Abstract
Accurate skeleton segmentation of the entire anteroposterior bone scintigrams of the human body is essential for diagnosing bone metastases. However, conventional methods lack a loss design incorporating prior anatomical information, leading to segmentation failures, particularly when dealing with the irregular shapes of organs or high concentrations of positive accumulation. Cases where diagnostic support systems present anatomically abnormal findings may shatter the confidence of doctors and their reliability in these systems. In this paper, we propose a novel multi-factor component tree loss function to resolve the topological issues in segmentation failures. The proposed loss function, computed based on the component trees, comprises two factors: image maxima vanishment and reconnection. We aim to discard the false positive connected components (FPCCs) and reconnect the disconnected true positive connected components (TPCCs) for each bone. Experiments conducted on a private bone scintigrams dataset show that our proposed method outperforms state-of-the-art approaches in dice similarity coefficient (DSC) while efficiently addressing topological issues at a low computational cost. Code is available at https://github.com/MultiCTree/MultiCTree.
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
Siegel, R.L., Giaquinto, A.N., Jemal, A.: Cancer statistics, 2024. CA Cancer J. Clin. 74(1), 8–9 (2024)
Donohoe, K.J., et al.: Appropriate use criteria for bone scintigraphy in prostate and breast cancer: summary and excerpts. J. Nucl. Med. 58(4), 14N-17N (2017)
Imbriaco, M., et al.: A new parameter for measuring metastatic bone involvement by prostate cancer: the Bone Scan Index. Clin. Cancer Res. 4(7), 1765–1772 (1998)
Shimizu, A., et al.: Automated measurement of bone scan index from a whole-body bone scintigram. Int. J. Comput. Assist. Radiol. Surg. 15(3), 389–400 (2020)
Yu, P.N., Lai, Y.C., Chen, Y.Y., Cheng, D.C.: Skeleton Segmentation on Bone Scintigraphy for BSI Computation. Diagnostics (Basel, Switzerland) 13(13), 2302 (2023)
Clough, J.R., Byrne, N., Oksuz, I., Zimmer, V.A., Schnabel, J.A., King, A.P.: A topological loss function for deep-learning based image segmentation using persistent homology. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 8766–8778 (2022)
Shit, S., et al.: clDice - a novel topology-preserving loss function for tubular structure segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16555–16564. IEEE Computer Society, United States (2021)
Perret, B., Cousty, J.: Component tree loss function: definition and optimization. In: Baudrier, É., Naegel, B., Krähenbühl, A., Tajine, M. (eds.) DGMM 2022. LNCS, vol. 13493, pp. 248–260. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19897-7_20
Souza, R., Tavares, L., Rittner, L. Lotufo, R.: An overview of max-tree principles, algorithms and applications. In: 2016 29th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T), Sao Paulo, Brazil, pp. 15–23 (2016)
Vachier, C., Meyer, F.: Extinction value: a new measurement of persistence. In: IEEE Workshop on Nonlinear Signal and Image Processing, pp. 254–257 (1995)
Salembier, P., Oliveras, A., Garrido, L.: Antiextensive connected operators for image and sequence processing. IEEE Trans. Image Process. Publ. IEEE Sig. Process. Soc. 7(4), 555–570 (1998)
Dou, Q., et al.: 3D deeply supervised network for automated segmentation of volumetric medical images. Med. Image Anal. 41, 40–54 (2021)
Robbins, H., Monro, S.: A stochastic approximation method. Herbert Robbins Selected Papers, pp. 102–109 (1985)
Gabrielsson, R.B., Nelson, B.J., Dwaraknath, A., Skraba, P.: A topology layer for machine learning. In: Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, pp. 1553–1563 (2020)
Nguyen, Q.A., Cousty, J., Kenmochi, Y., Higashiyama, S., Kawabe, J., Shimizu, A.: Improvement of a skeleton segmentation model of bone scintigrams with a transformer and component tree loss function. In: CARS 2023-Computer Assisted Radiology and Surgery Proceedings of the 37th International Congress and Exhibition Munich, Germany, 20–23 June 2023, Int J CARS, pp. S17–S18 (2023)
Acknowledgments
This study was supported by the JSPS Sakura program (JPJSBP 120233206) and PHC Sakura program (No. 49674K).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
Akinobu Shimizu has received research grants from Nihon Medi-Physics Co., Ltd.
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Nguyen, A.Q., Cousty, J., Kenmochi, Y., Higashiyama, S., Kawabe, J., Shimizu, A. (2025). Multi-factor Component Tree Loss Function: A Topology-Preserving Method for Skeleton Segmentation from Bone Scintigrams. In: Chen, C., Singh, Y., Hu, X. (eds) Topology- and Graph-Informed Imaging Informatics. TGI3 2024. Lecture Notes in Computer Science, vol 15239. Springer, Cham. https://doi.org/10.1007/978-3-031-73967-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-73967-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-73966-8
Online ISBN: 978-3-031-73967-5
eBook Packages: Computer ScienceComputer Science (R0)
