Abstract
Masticatory muscles are of significant aesthetic and functional importance to craniofacial developments. Automatic segmentation is a crucial step for shape and functional analysis of muscles. In this paper, we propose an automatic masseter segmentation framework using a deep neural network with coupled feature learning and label prediction pathways. The volumetric features are learned using the unsupervised convolutional auto-encoder and integrated with multi-level features in the label prediction pathway to augment features for segmentation. The label prediction pathway is built upon the nested residual network which is feasible for information propagation and fast convergence. The proposed method realizes the voxel-wise label inference of masseter muscles from the clinically captured computed tomography (CT) images. In the experiments, the proposed method outperforms the compared state-of-the-arts, achieving a mean Dice similarity coefficient (DSC) of \(93\pm 1.2\%\) for the segmentation of masseter muscles.
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
Cicek, z., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3d u-net: learning dense volumetric segmentation from sparse annotation. In: MICCAI, pp. 424–432
Criminisi, A., Robertson, D., Konukoglu, E., Shotton, J., Pathak, S., White, S., Siddiqui, K.: Regression forests for efficient anatomy detection and localization in computed tomography scans. Med. Image Anal. 17(8), 1293–1303 (2013)
Ghosh, S., Boulanger, P., Acton, S.T., Blemker, S.S., Ray, N.: Automated 3d muscle segmentation from mri data using convolutional neural network. In: IEEE ICIP (2017)
Guan, Q., Zhang, B., Long, H., Hu, H., Zhuang, X., Hu, Y., et al.: A modified distance regularized level set evolution for masseter segmentation. In: International Conference on Information Technology in Medicine and Education, pp. 16–19 (2017)
Majeed, T., Fundana, K., Lüthi, M., Kiriyanthan, S., Beinemann, J., Cattin, P.C., et al.: Using a flexibility constrained 3d statistical shape model for robust mrf-based segmentation. In: IEEE Workshop on Mathematical Methods in Biomedical Image Analysis (MMBIA), pp. 57–64. IEEE (2012)
Ng, H.P., Ong, S.H., Foong, K.W., Goh, P.S., Nowinski, W.L.: Masseter segmentation using an improved watershed algorithm with unsupervised classification. Comput. Biol. Med. 38(2), 171–184 (2008)
Ng, H.P., Ong, S.H., Liu, J., Huang, S., Foong, K.W.C., Goh, P.S., Nowinski, W.L.: 3d segmentation and quantification of a masticatory muscle from mr data using patient-specific models and matching distributions. J. Digit. Imaging 22(5), 449 (2009)
Nie, D., et al.: Segmentation of craniomaxillofacial bony structures from mri with a 3d deep-learning based cascade framework. In: International Workshop on Machine Learning in Medical Imaging, pp. 266–273 (2017)
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: IEEE International Conference on Computer Vision,. pp. 1520–1528 (2015)
Pei, Y., et al.: Multi-scale volumetric convnet with nested residual connections for segmentation of anterior cranial base. In: MLMI (2017)
Piau, N.H.: Segmentation of human muscles of mastication from magnetic resonance images. Basic Res. J. Agric. Sci. Rev. 180(2), 1167–1175 (2008)
Ray, N., Mukherjee, S., Nakka, K.K., Acton, S.T., Blanker, S.S.: 3d-to-2d mapping for user interactive segmentation of human leg muscles from mri data. In: Signal and Information Processing, pp. 50–54 (2015)
Sellatunis, T., Pokhojaev, A., Sarig, R., OHiggins, P., May, H.: Human mandibular shape is associated with masticatory muscle force. Sci. Rep. 8(1), 6042 (2018)
Yan, G., Ullrich, S., Grottke, O., Rossaint, R., Kuhlen, T., Deserno, T.M., et al.: Scene-based segmentation of multiple muscles from mri in mitk. Bildverarbeitung fr die Medizin (2011)
Yao, J., Kovacs, W., Hsieh, N., Liu, C.Y., Summers, R.M.: Holistic segmentation of intermuscular adipose tissues on thigh mri. In: MICCAI, pp. 737–745 (2017)
Yu, L., Yang, X., Chen, H., Qin, J., Heng, P.A.: Volumetric convnets with mixed residual connections for automated prostate segmentation from 3d mr images. In: AAAI (2017)
Acknowledgements
This work was supported by NSFC 61272342.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Qin, H., Pei, Y., Guo, Y., Ma, G., Xu, T., Zha, H. (2018). Masseter Segmentation from Computed Tomography Using Feature-Enhanced Nested Residual Neural Network. In: Shi, Y., Suk, HI., Liu, M. (eds) Machine Learning in Medical Imaging. MLMI 2018. Lecture Notes in Computer Science(), vol 11046. Springer, Cham. https://doi.org/10.1007/978-3-030-00919-9_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-00919-9_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00918-2
Online ISBN: 978-3-030-00919-9
eBook Packages: Computer ScienceComputer Science (R0)