Abstract
Random forests are widely used for classification and regression tasks in medical image analysis. Each tree in the forest contains binary decision nodes that choose whether a sample should be passed to one of two child nodes. We demonstrate that replacing this with something less decisive, where some samples may go to both child nodes, can improve performance for both individual trees and whole forests. Introducing a soft decision at each node means that a sample may propagate to multiple leaves. The tree output should thus be a weighted sum of the individual leaf values. We show how the leaves can be optimised to improve performance and how backpropagation can be used to optimise the parameters of the decision functions at each node. Finally, we show that the new method outperforms an equivalent random forest on a disease classification and prediction task.
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
References
Cootes, T.F., Taylor, C.J., et al.: Statistical models of appearance for computer vision (2004)
Cristinacce, D., Cootes, T.F.: Feature detection and tracking with constrained local models. In: BMVC (2006)
Felson, D., Niu, J., Neogi, T., Goggins, J., Nevitt, M., Roemer, F., Torner, J., Lewis, C., Guermazi, A., Group, M.I.: Synovitis and the risk of knee osteoarthritis: the MOST study. Osteoarthritis Cartilage 24(3), 458–464 (2016)
Kontschieder, P., Fiterau, M., Criminisi, A., Bulo, S.: Deep neural decision forests. In: International Conference on Computer Vision (2015)
Lindner, C., Bromiley, P., Ionita, M., Cootes, T.: Robust and accurate shape model matching using random forest regression-voting. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1862–1874 (2015)
Minciullo, L., Cootes, T.F.: Fully automated shape analysis for detection of osteoarthritis from lateral knee radiographs. In: ICPR (2016)
Minciullo, L., Thomson, J., Cootes, T.F.: Combination of lateral and PA view radiographs to study development of knee OA and associated pain. In: SPIE Medical Imaging, p. 1013411. International Society for Optics and Photonics (2017)
Ren, S., Cao, X., Wei, Y., Sun, J.: Global refinement of random forest. In: Computer Vision and Pattern Recognition (2015)
Suarez, A., Lutsko, J.: Globally optimal fuzzy decision trees for classification and regression. IEEE Trans. Pattern Anal. Mach. Intell. 21(12), 1297–1311 (1999)
Acknowledgments
The research leading to this results has received funding from EPSRC Centre for Doctoral Training grant 1512584. This publication also presents independent research supported by the Health Innovation Challenge Fund (grant no. HICF-R7-414/WT100936), a parallel funding partnership between the Department of Health and Wellcome Trust, and by the NIHR Invention for Innovation (i4i) programme (grant no. II-LB_0216-20009). The views expressed are those of the authors and not necessarily those of the NHS, NIHR, the Department of Health or Wellcome Trust.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Minciullo, L., Bromiley, P.A., Felson, D.T., Cootes, T.F. (2017). Indecisive Trees for Classification and Prediction of Knee Osteoarthritis. In: Wang, Q., Shi, Y., Suk, HI., Suzuki, K. (eds) Machine Learning in Medical Imaging. MLMI 2017. Lecture Notes in Computer Science(), vol 10541. Springer, Cham. https://doi.org/10.1007/978-3-319-67389-9_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-67389-9_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67388-2
Online ISBN: 978-3-319-67389-9
eBook Packages: Computer ScienceComputer Science (R0)