Developing a loss function with TransUnet for brain tumor segmentation from MRI images
373 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.78.2022.28-38Keywords:
Deep neural networks; TransUnet; MRI Brain tumor segmentation; Tversky loss.Abstract
Segmentation of brain tumor in magnetic resonance images plays an important role in diagnosis and treatment planning for patients. However, brain tumor segmentation is a nontrivial task of the variations and differences in tumor sizes, topology, shapes, and the presence of intensity inhomogeneity. In this study, we proposed a new approach for brain tumor segmentation based on advances in deep neural networks. In particular, we propose using the TransUnet, a newly developed architecture based on Transformers and U-Net. In addition, we propose a new loss function to handle the size and shape variations of tumors. The approach is validated on the Brain LGG Segmentation. Experiments show performances of the proposed approach in comparison with other states of the arts.
References
[1]. L. M. De Angelis, "Brain Tumos," New England Journal of Medicine, vol. 344, pp. 114-123, 2001.
[2]. B. H. Menze, et al., "The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) " IEEE Trans Med Imaging, vol. 34, pp. 1993-2024, 2015.
[3]. J. Sachdeva, V. Kumar, I. Gupta, N. Khandelwal, and C. K. Ahuja, "A novel content-based active contour model for brain tumor segmentation," Magnetic Resonance Imaging, vol. 30, pp. 694-715, 2012.
[4]. K. K. Shyu, V. T. Pham, T. T. Tran, and P. L. Lee, "Unsupervised active contours driven by density distance and local fitting energy with applications to medical image segmentation," Mach. Vis. Appl., vol. 23, pp. 1159-1175, 2012.
[5]. M. Havaei, N. Guizard, H. Larochelle, and P. Jodoin, "Deep Learning Trends for Focal Brain Pathology Segmentation in MRI," Machine Learning for Health Informatics pp. 125-148, 2016.
[6]. M. Buda, A. Saha, and M. A. Mazurowski, "Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm," Comp. in Bio. and Med., vol. 109, pp. 218-225, 2019.
[7]. J. Zhang, J. Zeng, P. Qin, and L. Zhao, "Brain tumor segmentation of multi-modality MR images via triple intersecting U-Nets," Neurocomputing, vol. 421, pp. 195-209, 2021.
[8]. Z. Liu, L. Chen, L. Tong, F. Zhou, Z. Jiang, and Q. Zhang, et al., "Deep learning based brain tumor segmentation: A survey," arXiv:2007.09479, 2020, [online] p. Available: http://arxiv.org/abs/2007.09479, 2020.
[9]. 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), pp. 3431–3440, 2015.
[10]. O. Ronneberger, P. Fischer, and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," in Proceedings of the Int. Conf. Med. Image Comput. Comput.-Assist. Intervent., 2015, pp. 234-241.
[11]. J. Chen, Y. Lu, Q. Yu, X. Luo, E. Adeli, Y. Wang, et al., "TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation," arXiv:2102.04306, 2021.
[12]. W. Chen, B. Liu, Peng. S., J. Sun, and X. Qiao, "S3D-UNet: Separable 3D U-Net for Brain Tumor Segmentation," in Proceedings of the International MICCAI Brainlesion Workshop, 2018, pp. 358-368.
[13]. R. Mehta and J. Sivaswamy, "M-net: A convolutional neural network for deep brain structure segmentation," in 2017 IEEE 14th International Symposium on Biomedical Imaging, 2017, pp. 18-21.
[14]. S. A. Taghanaki, Y. Zheng, S. K. Zhou, B. Georgescu, P. Sharma, D. Xu, et al., "Combo loss: Handling input and output imbalance in multi-organ segmentation," Computerized Medical Imaging and Graphics, vol. 75, pp. 24-33, 2019.
[15]. S. S. M. Salehi, D. Erdogmus, and A. Gholipour, "Tversky loss function for image segmentation using 3D fully convolutional deep networks," in Proceedings of the International Workshop on Machine Learning in Medical Imaging, 2017, pp. 379-387.
[16]. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., "Attention is all you need," in Advances in neural information processing systems, 2017, pp. 5998–6008.
[17]. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, et al., "An image is worth 16x16 words: Transformers for image recognition at scale," arXiv:2010.11929, 2020.
[18]. A. Tversky, "Features of similarity," Psychol. Rev., vol. 84, p. 327, 1977.
