Abstract
Beyin tümörleri kafatası içinde anormal hücre ve kitle büyümesinin genel adıdır. Beyin tümörü tanısı konulabilmesi için en yaygın tetkik beyin dokusu ve dokudaki yabancı kitleleri gösteren MR (manyetik rezonans) görüntülemesinin yapılmasıdır. Tanı konduktan sonra hızlıca tedavi süreci planlamalıdır. MR görüntüleri çekildikten sonra uzman radyologlar tarafından görüntülerin incelenerek raporlanması zaman alabilmektedir. Son yıllarda hızla gelişen derin öğrenme teknolojileri ile tıp alanında bulunan yenilikler sayesinde hastalıkların erken ve doğru teşhis edilmesi için çeşitli çalışmalar yapılmaktadır. İnsan kaynaklı hataların en aza indirilmesi bu çalışmalar içerisinde önemli bir yere sahiptir. Bu çalışmada MRI görüntülerinin işaretlenerek uzmanlara yardımcı olması için yapay zekâ tekniklerinden yararlanılarak yeni bir evrişimli sinir ağı modeli eğitilmiştir. Eğitim aşamasında U-Net modelinden yararlanılarak, BRAST veri kümesinin %80’i kullanılmıştır. Veri kümesi içerisindeki örneklerin %20’si modelin performansının değerlendirilmesi için kullanılmıştır. Eğitim ve test işlemleri sonucunda elde edilen bulgular incelendiğinde eğitilen modelin tüm tümör, tümör çekirdeği ve genişleyen tümör bölgelerini sırayla 0.908, 0.807 ve 0.877 Benzerlik oranı (BO, Dice Coefficent Score) ile başarılı bir şekilde işaretleme yapabilen bir model eğitildiği görülmektedir.
Keywords
Supporting Institution
Burdur Mehmet Akif Ersoy Üniversitesi Bilimsel Araştırma Projeleri Birimi
Project Number
0786-YL-21
References
- [1] A. Işın, C. Direkoğlu, and M. Şah, “Review of MRI-based brain tumor image segmentation using deep learning methods,” Procedia Comput. Sci., vol. 102, pp. 317–324, 2016.
- [2] E. Tüzün, F. Hanağası, P. A. Sabancı, G. Akman Demir, and J. Yazıcı, “Nöro-Onkoloji.” [Online]. Available: http://www.itfnoroloji.org/onkoloji/onkoloji.htm
- [3] N. Siddique, S. Paheding, C. P. Elkin, and V. Devabhaktuni, “U-net and its variants for medical image segmentation: A review of theory and applications,” IEEE Access, 2021.
- [4] V. Sundaresan, L. Griffanti, and M. Jenkinson, “Brain tumour segmentation using a triplanar ensemble of U-Nets on MR images,” in International MICCAI Brainlesion Workshop, 2020, pp. 340–353.
- [5] J. Zhang, X. Lv, H. Zhang, and B. Liu, “AResU-Net: Attention residual U-Net for brain tumor segmentation,” Symmetry, vol. 12, no. 5, p. 721, 2020.
- [6] Z. Jiang, C. Ding, M. Liu, and D. Tao, “Two-stage cascaded U-Net: 1st place solution to BraTS challenge 2019 segmentation task,” in International MICCAI brainlesion workshop, 2019, pp. 231–241.
- [7] W. Chen, B. Liu, S. Peng, J. Sun, and X. Qiao, “S3D-UNet: Separable 3D U-Net for Brain Tumor Segmentation,” in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Cham, 2019, pp. 358–368. doi: 10.1007/978-3-030-11726-9_32.
- [8] X. Cheng, Z. Jiang, Q. Sun, and J. Zhang, “Memory-efficient cascade 3D U-Net for brain tumor segmentation,” in International Miccai Brainlesion Workshop, 2019, pp. 242–253.
- [9] M. U. Rehman, S. Cho, J. H. Kim, and K. T. Chong, “Bu-net: Brain tumor segmentation using modified u-net architecture,” Electronics, vol. 9, no. 12, p. 2203, 2020.
- [10] A. G. Eker and N. Duru, “Medikal Görüntü İşlemede Derin Öğrenme Uygulamaları,” Acta Infologica, vol. 5, no. 2, Art. no. 2, Dec. 2021, doi: 10.26650/acin.927561.
