Abstract
Purpose
A new algorithm, based on fully convolutional networks (FCN), is proposed for the automatic localization of the bone interface in ultrasound (US) images. The aim of this paper is to compare and validate this method with (1) a manual segmentation and (2) a state-of-the-art method called confidence in phase symmetry (CPS).
Methods
The dataset used for this study was composed of 1738 US images collected from three volunteers and manually delineated by three experts. The inter- and intra-observer variabilities of this manual delineation were assessed. Images having annotations with an inter-observer variability higher than a confidence threshold were rejected, resulting in 1287 images. Both FCN-based and CPS approaches were studied and compared to the average inter-observer segmentation according to six criteria: recall, precision, F1 score, accuracy, specificity and root-mean-square error (RMSE).
Results
The intra- and inter-observer variabilities were inferior to 1 mm for 90% of manual annotations. The RMSE was 1.32 ± 3.70 mm and 5.00 ± 7.70 mm for, respectively, the FCN-based approach and the CPS algorithm. The mean recall, precision, F1 score, accuracy and specificity were, respectively, 62%, 64%, 57%, 80% and 83% for the FCN-based approach and 66%, 34%, 41%, 52% and 43% for the CPS algorithm.
Conclusion
The FCN-based approach outperforms the CPS algorithm, and the obtained RMSE is similar to the manual segmentation uncertainty.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Joskowicz L, Hazan EJ (2016) Computer aided orthopaedic surgery: incremental shift or paradigm change? Med Image Anal 33:84–90. https://doi.org/10.1016/j.media.2016.06.036
Sugano N (2013) Computer-assisted orthopaedic surgery and robotic surgery in total hip arthroplasty. Clin Orthop Surg. https://doi.org/10.4055/cios.2013.5.1.1
Sugano N (2003) Computer-assisted orthopedic surgery. J Orthop Sci 8:442–448. https://doi.org/10.1007/s10776-002-0623-6
Dib Z, Dardenne G, Poirier N, Huet P-Y, Lefevre C, Stindel E (2013) Detection of the hip center in computer-assisted surgery: an in vitro assessment study. IRBM 34:319–321. https://doi.org/10.1016/j.irbm.2013.08.005
Stindel E, Gil D, Briard J-L, Merloz P, Dé F, Dubrana R, Lefevre C (2005) Detection of the center of the hip joint in computer-assisted surgery: an evaluation study of the surgetics algorithm. Comput Aided Surg 10:133–139. https://doi.org/10.1080/10929080500229975
Stindel E, Briard J, Lverloz P, Dubrana F, Troccaz J (2002) Biomedical pear bone morphing: 3D morphological data for total knee arthroplasty. Comput Aided Surg 7:156–168. https://doi.org/10.3109/10929080209146026
Hacihaliloglu I (2017) Ultrasound imaging and segmentation of bone surfaces: a review. Technology 5:74–80. https://doi.org/10.1142/S2339547817300049
Mercier L, Langø T, Lindseth F, Collins LD (2005) A review of calibration techniques for freehand 3-D ultrasound systems. Ultrasound Med Biol. https://doi.org/10.1016/j.ultrasmedbio.2004.11.001
Ozdemir F, Ozkan E, Goksel O (2016) Graphical modeling of ultrasound propagation in tissue for automatic bone segmentation. In: International conference on medical image computing and computer-assisted intervention, Springer, Cham, pp 256–264. https://doi.org/10.1007/978-3-319-46723-8_30
Schumann S (2016) State of the art of ultrasound-based registration in computer assisted orthopedic interventions. Springer, Cham, pp 271–297
Hacihaliloglu I, Abugharbieh R, Hodgson AJ, Rohling RN, Guy P (2012) Automatic bone localization and fracture detection from volumetric ultrasound images using 3-D local phase features. World Fed Ultrasound Med Biol. https://doi.org/10.1016/j.ultrasmedbio.2011.10.009
Jia R, Mellon SJ, Hansjee S, Monk AP, Murray DW, Noble JA (2016) Automatic bone segmentation in ultrasound images using local phase features and dynamic programming. In: 2016 IEEE 13th international symposium on biomedical imaging (ISBI), IEEE, pp 1005–1008
Berton F, Cheriet F, Miron M-C, Laporte C (2016) Segmentation of the spinous process and its acoustic shadow in vertebral ultrasound images. Comput Biol Med. https://doi.org/10.1016/j.compbiomed.2016.03.018
Quader N, Hodgson A, Abugharbieh R (2014) Confidence weighted local phase features for robust bone surface segmentation in ultrasound. Lect Notes Comput Sci 8680:76–83. https://doi.org/10.1007/978-3-319-13909-8_10
Karamalis A, Wein W, Klein T, Navab N (2012) Ultrasound confidence maps using random walks. Med Image Anal 16:1101–1112. https://doi.org/10.1016/j.media.2012.07.005
Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. Miccai. https://doi.org/10.1007/978-3-319-24574-4_28
Moeskops P, Wolterink JM, van der Velden BHM, Gilhuijs KGA, Leiner T, Viergever MA, Išgum I (2017) Deep learning for multi-task medical image segmentation in multiple modalities. In: Miccai, pp 478–486
Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal. https://doi.org/10.1016/j.media.2017.07.005
Salehi M, Prevost R, Moctezuma JL, Navab N, Wein W (2017) Precise ultrasound bone registration with learning-based segmentation and speed of sound calibration. In: International conference on medical image computing and computer-assisted intervention, Springer, Cham, pp 682–690
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440
Jain AK, Taylor RH (2004) Understanding bone responses in B-mode ultrasound images and automatic bone surface extraction using a Bayesian probabilistic framework. Proc SPIE 5373:131–142. https://doi.org/10.1117/12.535984
Baka N, Leenstra S, van Walsum T (2017) Ultrasound aided vertebral level localization for lumbar surgery. IEEE Trans Med Imaging 36:2138–2147. https://doi.org/10.1109/TMI.2017.2738612
Galar M, Fernández A, Barrenechea E, Bustince H, Herrera F (2012) A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Trans Syst Man Cybern Part C. https://doi.org/10.1109/tsmcc.2011.2161285
Rushi Longadge M, Snehlata M, Dongre S, Malik L (2013) Class imbalance problem in data mining: review. Int J Comput Sci Netw 2:2277–5420
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, ACM, pp 675–678
Karamalis A (2013) Source code: Athanasios Karamalis. http://campar.in.tum.de/Main/AthanasiosKaramalisCode. Accessed 15 Apr 2018
Phasepack 1.5: A toolkit for phase-based feature detection. https://pypi.python.org/pypi/phasepack/1.5
Ben-David S, Shalev-Shwartz S (2014) Understanding machine learning: from theory to algorithms. Cambridge University Press, Cambridge
Chatelain P, Krupa A, Navab N (2015) Confidence-driven control of an ultrasound probe. IEEE Int Conf Robot Autom 2:1410–1424
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.
Rights and permissions
About this article
Cite this article
Villa, M., Dardenne, G., Nasan, M. et al. FCN-based approach for the automatic segmentation of bone surfaces in ultrasound images. Int J CARS 13, 1707–1716 (2018). https://doi.org/10.1007/s11548-018-1856-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-018-1856-x