Login | Register

A Performance-Consistent and Computation-Efficient CNN System for High-Quality Brain Tumor Segmentation


A Performance-Consistent and Computation-Efficient CNN System for High-Quality Brain Tumor Segmentation

Tong, Juncheng ORCID: https://orcid.org/0000-0002-2873-0465 (2022) A Performance-Consistent and Computation-Efficient CNN System for High-Quality Brain Tumor Segmentation. Masters thesis, Concordia University.

[thumbnail of TONG_MA_S2022.pdf]
Text (application/pdf)
TONG_MA_S2022.pdf - Accepted Version


Brain tumors cause serious health problems and brain tumor detection is important for the diagnosis. The detection is a very challenging task due to the complexity in brain structures and in brain tumor patterns. Manual segmentation requires an expertise of highly trained medical specialists and is very time-consuming. Therefore, it’s imperative to develop fully automated brain tumor segmentation systems, i.e., CNN based systems, to accelerate the diagnosis process. The research on developing such systems has been progressed rapidly in recent years. For the systems to be applicable in practice, a good processing quality and reliability are required. Moreover, for a wide range of applications of such systems, a minimization of computation complexity is desirable, which can also result in a minimization of randomness in computation and, consequently, a better performance consistency.
In this thesis, a new CNN system for brain tumor segmentation is proposed. The CNN in the proposed system is custom-designed with 2 distinguished characters dedicated to optimizing the feature extraction and classification processes. Firstly, there are three paths in its feature extraction block, designed to extract, from the multi-modality input, comprehensive feature information of mono-modality, paired-modality and cross-modality, respectively. Also, it has a particular three-branch classification block to identify the pixels of 4 classes, namely, whole tumor, enhancing tumor, non-enhancing core/necrotic tumor and those in the background. By means of the three branches, a complex multi-class classification problem is decomposed into several simple binary classification problems. Each branch is trained separately so that the parameters are adjusted specifically to suit the detection of one specific kind of tumor areas. The parameters of the convolution layers in the proposed system are determined to suit the specific purposes so that the computation volume for each filtering operations in each layer are just-sufficient, which results in a very simple config of 61,843 parameters in total, while most existing CNN systems require multi-millions.
The performance of the proposed system has been tested extensively with BraTS 2018 and BraTS 2019 data samples. A good mean Dice scores in each experiment has been obtained. The average of the mean Dice scores obtained from ten experiments are very close to each other with very small deviations. In the case of the 10 experiments on BraTS 2018 validation samples, the average Dice scores and their standard deviations are 0.787±0.003, 0.886±0.002, 0.801±0.007, respectively, for enhancing tumor, whole tumor and tumor core. For the validation samples of BraTS 2019 in 10 experiments, the average Dice scores and standard deviations of enhancing tumor, whole tumor and tumor core are 0.751±0.007, 0.885±0.002, 0.776±0.004, respectively. The test results demonstrate that the proposed system is able to perform high-quality segmentation in a consistent manner. Furthermore, it only requires 146G FLOPs to complete a segmentation of the four 3D images (155x240x240x4 voxels) of a single patient case. The extremely low computation complexity of the proposed system will facilitate its implementation/application in various environments.
The high processing quality and low computation complexity of the proposed system make it implementable in various environments. It can be expected that such system will have wide applications in medical image processing.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering
Item Type:Thesis (Masters)
Authors:Tong, Juncheng
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Electrical and Computer Engineering
Date:April 2022
Thesis Supervisor(s):Wang, Chunyan
Keywords:Brain tumor segmentation, multi-path feature extraction block, multi-branch classification block, performance consistency and reliability, separate and parallel training.
ID Code:990485
Deposited On:16 Jun 2022 15:17
Last Modified:16 Jun 2022 15:17


