Brain tumor segmentation based on U-Net with image driven level set loss

Pham Van Truong; Tran Thi Thao

doi:10.15625/2525-2518/59/5/15772

Author affiliations

Authors

Pham Van Truong Hanoi University of Science and Technology, No.1 Dai Co Viet, Hai Ba Trung, Ha Noi, Viet Nam
Tran Thi Thao Hanoi University of Science and Technology, No.1 Dai Co Viet, Hai Ba Trung, Ha Noi, Viet Nam

DOI:

https://doi.org/10.15625/2525-2518/59/5/15772

Keywords:

Brain Tumor Segmentation, U-net, Mumford-Shah loss, Level set method, Activate Contour Model

Abstract

This paper presents an approach for brain tumor segmentation based on deep neural networks. The paper proposes to utilize U-Net as an architecture of the approach to capture the fine and soars information from input images. Especially, to train the network, instead of using commonly used cross-entropy loss, dice loss or both, in this study, we propose to employ a new loss function including Level set loss and Dice loss function. The level set loss is inspired from Mumford-Shah functional for unsupervised task. Meanwhile, the Dice loss function measures the similarity between the predicted mask and desired mask. The proposed approach is then applied to segment brain tumor from MRI images as well as evaluated and compared with other approaches on a dataset of nearly 4000 brain MRI scans. Experiment results show that the proposed approach achieves high performance in terms of Dice coefficient and Intersection over Union (IoU) scores.

Downloads

Download data is not yet available.

References

De Angelis L. M., Brain Tumos, New England Journal of Medicine, 344 (2) (2001) 114-123. DOI: https://doi.org/10.1056/NEJM200101113440207

Siegel R., Miller K., and Jemal A., Cancer statistics, 2020 (US statistics), CA A Cancer J Clin,70 (1) (2020) 7-30. DOI: https://doi.org/10.3322/caac.21590

Khan A., Perez J., Wells C., and Fuentes O., Computer vision evidence supporting craniometric alignment of rat brain atlases to streamline expert-guided, first-order migration of hypothalamic spatial datasets related to behavioral control, Front Syst Neurosci., 12 (2018) 1-29. DOI: https://doi.org/10.3389/fnsys.2018.00007

Bauer S., Wiest R., Nolte L. P., and Reyes M., A survey of MRI-based medical image analysis for brain tumor studies, Phys Med Biol, 58 (13) (2013) 58(13):R97-129. DOI: https://doi.org/10.1088/0031-9155/58/13/R97

Menze B. H., et al., The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) IEEE Trans Med Imaging, 34 (10) (2015) 1993-2024.

Taheria S., Ongb S. H., and Chong. V.F.H., Level-set segmentation of brain tumors using a threshold-based speed function, Image and Vision Computing, 28 (1) (2010) 26-37. DOI: https://doi.org/10.1016/j.imavis.2009.04.005

Sachdeva J., Kumar V., Gupta I., Khandelwal N., and Ahuja C. K., A novel content-based active contour model for brain tumor segmentation, Magnetic Resonance Imaging, 30 (5) (2012) 694-715. DOI: https://doi.org/10.1016/j.mri.2012.01.006

Shyu K. K., Pham V. T., Tran T. T., and Lee P. L., Unsupervised active contours driven by density distance and local fitting energy with applications to medical image segmentation, Mach. Vis. Appl., 23 (6) (2012) 1159-1175. DOI: https://doi.org/10.1007/s00138-011-0373-5

Bauer S., P. Nolte L., and Reyes M. Fully Automatic Segmentation of Brain Tumor Images Using Support Vector Machine Classification in Combination with Hierarchical Conditional Random Field Regularization, Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2010. 354-361. DOI: https://doi.org/10.1007/978-3-642-23626-6_44

Havaei M., Guizard N., Larochelle H., and Jodoin P., Deep Learning Trends for Focal Brain Pathology Segmentation in MRI, Machine Learning for Health Informatics (2016) 125-148. DOI: https://doi.org/10.1007/978-3-319-50478-0_6

Buda M., Saha A., and A. Mazurowski M., Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm, Comp. in Bio. and Med., 109 (2019) 218-225. DOI: https://doi.org/10.1016/j.compbiomed.2019.05.002

