Using 3D U-Net for Brain Tumour Segmentation from Magnetic Resonance Images

Abstract

Brain tumours within the skull can lead to serious health issues. The rapid and accurate detection and segmentation of tumour regions allow patients to receive appropriate treatment at an early stage, increasing their chances of recovery and survival. Various medical imaging methods, such as Magnetic Resonance Imaging (MRI), Positron and digital pathology, Emission Tomography (PET), Computed Tomography (CT) are used for the detection of brain tumours. Nowadays, with advancing technology and hardware, concepts like artificial intelligence and deep learning (DL) are becoming increasingly popular. Many artificial intelligence methods are also being utilized in studies on brain tumour segmentation. This paper proposes a 3D U-Net DL model for brain tumour segmentation. The training and testing processes are carried out on the Brain Tumour Segmentation (BraTS) 2020 dataset, which is widely used in the literature. As a result, an Intersection over Union (IoU) score of 0.81, a dice score of 0.87 and a pixel accuracy of 0.99 are achieved. The proposed model has the potential to assist experts in diagnosing the disease and developing appropriate treatment plans, thanks to its ability to segment brain tumours quickly and with high accuracy.

Keywords

• magnetic resonance images
• brain tumour
• deep learning
• semantic segmentation
• 3D U-Net

References

1. R. Bütüner and M. H. Calp, "Predicting of Melanoma Skin Cancer Using Machine Learning Methods," Gazi Journal of Engineering Sciences, vol. 10, no. 1, pp. 141–154, 2024.
2. A. Ergin, R. Özdilek, and N. Dutucu, "The Distribution and Types of Women’s Cancers Seen Between 2012 And 2017: A University Hospital Example," Journal of Women's Health Nursing Jowhen, vol. 5, no. 1, pp. 1–21, 2019.
3. The American Cancer Society medical and editorial content team, About Brain and Spinal Cord Tumours in Adults. American Cancer Society, 2020. Accessed on: May. 10, 2024. [Online]. Available: https://www.cancer.org/content/dam/CRC/PDF/Public/8567.00.pdf
4. T. Şentürk and F. Latifoğlu, "Deep Learning Based Methods for Biomedical Image Segmentation: A Review," Dicle University Journal of the Institute of Natural and Applied Sciences, vol. 12, no. 1, pp. 161–187, 2023.
5. X. Zhou, X. Li, K. Hu, Y. Zhang, Z. Chen and X. Gao, "ERV-Net: An efficient 3D residual neural network for brain tumour segmentation," Expert Systems with Applications, vol. 170, p. 114566, 2021.
6. F. Ye, Y. Zheng, H. Ye, X. Han, Y. Li, J. Wang and J. Pu, "Parallel pathway dense neural network with weighted fusion structure for brain tumour segmentation," Neurocomputing, vol. 425, pp. 1–11, 2021.
7. Z. Zhou, Z. He and Y. Jia, "AFPNet: A 3D fully convolutional neural network with atrous-convolution feature pyramid for brain tumour segmentation via MRI images," Neurocomputing, vol. 402, pp. 235–244, 2020.
8. J. Zhang, J. Zeng, P. Qin and L. Zhao, "Brain tumour segmentation of multi-modality MR images via triple intersecting U-Nets," Neurocomputing, vol. 421, pp. 195–209, 2021.

9. P. Li, W. Wu, L. Liu, F. M. Serry, J. Wang, and H. Han, "Automatic brain tumor segmentation from Multiparametric MRI based on cascaded 3D U-Net and 3D U-Net++," Biomedical Signal Processing and Control, vol. 78, 103979, 2022.
10. T. Henry, A. Carré, M. Lerousseau, T. Estienne, C. Robert, N. Paragios, and E. Deutsch, "Brain tumor segmentation with self-ensembled, deeply-supervised 3D U-net neural networks: a BraTS 2020 challenge solution," In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 6th International Workshop, BrainLes, Held in Conjunction with MICCAI 2020, pp. 327–339, 2020.
11. M. D. Cirillo, D. Abramian, and A. Eklund, "Vox2Vox: 3D-GAN for brain tumour segmentation," In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 6th International Workshop, BrainLes 2020, Held in Conjunction with MICCAI 2020, pp. 274–284, 2020.
12. M. Lin, S. Momin, Y. Lei, H. Wang, W. J. Curran, T. Liu, and X. Yang, "Fully automated segmentation of brain tumor from multiparametric MRI using 3D context deep supervised U‐Net," Medical Physics, vol. 48, no. 8, pp. 4365–4374, 2021.
13. V. V. V. Sasank, and S. Venkateswarlu, "An automatic tumour growth prediction based segmentation using full resolution convolutional network for brain tumour,” Biomedical Signal Processing and Control, vol. 71, 103090, 2022.
14. D. LaBella, et al., "A multi-institutional meningioma MRI dataset for automated multi-sequence image segmentation," Scientific Data, vol. 11, no. 496, pp. 1–8, 2024.
15. Brain Tumour Segmentation 2020 Dataset. Accessed on: May. 2, 2024. [Online]. https://www.kaggle.com/awsaf49/brats20-dataset-training-validation.
16. E. Gökçe, M. F. Demiral, A. H. Isık, and M. Bilen, "Brain Tumour Segmentation with Convolutional Neural Networks," El-Cezerî Journal of Science and Engineering, vol. 9, no. 4, pp. 1518–1528, 2022.
17. P. Khurana, A. Sharma, S. N. Singh and P. K. Singh, "A survey on object recognition and segmentation techniques," in 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom), pp. 3822–3826, 2016.
18. B. Kayhan, "Deep learning based multi organ segmentation in computed tomography images," Master thesis, Konya Technical Univ., Konya, Türkiye, 2022.
19. J. Long, E. Shelhamer, T. Darrell, "Fully convolutional networks for semantic segmentation," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440, 2015.
20. O. Ronneberger, P. Fischer and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," in Medical image computing and computer-assisted intervention–MICCAI 2015, pp. 234–241, 2015.
21. Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox and O. Ronneberger, "3D U-Net: learning dense volumetric segmentation from sparse annotation," in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th International Conference, pp. 424–432, 2016.