[1] https://www.tfri.ca/about-cancer/cancer-types/cancer-type/brain
[2] https://www.mayfieldclinic.com/pe-anatbrain.htm
[3] https://www.newscientist.com/article/dn9969-introduction-the-human-brain/
[4] https://www.hopkinsmedicine.org/health/conditions-and-diseases/brain-tumor
[5] Menze, B. H. et al. (2014). The multimodal brain tumor image segmentation benchmark (BRATS). IEEE transactions on medical imaging, 34(10), 1993-2024.
[6] Gibbs, P., Buckley, D. L., Blackband, S. J., & Horsman, A. (1996). Tumour volume determination from MR images by morphological segmentation. Physics in Medicine & Biology, 41(11), 2437.
[7] Praveen, G. B., & Agrawal, A. (2015, November). Hybrid approach for brain tumor detection and classification in magnetic resonance images. In 2015 Communication, Control and Intelligent Systems (CCIS) (pp. 162-166). IEEE.
[8] LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
[9] Matsugu, M., Mori, K., Mitari, Y., & Kaneda, Y. (2003). Subject independent facial expression recognition with robust face detection using a convolutional neural network. Neural Networks, 16(5-6), 555-559.
[10] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
[11] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
[12] https://medium.com/unpackai/batch-normalization-25905f889723.
[13] https://en.wikipedia.org/wiki/Bilinear_interpolation.
[14] Ng, D., & Feng, M. (2020). Medical Image Recognition: An Explanation and Hands-On Example of Convolutional Networks. In Leveraging Data Science for Global Health (pp. 263-284). Springer, Cham.
[15] Ronneberger, O., Fischer, P., & Brox, T. (2015, October). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Springer, Cham.
[16] Li, X., Chen, H., Qi, X., Dou, Q., Fu, C. W., & Heng, P. A. (2018). H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE transactions on medical imaging, 37(12), 2663-2674.
[17] Salehi, S. S. M., Erdogmus, D., & Gholipour, A. (2017). Auto-context convolutional neural network (auto-net) for brain extraction in magnetic resonance imaging. IEEE transactions on medical imaging, 36(11), 2319-2330.
[18] Rosas González, S., Birgui Sekou, T., Hidane, M., Zemmoura, I., & Tauber, C. (2021). Asymmetric Ensemble of Asymmetric U-Net Models for Brain Tumor Segmentation With Uncertainty Estimation. Frontiers in Neurology, 1421.
[19] Luo, Z., Jia, Z., Yuan, Z., & Peng, J. (2020). Hdc-net: Hierarchical decoupled convolution network for brain tumor segmentation. IEEE Journal of Biomedical and Health Informatics, 25(3), 737-745.
[20] Maji, D., Sigedar, P., & Singh, M. (2022). Attention Res-UNet with Guided Decoder for semantic segmentation of brain tumors. Biomedical Signal Processing and Control, 71, 103077.
[21] Zhou, T., Ruan, S., Vera, P., & Canu, S. (2021). A Tri-Attention fusion guided multi-modal segmentation network. Pattern Recognition, 108417.
[22] Chen, Y., Cao, Z., Cao, C., Yang, J., & Zhang, J. (2018, June). A modified U-Net for brain Mr image segmentation. In International Conference on Cloud Computing and Security (pp. 233-242). Springer, Cham.
[23] Cahall, D. E., Rasool, G., Bouaynaya, N. C., & Fathallah-Shaykh, H. M. (2019). Inception modules enhance brain tumor segmentation. Frontiers in computational neuroscience, 13, 44.
[24] Akil, M., Saouli, R., & Kachouri, R. (2020). Fully automatic brain tumor segmentation with deep learning-based selective attention using overlapping patches and multi-class weighted cross-entropy. Medical image analysis, 63, 101692.
[25] Yogananda, C. G. B., Shah, B. R., Vejdani-Jahromi, M., Nalawade, S. S., Murugesan, G. K., Yu, F. F., ... & Maldjian, J. A. (2020). A fully automated deep learning network for brain tumor segmentation. Tomography, 6(2), 186-193.
[26] Wang, L., Wang, S., Chen, R., Qu, X., Chen, Y., Huang, S., & Liu, C. (2019). Nested dilation networks for brain tumor segmentation based on magnetic resonance imaging. Frontiers in Neuroscience, 13, 285.
