Accurate Segmentation of Brain Tumor Image using U-Net Based Self-Attention Mechanism
Keywords:
U-Net architecture, attention mechanisms, BraTS 2020 dataset, brain tumor MRI imagesAbstract
In the sphere of neurooncology, precise diagnosis and intervention for Glioma brain tumors are of utmost importance. While the past three years have witnessed over 50 pivotal studies targeting MRI image classification of brain tumors, there remains an imperative need to develop advanced segmentation techniques. These techniques must effectively address challenges such as imaging artifacts, intricate tumor boundary demarcation, tumor heterogeneity, ambiguous classifications, and class disparities. In this study, we unveil an innovative deep learning strategy, synergizing the U-Net architecture with self-attention mechanisms. Drawing upon U-Net's proficiency in extracting both localized and holistic features from 3D cerebral scans, our integrated attention mechanisms spotlight key tumor regions. Evaluations on the BraTS 2020 dataset revealed a remarkable accuracy rate of 99.34% and a Dice coefficient of 95%, underscoring our model's exceptional segmentation capabilities. Additionally, the model demonstrated unparalleled precision (99.36%), sensitivity (99.19%), and specificity (99.78%), reiterating its robustness in discerning tumorous regions from healthy brain tissue. This study accentuates the revolutionizing capacity of melding U-Net with attention mechanisms for MRI-based brain tumor segmentation. The breakthroughs delineated herald an era of optimized clinical neurooncology procedures, fortifying the diagnostic and therapeutic landscape to the immense benefit of patients and healthcare professionals.
Downloads
References
Ali TM, Nawaz A, Ur Rehman A, Ahmad RZ, Javed AR, Gadekallu TR, Chen C-L and Wu C-M (2022) A Sequential Machine Learning-cum-Attention Mechanism for Effective Segmentation of Brain Tumor. Front. Oncol. 12:873268. doi: 10.3389/fonc.2022.873268.
Abiwinanda , N, Muhammad Tafwida HS. H, Astri H, and Tati RM. "BrainvTumor Classification Using Convolutional Neural Network." In World Congress on Medical Physics and Biomedical Engineering 2018. Singapore: Springer (2019). p. 183-9.
Forst DA, Nahed BV, Loeffler JS, Batchelor TT. Low-Grade Gliomas. Oncol (2014) 19:403–13. doi: 10.1634/theoncologist.2013-0345
Zhaohong Jia, Hongxin Zhu, Junan Zhu, Ping Ma, Two-Branch network for brain tumor segmentation using attention mechanism and super-resolution reconstruction, Computers in Biology and Medicine, Volume 157, 2023, 106751, ISSN 0010-4825., https://doi.org/10.1016/j.compbiomed.2023.106751
Qi Zhang, Yinglu Liang, Yi Zhang, Zihao Tao, Rui Li, Hai Bi, A comparative study of attention mechanism based deep learning methods for bladder tumor segmentation, International Journal of Medical Informatics, Volume 171, 2023, 104984, ISSN 1386-5056, https://doi.org/10.1016/j.ijmedinf.2023.104984.
Shaik, N.S., Cherukuri, T.K. Multi-level attention network: application to brain tumor classification. SIViP 16, 817–824 (2022). https://doi.org/10.1007/s11760-021-02022-0
T. Ruba, R. Tamilselvi, M. Parisa Beham, Brain tumor segmentation using JGate-AttResUNet – A novel deep learning approach, Biomedical Signal Processing and Control, Volume 84, 2023, 104926, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2023.104926.
Shiqiang Ma1, Jijun Tang, Fei Guo, Multi-Task Deep Supervision On Attention R2U-Net For Brain Tumor Segmentation, Volume 11 - 2021 | https://doi.org/10.3389/fonc.2021.704850G. O. Young, “Synthetic structure of industrial plastics (Book style with paper title and editor),” in Plastics, 2nd ed. vol. 3, J. Peters, Ed. New York: McGraw-Hill, 1964, pp. 15–64.
Guan, X., Yang, G., Ye, J. et al. 3D AGSE-VNet: an automatic brain tumor MRI data segmentation framework. BMC Med Imaging 22, 6 (2022). https://doi.org/10.1186/s12880-021-00728-8
Yuan Cao, Weifeng Zhou, Min Zang, Dianlong An, Yan Feng, Bin Yu, MBANet: A 3D convolutional neural network with multi-branch attention for brain tumor segmentation from MRI images, Biomedical Signal Processing and Control, Volume 80, Part 1, 2023, 104296, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2022.104296.
O. Alirr, R. Alshatti, S. Altemeemi, S. Alsaad and A. Alshatti, "Automatic Brain Tumor Segmentation from MRI Scans using U-net Deep Learning," 2023 5th International Conference on Bio-engineering for Smart Technologies (BioSMART), Paris, France, 2023, pp. 1-5, doi: 10.1109/BioSMART58455.2023.10162093.
