. acknowledges funding from the Finnish Cultural Foundation (Central Fund No. 191044) and Maire Lisko Foundation. A.T. is a CTO and a shareholder of Ailean Technologies Oy. W.H. was supported by The Canadian Institutes of Health Research (No. FDN-143341), The Canada Research Chair Programme (No. 950-200955), and Killam Foundation (No. 10001203). R.K.K. was supported by the Academy of Finland (no. 324529) and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 713645 (for L.H.). S.S. was supported by the Academy of Finland (no. 303786) and the European Research Council under the European Union’s Seventh Framework Programme (FP/2007–2013)/ERC Grant Agreement No. 336267. M.A.J.F. received funding from the Finnish Cultural Foundation (North Ostrobothnia Regional Fund No. 60172246). The strategic funding of the University of Oulu and the University of Eastern Finland are acknowledged. CSC—IT Center for Science, Espoo, Finland is acknowledged for generous computational resources.
|Academy of Finland Grant Number:||
303786 (Academy of Finland Funding decision)
© 2021 The Authors. Journal of Anatomy published by John Wiley & Sons Ltd on behalf of Anatomical Society. 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.