Point Cloud Learning for Automated Reconstruction and Quantification of Human Skeletal Anatomy

Authors

  • Suus van Hostaden School of Information Technology, University of Cincinnati, Cincinnati, OH, USA.

Keywords:

point cloud learning; skeletal anatomy; anatomical landmarks; shape completion; uncertainty quantification; statistical shape models

Abstract

Automated reconstruction and quantification of human skeletal anatomy from three-dimensional point clouds is complicated by partial coverage, thin cortical surfaces, sparse anatomical labels, and measurement requirements that differ from generic object segmentation. This manuscript develops an anatomy-constrained point-cloud learning framework that links semantic reconstruction, landmark localization, template-based shape completion, and uncertainty-aware quantification in one inferential sequence. The input is a calibrated but incomplete bone-surface point cloud; the outputs are anatomical labels, landmarks, a completed surface consistent with a statistical shape prior, and derived linear, angular, and curvature measures. A hierarchical point encoder extracts local geometry, a multi-task head combines dense segmentation with sparse landmark supervision, and a deformation energy regularizes completion and registration toward anatomically plausible shapes. Quantification is expressed as a measurement map defined on the reconstructed surface, with predictive uncertainty decomposed into epistemic and aleatoric components. An acceptance rule converts calibrated uncertainty and surface coverage into a review decision rather than a silent automated output. The analysis identifies the principal failure modes: landmark displacement near axes of rotation, template bias in rare morphology, hallucinated geometry in unobserved regions, and propagation of segmentation error into clinical measurements. The framework's contribution is methodological: it specifies how reconstruction, shape priors, and measurement uncertainty should be coupled so that quantified skeletal anatomy remains traceable to observed evidence. This framing supports reproducible evaluation and safer translation of point-cloud learning into surgical planning, orthopaedic assessment, and anatomical research.

References

1. Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017). PointNet: Deep learning on point sets for 3D classification and segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 652–660.

2. Qi, C. R., Yi, L., Su, H., & Guibas, L. J. (2017). PointNet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems, 30, 5099–5108.

3. Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019). Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics, 38(5), Article 146.

4. Thomas, H., Qi, C. R., Deschaud, J.-E., Marcotegui, B., Goulette, F., & Guibas, L. J. (2019). KPConv: Flexible and deformable convolution for point clouds. Proceedings of the IEEE/CVF International Conference on Computer Vision, 6411–6420.

5. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88.

6. Liu, S., Jin, J., Li, W., & Yan, X. (2026). Segmentation-Guided Semi-Supervised Landmark Detection on Intraoral 3D Scans. Preprints. https://doi.org/10.20944/preprints202609.1722.v1

7. Cootes, T. F., Taylor, C. J., Cooper, D. H., & Graham, J. (1995). Active shape models—their training and application. Computer Vision and Image Understanding, 61(1), 38–59.

8. Heimann, T., & Meinzer, H.-P. (2009). Statistical shape models for 3D medical image segmentation: A review. Medical Image Analysis, 13(4), 543–563.

9. Sarkalkan, N., Weinans, H., & Zadpoor, A. A. (2014). Statistical shape and appearance models of bones. Bone, 60, 129–140.

10. Yuan, W., Khot, T., Held, D., Mertz, C., & Hebert, M. (2018). PCN: Point completion network. 2018 International Conference on 3D Vision, 728–737.

11. Xie, H., Yao, H., Zhou, S., Mao, J., Zhang, S., & Sun, W. (2020). GRNet: Gridding residual network for dense point cloud completion. Computer Vision – ECCV 2020, 12351, 365–381.

12. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, 9351, 234–241.

13. Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016). 3D U-Net: Learning dense volumetric segmentation from sparse annotation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, 9901, 424–432.

14. Besl, P. J., & McKay, N. D. (1992). A method for registration of 3-D shapes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14(2), 239–256.

15. Goodall, C. (1991). Procrustes methods in the statistical analysis of shape. Journal of the Royal Statistical Society: Series B, 53(2), 285–339.

16. Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? Advances in Neural Information Processing Systems, 30, 5574–5584.

17. Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the 33rd International Conference on Machine Learning, 48, 1050–1059.

18. Taha, A. A., & Hanbury, A. (2015). Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Medical Imaging, 15, Article 29.

19. Ambellan, F., Tack, A., Ehlke, M., & Zachow, S. (2019). Automated segmentation of knee bone and cartilage combining statistical shape knowledge and convolutional neural networks: Data from the Osteoarthritis Initiative. Medical Image Analysis, 52, 109–118.

Downloads

Published

2026-09-24

How to Cite

Suus van Hostaden. (2026). Point Cloud Learning for Automated Reconstruction and Quantification of Human Skeletal Anatomy. International Journal of Clinical and Translational Medicine, 2(2). Retrieved from https://ijctmed.org/index.php/home/article/view/239