Abstract
Landmark localization is an important step in image analysis, where the clinical definition of a landmark can be ambiguous, leading to a practical necessity for model uncertainty quantification that is rigorous and trustworthy. In this paper, we present the first Bayesian framework using Gaussian processes to capture both dataset-level landmark ambiguity and sample-level model uncertainty. Our proposed two-stage approach includes a deep learning based U-Net for coarse predictions, followed by a convolutional Gaussian process (CGP) for fine-grained predictions with uncertainty estimates, learning covariance matrices rather than using a pre-defined covariance matrix. Our Bayesian approach yields a more rigorous quantification of uncertainty compared to deep learning-based uncertainty estimation techniques, whilst still achieving comparable localization accuracy. Our results suggest that CGPs can better model the inherent uncertainties in landmark localization tasks and provide more reliable confidence estimates, making it a promising direction for future research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alvarez, M.A., Lawrence, N.D.: Computationally efficient convolved multiple output Gaussian processes. J. Mach. Learn. Res. 12, 1459–1500 (2011)
Beichel, R., Bischof, H., Leberl, F., Sonka, M.: Robust active appearance models and their application to medical image analysis. IEEE Trans. Med. Imaging 24(9), 1151–1169 (2005)
Branch, M.A., Coleman, T.F., Li, Y.: A subspace, interior, and conjugate gradient method for large-scale bound-constrained minimization problems. SIAM J. Sci. Comput. 21(1), 1–23 (1999)
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: Proceedings ICML, pp. 1321–1330. PMLR (2017)
Holzinger, A.: Interactive machine learning for health informatics: when do we need the human-in-the-loop? Brain Inf. 3(2), 119–131 (2016)
Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnU-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021)
Jiang, Y., Li, Y., Wang, X., Tao, Y., Lin, J., Lin, H.: CephalFormer: incorporating global structure constraint into visual features for general cephalometric landmark detection. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Proceedings MICCAI, pp. 227–237. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16437-8_22
Johnson, H.J., Christensen, G.E.: Consistent landmark and intensity-based image registration. IEEE Trans. Med. Imaging 21(5), 450–461 (2002)
Journel, A.G., Huijbregts, C.J.: Mining geostatistics (1976)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Lee, J.H., Yu, H.J., Kim, M.J., Kim, J.W., Choi, J.: Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networks. BMC Oral Health 20(1), 1–10 (2020)
Leibfried, F., Dutordoir, V., John, S., Durrande, N.: A tutorial on sparse Gaussian processes and variational inference. arXiv preprint arXiv:2012.13962 (2020)
Lindner, C., Wang, C.W., Huang, C.T., Li, C.H., Chang, S.W., Cootes, T.F.: Fully automatic system for accurate localisation and analysis of cephalometric landmarks in lateral cephalograms. Sci. Rep. 6(1), 1–10 (2016)
Murphy, K., et al.: Semi-automatic construction of reference standards for evaluation of image registration. Med. Image Anal. 15(1), 71–84 (2011)
Payer, C., Štern, D., Bischof, H., Urschler, M.: Integrating spatial configuration into heatmap regression based CNNs for landmark localization. Med. Image Anal. 54, 207–219 (2019)
Payer, C., Urschler, M., Bischof, H., Štern, D.: Uncertainty estimation in landmark localization based on Gaussian heatmaps. In: Sudre, C.H., et al. (eds.) UNSURE/GRAIL -2020. LNCS, vol. 12443, pp. 42–51. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60365-6_5
Rasmussen, C.E.: Gaussian processes in machine learning. In: Bousquet, O., von Luxburg, U., Rätsch, G. (eds.) ML -2003. LNCS (LNAI), vol. 3176, pp. 63–71. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-28650-9_4
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
Schöbs, L., Swift, A.J., Lu, H.: Uncertainty estimation for heatmap-based landmark localization. IEEE Trans. Med Imaging, 1 (2022)
Thaler, F., Payer, C., Urschler, M., Štern, D., et al.: Modeling annotation uncertainty with Gaussian heatmaps in landmark localization. J. Mach. Learn. Biomed. Imaging 1, 1–10 (2021)
Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)
Wang, C.W., et al.: A benchmark for comparison of dental radiography analysis algorithms. Med. Image Anal. 31, 63–76 (2016)
Van der Wilk, M., Rasmussen, C.E., Hensman, J.: Convolutional Gaussian processes. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Zhong, Z., Li, J., Zhang, Z., Jiao, Z., Gao, X.: An attention-guided deep regression model for landmark detection in cephalograms. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 540–548. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_60
Acknowledgements
This work was supported by EPSRC (2274702) and the Welcome Trust (215799/Z/19/Z and 205188/Z/16/Z). Thomas M. McDonald would like to thank the Department of Computer Science at The University of Manchester for their financial support.
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
Schobs, L., McDonald, T.M., Lu, H. (2023). Bayesian Uncertainty Estimation in Landmark Localization Using Convolutional Gaussian Processes. In: Sudre, C.H., Baumgartner, C.F., Dalca, A., Mehta, R., Qin, C., Wells, W.M. (eds) Uncertainty for Safe Utilization of Machine Learning in Medical Imaging. UNSURE 2023. Lecture Notes in Computer Science, vol 14291. Springer, Cham. https://doi.org/10.1007/978-3-031-44336-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-44336-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44335-0
Online ISBN: 978-3-031-44336-7
eBook Packages: Computer ScienceComputer Science (R0)