[27] Zhang, J., Jiang, Z., Dong, J., Hou, Y., & Liu, B. (2020). Attention gate resU-Net for automatic MRI brain tumor segmentation. IEEE Access, 8, 58533-58545.
[28] Huang, Z., Zhao, Y., Liu, Y., & Song, G. (2021). GCAUNet: A group cross-channel attention residual UNet for slice based brain tumor segmentation. Biomedical Signal Processing and Control, 70, 102958.
[29] Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2019). Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE transactions on medical imaging, 39(6), 1856-1867.
[30] Zhou, T., Canu, S., Vera, P., & Ruan, S. (2021). Latent correlation representation learning for brain tumor segmentation with missing MRI modalities. IEEE Transactions on Image Processing, 30, 4263-4274.
[31] Wang, B., Yang, J., Peng, H., Ai, J., An, L., Yang, B., ... & Ma, L. (2021). Brain Tumor Segmentation via Multi-Modalities Interactive Feature Learning. Frontiers in Medicine, 8.
[32] Wang, G., Li, W., Ourselin, S., & Vercauteren, T. (2019). Automatic brain tumor segmentation based on cascaded convolutional neural networks with uncertainty estimation. Frontiers in computational neuroscience, 13, 56.
[33] Jiang, Z., Ding, C., Liu, M., & Tao, D. (2019, October). Two-stage cascaded U-Net: 1st place solution to BraTS challenge 2019 segmentation task. In International MICCAI brainlesion workshop (pp. 231-241). Springer, Cham.
[34] Zhou, C., Ding, C., Wang, X., Lu, Z., & Tao, D. (2020). One-pass multi-task networks with cross-task guided attention for brain tumor segmentation. IEEE Transactions on Image Processing, 29, 4516-4529.
[35] Li, X., Luo, G., & Wang, K. (2019, October). Multi-step cascaded networks for brain tumor segmentation. In International MICCAI Brainlesion Workshop (pp. 163-173). Springer, Cham.
[36] https://www.med.upenn.edu/sbia/brats2018/evaluation.html
[37] https://www.med.upenn.edu/cbica/brats2019/evaluation.html\
[38] Salehi, S. S. M., Erdogmus, D., & Gholipour, A. (2017, September). Tversky loss function for image segmentation using 3D fully convolutional deep networks. In International workshop on machine learning in medical imaging (pp. 379-387). Springer, Cham.
[39] Huang, H., Yang, G., Zhang, W., Xu, X., Yang, W., Jiang, W., & Lai, X. (2021). A deep multi-task learning framework for brain tumor segmentation. Frontiers in Oncology, 11.
[40] Liu, Z., Tong, L., Chen, L., Zhou, F., Jiang, Z., Zhang, Q., ... & Zhou, H. (2021). CANet: Context aware network for brain glioma segmentation. IEEE Transactions on Medical Imaging, 40(7), 1763-1777.
[41] Sun, J., Peng, Y., Guo, Y., & Li, D. (2021). Segmentation of the multimodal brain tumor image used the multi-pathway architecture method based on 3D FCN. Neurocomputing, 423, 34-45.
[42] Rehman, M. U., Cho, S., Kim, J., & Chong, K. T. (2021). BrainSeg-net: Brain tumor MR image segmentation via enhanced encoder–decoder network. Diagnostics, 11(2), 169.
[43] Zhang, D., Huang, G., Zhang, Q., Han, J., Han, J., Wang, Y., & Yu, Y. (2020). Exploring task structure for brain tumor segmentation from multi-modality MR images. IEEE Transactions on Image Processing, 29, 9032-9043.
[44] Di Ieva, A., Russo, C., Liu, S., Jian, A., Bai, M. Y., Qian, Y., & Magnussen, J. S. (2021). Application of deep learning for automatic segmentation of brain tumors on magnetic resonance imaging: a heuristic approach in the clinical scenario. Neuroradiology, 63(8), 1253-1262.
[45] Ali, M. J., Raza, B., & Shahid, A. R. (2021). Multi-level Kronecker Convolutional Neural Network (ML-KCNN) for Glioma Segmentation from Multi-modal MRI Volumetric Data. Journal of Digital Imaging, 34(4), 905-921.
[46] Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
[47] He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision (pp. 1026-1034).
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top