Abstract
Developmental Dysplasia of the Hip (DDH) is the most common paediatric hip disorder and a major cause of early hip replacement and osteoarthritis (OA) in young adults. Clinical practice for diagnosis remains reliant on manual measurement of pediatric hip joint features from 2D Ultrasound (US) scans, a process plagued with high inter/intra operator and scan variability. Recently, 3D US was shown to be markedly more reliable with deeply-learned image features effectively used to localize and measure anatomical bone landmarks. However, opaqueness of neural-net based analysis provides no means for assessing the reliability of computed results, a limitation that hampers deployment in clinical settings. We propose using interpretable uncertainty measures that can simultaneously measure bone segmentation reliability and quantify scan adequacy in clinical DDH assessment from 3D US. Our approach measures the variability of estimates generated from an encoder-decoder type CNN optimized for hip joint localization using random dropout. We quantitatively evaluate our proposed uncertainty estimates on a clinical dataset comprising 118 neonates. Results demonstrate smaller variability in dysplasia metrics to be markedly correlated with higher Dice scores for repeated segmentation estimates. Further, we observe that US scans with lower dysplasia metric variability are strongly associated with those labelled as clinically adequate by a human expert. Findings suggest that our uncertainty estimation may improve clinical workflow acting as a quality control check on deep learning based analysis. This in turn may improve overall reliability of the diagnostic process and the prospects of adoption in clinical settings.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cox, P., Woodacre, T.: The costs of late detection of developmental dysplasia of the hip. Orthop. Proc. 95-B(SUPP\(\_\)18), 14–14 (2013). https://doi.org/10.1302/1358-992X.95BSUPP_18.SWOC2012-014
Denker, J.S., LeCun, Y.: Transforming neural-net output levels to probability distributions. In: NIPS (1990)
El-Hariri, H., Mulpuri, K., Hodgson, A., Garbi, R.: Comparative Evaluation of Hand-Engineered and Deep-Learned Features for Neonatal Hip Bone Segmentation in Ultrasound. In: Shen, D., Liu, T., Peters, T.M., Staib, L.H., Essert, C., Zhou, S., Yap, P.-T., Khan, A. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 12–20. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_2
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: International Conference on Machine Learning, pp. 1050–1059 (2016)
Loder, R.T., Skopelja, E.N.: The epidemiology and demographics of hip dysplasia. ISRN Orthop. 2011, 46 (2011)
Paserin, O., Mulpuri, K., Cooper, A., Hodgson, A.J., Garbi, R.: Real Time RNN Based 3D Ultrasound Scan Adequacy for Developmental Dysplasia of the Hip. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 365–373. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_42
Quader, N., Hodgson, A., Mulpuri, K., Cooper, A., Abugharbieh, R.: Towards Reliable Automatic Characterization of Neonatal Hip Dysplasia from 3D Ultrasound Images. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9900, pp. 602–609. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46720-7_70
Quader, N., Hodgson, A.J., Mulpuri, K., Cooper, A., Abugharbieh, R.: A 3D femoral head coverage metric for enhanced reliability in diagnosing hip dysplasia. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 100–107. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66182-7_12
Quader, N., Hodgson, A.J., Mulpuri, K., Schaeffer, E., Abugharbieh, R.: Automatic evaluation of scan adequacy and dysplasia metrics in 2-D ultrasound images of the neonatal hip. Ultrasound Med. Biol. 43(6), 1252–1262 (2017)
Quader, N., Schaeffer, E.K., Hodgson, A.J., Abugharbieh, R., Mulpuri, K.: A systematic review and meta-analysis on the reproducibility of ultrasound-based metrics for assessing developmental dysplasia of the hip. J. Pediatr. Orthop. 38(6), e305–e311 (2018)
Roy, A.G., Conjeti, S., Navab, N., Wachinger, C.: Inherent brain segmentation quality control from fully ConvNet Monte Carlo sampling. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 664–672. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_75
Acknowledgement
We would like to thank NVIDIA Corporation and Compute Canada for supporting our research through their GPU grant program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kannan, A., Hodgson, A., Mulpuri, K., Garbi, R. (2020). Uncertainty Estimation for Assessment of 3D US Scan Adequacy and DDH Metric Reliability. In: Sudre, C.H., et al. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Graphs in Biomedical Image Analysis. UNSURE GRAIL 2020 2020. Lecture Notes in Computer Science(), vol 12443. Springer, Cham. https://doi.org/10.1007/978-3-030-60365-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-60365-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60364-9
Online ISBN: 978-3-030-60365-6
eBook Packages: Computer ScienceComputer Science (R0)