Abstract
Musculoskeletal diseases such as sarcopenia and osteoporosis are major obstacles to health during aging. Although dual-energy X-ray absorptiometry (DXA) and computed tomography (CT) can be used to evaluate musculoskeletal conditions, frequent monitoring is difficult due to the cost and accessibility (as well as high radiation exposure in the case of CT). We propose a method (named MSKdeX) to estimate fine-grained muscle properties from a plain X-ray image, a low-cost, low-radiation, and highly accessible imaging modality, through musculoskeletal decomposition leveraging fine-grained segmentation in CT. We train a multi-channel quantitative image translation model to decompose an X-ray image into projections of CT of individual muscles to infer the lean muscle mass and muscle volume. We propose the object-wise intensity-sum loss, a simple yet surprisingly effective metric invariant to muscle deformation and projection direction, utilizing information in CT and X-ray images collected from the same patient. While our method is basically an unpaired image-to-image translation, we also exploit the nature of the bone’s rigidity, which provides the paired data through 2D-3D rigid registration, adding strong pixel-wise supervision in unpaired training. Through the evaluation using a 539-patient dataset, we showed that the proposed method significantly outperformed conventional methods. The average Pearson correlation coefficient between the predicted and CT-derived ground truth metrics was increased from 0.460 to 0.863. We believe our method opened up a new musculoskeletal diagnosis method and has the potential to be extended to broader applications in multi-channel quantitative image translation tasks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kitamura, A., Seino, S., Takumi, A., et al.: Sarcopenia: prevalence, associated factors, and the risk of mortality and disability in Japanese older adults. J. Cachexia Sarcopenia Muscle 12(1), 30–38 (2021). https://doi.org/10.1002/jcsm.12651
Chen, L.-K., Lee, W.-J., Peng, L.-N., Liu, L.-K., et al.: Recent advances in sarcopenia research in Asia: 2016 update from the Asian Working Group for Sarcopenia. JAMDA 17(8), 767.e1-767.e7 (2016). https://doi.org/10.1016/j.jamda.2016.05.016
Marzetti, E., Calvani, R., Tosato, M., Cesari, M., et al.: Sacopenia: an overview. Aging Clin. Exp. Res. 29, 11–17 (2017). https://doi.org/10.1007/s40520-016-0704-5
Petermann-Rocha, F., Balntze, V., Gray, S.R., et al.: Global prevalence of sarcopenia and severe sarcopenia: a systematic review and meta-analysis. J. Cachexia Sarcopenia Muscle 13(1), 86–99 (2022). https://doi.org/10.1002/jcsm.12783
Shu, X., Lin, T., Wang, H., Zhao, Y., et al.: Diagnosis, prevalence, and mortality of sarcopenia in dialysis patients: a systematic review and meta-analysis. J. Cachexia Sarcopenia Muscle 13(1), 145–158 (2022). https://doi.org/10.1002/jcsm.12890
Edwards, M.H., Dennision, E.M., Sayer, A.A., et al.: Osteoporosis and sarcopenia in older age. Bone 80, 126–130 (2015). https://doi.org/10.1016/j.bone.2015.04.016
Shepherd, J., Ng, B., Sommer, M., Heymsfield, S.B.: Body composition by DXA. Bone 104, 101–105 (2017). https://doi.org/10.1016/j.bone.2017.06.010
Nana, A., Slater, G.J., Stewart, A.D., Burke, L.M.: Methodology review: using dual-energy X-ray absorptiometry (DXA) for the assessment of body composition in athletes and active people. Int. J. Sport Nutr. Exerc. Metab. 25(2), 198–215 (2015). https://doi.org/10.1123/ijsnem.2013-0228
Feliciano, E.M.C., et al.: Evaluation of automated computed tomography segmentation to assess body composition and mortality associations in cancer patients. J. Cachexia Sarcopenia Muscle 11(5), 1258–1269 (2020). https://doi.org/10.1002/jcsm.12573
Paris, M.T., Tandon, P., Heyland, D.K., et al.: Automated body composition analysis of clinically acquired computed tomography scans using neural networks. Clin. Nutr. 39(10), 3049–3055 (2020). https://doi.org/10.1016/j.clnu.2020.01.008