Zhiqin Zhu, Xianyu He, Guanqiu Qi, Yuanyuan Li, Baisen Cong, Yu Liu, Brain tumor segmentation based on the fusion of deep semantics and edge information in multimodal MRI, Information Fusion, Volume 91, 2023, Pages 376-387, ISSN 1566-2535, https://doi.org/10.1016/j.inffus.2022.10.022.
Su, Run, et al. "MSU-Net: Multi-scale U-Net for 2D medical image segmentation." Frontiers in Genetics 12 (2021): 639930.
Jun, Wen, and Zheng Liyuan. "Brain Tumor Classification Based on Attention Guided Deep Learning Model." International Journal of Computational Intelligence Systems 15.1 (2022)
Hengxin Liu, Guoqiang Huo, Qiang Li, Xin Guan, Ming-Lang Tseng, Multiscale lightweight 3D segmentation algorithm with attention mechanism: Brain tumor image segmentation, Expert Systems with Applications, Volume 214, 2023, 119166, ISSN 0957-4174, ps://doi.org/10.1016/j.eswa.2022.119166.
Ranjbarzadeh, R., Bagherian Kasgari, A., Jafarzadeh Ghoushchi, S. et al. Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images. Sci Rep 11, 10930 (2021). https://doi.org/10.1038/s41598-021-90428-8
Liu, Zhihua, et al. "Deep learning based brain tumor segmentation: a survey." Complex & intelligent systems 9.1 (2023): 1001-1026.
Montaha, Sidratul, et al. "Brain Tumor Segmentation from 3D MRI Scans Using U-Net." SN Computer Science 4.4 (2023): 386.
Zhang, Fuchun, et al. "A Multi-Scale Brain Tumor Segmentation Method based on U-Net Network." Journal of Physics: Conference Series. Vol. 2289. No. 1. IOP Publishing, 2022.
Walsh, Jason, et al. "Using U-Net network for efficient brain tumor segmentation in MRI images." Healthcare Analytics 2 (2022): 100098.
Zhang, Jianxin, et al. "AResU-Net: Attention residual U-Net for brain tumor segmentation." Symmetry 12.5 (2020): 721.
Zhang, Wenxuan, et al. "Attention-Guided U-Net for Brain Tumor Segmentation." Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer International Publishing, 2020, pp. 148-157.
Liu, Zexiang, et al. "Multi-Modal Attention U-Net for Brain Tumor Segmentation." Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer International Publishing, 2020, pp. 562-571.
Zhang, Jinyu, et al. "Attention U-Net with Residual Learning for Brain Tumor Segmentation." IEEE Access, vol. 8, pp. 58533-58545, 2020.
Singh, Sandeep, Benoy Kumar Singh, and Anuj Kumar. "Magnetic resonance imaging image-based segmentation of brain tumor using the modified transfer learning method." Journal of Medical Physics 47.4 (2022): 315.
Zhang, Wenxuan, et al. "Brain Tumor Segmentation with Attention-Guided Multimodal Deep Learning." IEEE Transactions on Medical Imaging, vol. 41, no. 1, pp. 142-152, 2022.
Wang, Xinchao, et al. "Brain Tumor Segmentation with a Multi-Scale Cascaded Attention Network." IEEE Transactions on Medical Imaging, vol. 42, no. 9, pp. 1900-1910, 2023.
Zhang, Tianchi, et al. "Brain Tumor Segmentation with a Transformer-Based Attention Network." Frontiers in Neuroscience, vol. 17, article 776960, 2023.
Nodirov, Jakhongir, Akmalbek Bobomirzaevich Abdusalomov, and Taeg Keun Whangbo. "Attention 3D U-Net with Multiple Skip Connections for Segmentation of Brain Tumor Images." Sensors 22.17 (2022): 6501.
Aboussaleh, Ilyasse, et al. "Efficient U-Net Architecture with Multiple Encoders and Attention Mechanism Decoders for Brain Tumor Segmentation." Diagnostics 13.5 (2023): 872.
Shaik, Nagur Shareef, and Teja Krishna Cherukuri. "Multi-level attention network: application to brain tumor classification." Signal, Image and Video Processing 16.3 (2022): 817-824.
Montaha, Sidratul, et al. "Brain Tumor Segmentation from 3D MRI Scans Using U-Net." SN Computer Science 4.4 (2023): 386.
Wang, Wenxuan, et al. "Transbts: Multimodal brain tumor segmentation using transformer." Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24. Springer International Publishing, 2021.
Li, Zhaopei, et al. "Automatic brain tumor segmentation using multi-scale features and attention mechanism." International MICCAI Brainlesion Workshop. Cham: Springer International Publishing, 2021.
Gan, Xiuling, et al. "GAU-Net: U-Net based on global attention mechanism for brain tumor segmentation." Journal of Physics: Conference Series. Vol. 1861. No. 1. IOP Publishing, 2021.]
Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, 8th International Workshop, BrainLes 2022, Held in Conjunction with MICCAI 2022, Singapore, September 18, 2022
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Chandrakant M. Umarani, Shantappa G. Gollagi, Kalyan Devappa Bamane, Priyanka Gupta, Sonali J. More, Sanjay B. Ankali
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