J. Long, E. Shelhamer, and T. Darrell, Fully convolutional networks for semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2015) 3431–3440. DOI: https://doi.org/10.1109/CVPR.2015.7298965

Pham V. T., Tran T. T., Wang P. C., and Lo M. T., Tympanic Membrane Segmentation in Otoscopic Images based on Fully Convolutional Network with Active Contour Loss, Signal, Image and Video Processing, DOI: 10.1007/s11760-020-01772-7 (2020) DOI: https://doi.org/10.1007/s11760-020-01772-7

Ninh Q. C., Tran T. T., Tran T. T., Tran T. A. X., and Pham V. T. Skin Lesion Segmentation Based on Modification of SegNet Neural Networks, Proceedings of the 6th NAFOSTED Conference on Information and Computer Science (NICS), 2020 Hanoi. 575-578. DOI: https://doi.org/10.1109/NICS48868.2019.9023862

Ronneberger O., Fischer P., and Brox T. U-net: Convolutional networks for biomedical image segmentation, Proceedings of the Int. Conf. Med. Image Comput. Comput.-Assist. Intervent., 2015. 234-241. DOI: https://doi.org/10.1007/978-3-319-24574-4_28

Chen W., Liu B., Peng. S., Sun J., and Qiao X. S3D-UNet: Separable 3D U-Net for Brain Tumor Segmentation, Proceedings of the International MICCAI Brainlesion Workshop, 2018. 358-368. DOI: https://doi.org/10.1007/978-3-030-11726-9_32

Salehi S. S. M., Erdogmus D., and Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks, Proceedings of the International Workshop on Machine Learning in Medical Imaging, 2017. Springer, 379-387. DOI: https://doi.org/10.1007/978-3-319-67389-9_44

Chen X., Williams B. M., Vallabhaneni S. R., Czanner G., Williams R., and Zheng Y. Learning active contour models for medical image segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, 2019. 11632-11640.

Oktay O., Schlemper J., Folgoc L. L., Lee M., Heinrich M., Misawa K., et al. Attention U-Net: Learning Where to Look for the Pancreas, Proceedings of the 1st Conf. Med. Imaging with Deep Learn., 2018. Available: https://arxiv.org/abs/1804.03999.

Chen X., M. Williams B., R. Vallabhaneni S., Czanner G., Williams R., and Zheng Y. Learning Active Contour Models for Medical Image Segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. 11623-11640. DOI: https://doi.org/10.1109/CVPR.2019.01190

Mumford D. and Shah J., Optimal approximations by piecewise smoothfunctions and associated variational problems, Communications on Pure and Applied Mathematics, 42 (5) (1989) 577–685. DOI: https://doi.org/10.1002/cpa.3160420503

Kim B. and Ye J. C., Mumford–Shah loss functional for image segmentation with deep learning, IEEE Transactions on Image Processing, 29 (2019) 1856-1866. DOI: https://doi.org/10.1109/TIP.2019.2941265

Chan T. F. and Vese L. A. Image segmentation using level sets and the piecewise-constant Mumford-Shah model, Tech. Rep. 0014, Computational Applied Math Group, 2000. Citeseer.

Krizhevsky A., Sutskever I., and Hinton G. ImageNet classification with deep convolutional neural networks, Neural Information Processing Systems (NIPS), 2012.

Kingma D. and Ba J. ADAM: A Method for Stochastic Optimization, Proceedings of the International Conference on Learning Representations (ICLR), 2015.

TCGA-LGG - the cancer imaging archive (TCIA) public access -cancer imaging, [Online]. Available: https://wiki.cancerimagingarchive.net/display/Public/TCGA-LGG ( acess date: August, 29, 2020),

"Brain-segmentation-pytorch Kaggle," [Online], Available: www.kaggle.com/mateuszbuda/brain-segmentation-pytorch/data (access date: August, 29, 2020).

Lynch M., Ghita O., and Whelan P. F., Segmentation of the left ventricle of the heart in 3-D+t MRI data using an optimized nonrigid temporal model, IEEE Trans. Med. Imaging, 27 (2) (2008) 195-203. DOI: https://doi.org/10.1109/TMI.2007.904681