Ogawa, T., Takao, M., et al.: Validation study of the CT-based cross-sectional evaluation of muscular atrophy and fatty degeneration around the pelvis and the femur. J. Orthop. 25(1), 139–144 (2020). https://doi.org/10.1016/j.jos.2019.02.004
Hsieh, C.-I., Zheng, K., Lin, C., Mei, L., et al.: Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning. Nat. Commun. 12(1), 5472 (2021). https://doi.org/10.1038/s41467-021-25779-x
Wang, F., Zheng, K., Lu, Le, et al.: Lumbar bone mineral density estimation from chest X-ray images: anatomy-aware attentive multi-ROI modeling. IEEE Trans. Med. Imaging. 42(1), 257–267 (2023). https://doi.org/10.1109/TMI.2022.3209648
Ho, C.-S., Chen, Y.-P., Fan, T.-Y., Kuo, C.-F., et al.: Application of deep learning neural network in predicting bone mineral density from plain X-ray radiography. Arch. Osteoporosis 16(1), 153 (2021). https://doi.org/10.1007/s11657-021-00985-8
Gu, Y., et al.: BMD-GAN: bone mineral density estimation using X-Ray image decomposition into projections of bone-segmented quantitative computed tomography using hierarchical learning. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. MICCAI 2022. LNCS, vol. 13436, pp. 644–654. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16446-0_61
Ryu, J., et al.: Chest X-ray-based opportunistic screening of sarcopenia using deep learning. J. Cachexia Sarcopenia Muscle 14(1), 418–428 (2023). https://doi.org/10.1002/jcsm.13144
Nakanishi, N., Otake, Y., Hiasa, Y., Gu, Y., Uemura, K., et al.: Decomposition of musculoskeletal structures from radiography using an improved CycleGAN framework. Sci. Rep. 13, 8482 (2023). https://doi.org/10.1038/s41598-023-35075-x
Hiasa, Y., Otake, Y., et al.: Automated muscle segmentation from clinical CT using Bayesian U-Net for personalized musculoskeletal modeling. IEEE Trans. Med. Imaging 39(4), 1030–1040 (2019). https://doi.org/10.1109/TMI.2019.2940555
Aubrey, J., Esfandiari, N., Baracos, V.E., Buteau, F.A., et al.: Measurement of skeletal muscle radiation attenuation and basis of its biological variation. Acta Physiol. (Oxf) 210(3), 489–497 (2014). https://doi.org/10.1111/apha.12224
Wilfried, S., Thomas, B., Wolfgang, S.: Correlation between CT numbers and tissue parameters needed for Monte Carlo simulations of clinical dose distributions. Phys. Med. Biol. 45(2), 459 (2000). https://doi.org/10.1088/0031-9155/45/2/314
Otake, Y., et al.: Intraoperative image-based multiview 2D/3D registration for image-guided orthopaedic surgery: incorporation of fiducial-based C-arm tracking and GPU-acceleration. IEEE Trans. Med. Imaging 31(4), 948–962 (2012)
Hiasa, Y., et al.: Cross-modality image synthesis from unpaired data using CycleGAN. In: Gooya, A., Goksel, O., Oguz, I., Burgos, N. (eds.) SASHIMI 2018. LNCS, vol. 11037, pp. 31–41. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00536-8_4
Zhu, J.-Y., Park. T., Isola, P. Efros, A. A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV 2017, pp. 2242–2251 (2017)
Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE TPAMI 43(10), 3349–3364 (2021). https://doi.org/10.1109/TPAMI.2020.2983686
Acknowledgement
The research in this paper was funded by MEXT/JSPS KAKENHI (19H01176, 20H04550, 21K16655).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Code Availability
The code is available from the authors ({gu.yi.gu4,otake, yoshi}@is.naist.jp) upon reasonable request for research activity.
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gu, Y. et al. (2023). MSKdeX: Musculoskeletal (MSK) Decomposition from an X-Ray Image for Fine-Grained Estimation of Lean Muscle Mass and Muscle Volume. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14226. Springer, Cham. https://doi.org/10.1007/978-3-031-43990-2_47
Download citation
DOI: https://doi.org/10.1007/978-3-031-43990-2_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43989-6
Online ISBN: 978-3-031-43990-2
eBook Packages: Computer ScienceComputer Science (R0)