Abstract
Multiple sclerosis lesions segmentation is an important step in the diagnosis and tracking in the evolution of the disease. Convolutional Neural Networks (CNN) have been obtaining successful results in the task of lesion segmentation in recent years, but still present problem segmenting boundaries of the lesions. In this work we focus the learning process on hard voxels close to the boundaries of the lesions by means of a stratified sampling and the use of focal loss function that dynamically increase the penalization on this kind of voxels. This approach was applied on the 2015 Longitudinal MS Lesion Segmentation Challenge dataset (ISBI2015 (https://smart-stats-tools.org/lesion-challenge)), obtaining better results than approaches using binary cross entropy loss and focal loss functions with uniform sampling.
Supported by Fondecyt Grant 1170123.
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
Similar content being viewed by others
References
Birenbaum, A., Greenspan, H.: Multi-view longitudinal CNN for multiple sclerosis lesion segmentation. Eng. Appl. Artif. Intell. 65, 111–118 (2017)
Carass, A., et al.: Longitudinal multiple sclerosis lesion segmentation: resource and challenge. NeuroImage 148, 77–102 (2017)
Chollet, F., et al.: Keras (2015). https://keras.io
Danelakis, A., Theoharis, T., Verganelakis, D.A.: Survey of automated multiple sclerosis lesion segmentation techniques on magnetic resonance imaging. Comput. Med. Imaging Graph. 70, 83–100 (2018). https://doi.org/10.1016/j.compmedimag.2018.10.002. http://www.sciencedirect.com/science/article/pii/S0895611118303227
Giorgio, A., Stefano, N.D.: Effective utilization of MRI in the diagnosis and management of multiple sclerosis. Neurol. Clin. 36(1), 27–34 (2018). https://doi.org/10.1016/j.ncl.2017.08.013. http://www.sciencedirect.com/science/article/pii/S0733861917301007, multiple Sclerosis
Goldenberg, M.M.: Multiple sclerosis review. P & T Peer-Rev. J. Formul. Manag. 37(3), 175–184 (2012). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3351877/, https://www.ncbi.nlm.nih.gov/pubmed/22605909, multiple Sclerosis
Jenkinson, M., Bannister, P., Brady, M., Smith, S.: Improved optimization for the robust and accurate linear registration and motion correction of brain images. NeuroImage 17(2), 825–841 (2002). https://doi.org/10.1006/nimg.2002.1132. http://www.sciencedirect.com/science/article/pii/S1053811902911328
Kazancli, E., Prchkovska, V., Rodrigues, P., Villoslada, P., Igual, L.: Multiple sclerosis lesion segmentation using improved convolutional neural networks. In: Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4 VISAPP: VISAPP, pp. 260–269. INSTICC, SciTePress (2018). https://doi.org/10.5220/0006540902600269
Lin, T., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 318–327 (2020). https://doi.org/10.1109/TPAMI.2018.2858826
Roy, S., Butman, J.A., Reich, D.S., Calabresi, P.A., Pham, D.L.: Multiple sclerosis lesion segmentation from brain MRI via fully convolutional neural networks (2018)
Valverde, S., et al.: Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach. NeuroImage 155, 159–168 (2017)
Valverde, S., et al.: One-shot domain adaptation in multiple sclerosis lesion segmentation using convolutional neural networks. NeuroImage Clin. 21, 101638 (2019). https://doi.org/10.1016/j.nicl.2018.101638. http://www.sciencedirect.com/science/article/pii/S2213158218303863
Warfield, S.K., Zou, K.H., Wells, W.M.: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imaging 23(7), 903–921 (2004). https://doi.org/10.1109/TMI.2004.828354
Zhou, T., Ruan, S., Canu, S.: A review: deep learning for medical image segmentation using multi-modality fusion. Array 3–4, 100004 (2019). https://doi.org/10.1016/j.array.2019.100004. http://www.sciencedirect.com/science/article/pii/S2590005619300049
Acknowledgments
This work was supported in part by the Fondecyt Grant 1170123 and ANID PIA/apoyo Project AFB 1800082. Alejandro Veloz is supported by the Fondecyt Grant 1201822. Héctor Allende-Cid is supported by Fondecyt Initiation into Research 11150248.
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
Ulloa, G., Veloz, A., Allende-Cid, H., Allende, H. (2020). Improving Multiple Sclerosis Lesion Boundaries Segmentation by Convolutional Neural Networks with Focal Learning. In: Campilho, A., Karray, F., Wang, Z. (eds) Image Analysis and Recognition. ICIAR 2020. Lecture Notes in Computer Science(), vol 12132. Springer, Cham. https://doi.org/10.1007/978-3-030-50516-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-50516-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50515-8
Online ISBN: 978-3-030-50516-5
eBook Packages: Computer ScienceComputer Science (R0)