Abstract
Computed tomography (CT) scans of the abdomen have emerged as a robust, precise, and dependable means of determining body composition. The accurate prediction of skeletal muscle volume (SMV) using slices of CT scans holds critical importance in facilitating subsequent diagnosis and prognosis. A significant proportion of research in the field of abdominal image analysis is primarily focused on the third lumbar spine vertebra (L3), owing to two prominent factors. Firstly, L3 is a large vertebra situated in the middle of the lumbar spine, rendering it less susceptible to degenerative changes in comparison to other lumbar vertebrae, making it a stable landmark. Secondly, the slice labeling in a CT volume is an intricate and time-consuming process, demanding significant human efforts, whereas labeling a single slice from a specific vertebral level is comparatively simpler. This study leverages labeled L3 slices i.e., source domain to reliably predict unlabeled lumbar region slices other than L3 i.e., target domain. We use Cross-Domain Consistency Training (CDCT) to extend network’s current knowledge, acquired through segmenting a source domain, by learning to label a target domain. A consistency is enforced between the predictions from two segmentation networks with identical lightweight architecture but have different weight initialization points. The training objective consists of supervised loss terms for the source domain data and unsupervised loss terms for the target domain data. Remarkably, our trained network exhibits a marked enhancement in performance when applied to the target domain, indicating domain invariant feature learning through cross-domain consistency training could significantly enhance a network’s generalization capability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Public release of the dataset is subject to the approval from the Institutional Review Board/Ethics Committee of the Kyungpook National University Hospital and Kyungpook National University.
References
Ali, S., Mahmood, A., Jung, S.K.: Lightweight encoder-decoder architecture for foot ulcer segmentation. In: Sumi, K., Na, I.S., Kaneko, N. (eds.) IW-FCV 2022. CCIS, vol. 1578, pp. 242–253. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-06381-7_17
Chen, X., Yuan, Y., Zeng, G., Wang, J.: Semi-supervised semantic segmentation with cross pseudo supervision. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2613–2622 (2021)
Chen, Y.C., Lin, Y.Y., Yang, M.H., Huang, J.B.: CrDoCo: pixel-level domain transfer with cross-domain consistency. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1791–1800 (2019)
Englesson, E., Azizpour, H.: Generalized Jensen-Shannon divergence loss for learning with noisy labels. In: Advances in Neural Information Processing Systems 34, pp. 30284–30297 (2021)
Guan, H., Liu, M.: Domain adaptation for medical image analysis: a survey. IEEE Trans. Biomed. Eng. 69(3), 1173–1185 (2021)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, pp. 7482–7491 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Liebel, L., Körner, M.: Auxiliary tasks in multi-task learning. arXiv preprint arXiv:1805.06334, May 2018
Liu, X., et al.: Deep unsupervised domain adaptation: a review of recent advances and perspectives. APSIPA Trans. Signal Inf. Process. 11(1) (2022)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
Ouali, Y., Hudelot, C., Tami, M.: Semi-supervised semantic segmentation with cross-consistency training. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12674–12684 (2020)
Paris, M.T., et al.: Automated body composition analysis of clinically acquired computed tomography scans using neural networks. Clin. Nutr. 39, 3049–3055 (2020)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Zhou, K., Loy, C.C., Liu, Z.: Semi-supervised domain generalization with stochastic stylematch. arXiv preprint arXiv:2106.00592 (2021)
Acknowledgments
This study was supported by the AI-based CT Analysis Software Development project funded by AI Plus Healthcare Co., Ltd., Daegu, Korea (202300510000), the MSIT (Ministry of Science and ICT), Korea, under the Innovative Human Resource Development for Local Intellectualization support program (IITP-2022-RS-2022-00156389) supervised by the IITP (Institute of Information & Communications Technology Planning & Evaluation), and the BK21 FOUR project (AI-driven Convergence Software Education Research Program) funded by the MOE (Ministry of Education), School of Computer Science and Engineering, Kyungpook National University, Korea (4199990214394).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ali, S., Lee, Y.R., Park, S.Y., Tak, W.Y., Jung, S.K. (2023). Volumetric Body Composition Through Cross-Domain Consistency Training for Unsupervised Domain Adaptation. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2023. Lecture Notes in Computer Science, vol 14361. Springer, Cham. https://doi.org/10.1007/978-3-031-47969-4_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-47969-4_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47968-7
Online ISBN: 978-3-031-47969-4
eBook Packages: Computer ScienceComputer Science (R0)