- [11] B. H. Menze et al., “The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS),” IEEE Trans. Med. Imaging, vol. 34, no. 10, pp. 1993–2024, Oct. 2015, doi: 10.1109/TMI.2014.2377694.
- [12] S. Bakas et al., “Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features,” Sci. Data, vol. 4, no. 1, p. 170117, Dec. 2017, doi: 10.1038/sdata.2017.117.
- [13] S. Bakas et al., “Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge,” ArXiv Prepr. ArXiv181102629, 2018.
- [14] C. Zhang et al., “ErbB2/HER2-Specific NK Cells for Targeted Therapy of Glioblastoma,” JNCI J. Natl. Cancer Inst., vol. 108, no. 5, p. djv375, May 2016, doi: 10.1093/jnci/djv375.
- [15] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” ArXiv150504597 Cs, May 2015, Accessed: May 01, 2021. [Online]. Available: http://arxiv.org/abs/1505.04597
- [16] P. Ahmad, H. Jin, S. Qamar, R. Zheng, and A. Saeed, “RD2A: densely connected residual networks using ASPP for brain tumor segmentation,” Multimed. Tools Appl., vol. 80, no. 18, pp. 27069–27094, Jul. 2021, doi: 10.1007/s11042-021-10915-y.
- [17] N. M. AboElenein, S. Piao, A. Noor, and P. N. Ahmed, “MIRAU-Net: An improved neural network based on U-Net for gliomas segmentation,” Signal Process. Image Commun., vol. 101, p. 116553, 2022.
- [18] N. Sheng et al., “Second-order ResU-Net for automatic MRI brain tumor segmentation,” Math. Biosci. Eng., vol. 18, no. 5, pp. 4943–4960, 2021, doi: 10.3934/mbe.2021251.
Abstract
Brain tumors are the general name for abnormal cell and mass growth in the skull. In order to diagnose a brain tumor, the most common examination is an MRI (magnetic resonance) image that shows foreign masses in the brain tissue and tissue. After the diagnosis is made, one should quickly plan a course of treatment. After the MRI images are taken, it may take time for the images to be examined and reported by expert radiologists. In recent years, thanks to the rapidly developing deep learning technologies and innovations in the field of medicine, various studies are being conducted to diagnose diseases early and accurately. Minimizing human-caused errors has an important place in these studies. In this study, a new convolutional neural network model has been trained by using artificial intelligence techniques to help experts by marking MRI images. At the training stage, 80% of the BRAST dataset was used by using the U-Net model. 20% of the samples in the dataset were used to evaluate the performance of the model. When the findings obtained as a result of the training and testing procedures are examined, it is seen that the trained model has been trained as a model that can successfully mark the entire tumor, tumor nucleus and expanding tumor sites with a similarity ratio of 0.908, 0.807 and 0.877 (BO, Dice Coefficient Score), respectively.
Project Number
0786-YL-21
References
- [1] A. Işın, C. Direkoğlu, and M. Şah, “Review of MRI-based brain tumor image segmentation using deep learning methods,” Procedia Comput. Sci., vol. 102, pp. 317–324, 2016.
- [2] E. Tüzün, F. Hanağası, P. A. Sabancı, G. Akman Demir, and J. Yazıcı, “Nöro-Onkoloji.” [Online]. Available: http://www.itfnoroloji.org/onkoloji/onkoloji.htm
- [3] N. Siddique, S. Paheding, C. P. Elkin, and V. Devabhaktuni, “U-net and its variants for medical image segmentation: A review of theory and applications,” IEEE Access, 2021.
- [4] V. Sundaresan, L. Griffanti, and M. Jenkinson, “Brain tumour segmentation using a triplanar ensemble of U-Nets on MR images,” in International MICCAI Brainlesion Workshop, 2020, pp. 340–353.
- [5] J. Zhang, X. Lv, H. Zhang, and B. Liu, “AResU-Net: Attention residual U-Net for brain tumor segmentation,” Symmetry, vol. 12, no. 5, p. 721, 2020.
- [6] Z. Jiang, C. Ding, M. Liu, and D. Tao, “Two-stage cascaded U-Net: 1st place solution to BraTS challenge 2019 segmentation task,” in International MICCAI brainlesion workshop, 2019, pp. 231–241.
- [7] W. Chen, B. Liu, S. Peng, J. Sun, and X. Qiao, “S3D-UNet: Separable 3D U-Net for Brain Tumor Segmentation,” in Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, Cham, 2019, pp. 358–368. doi: 10.1007/978-3-030-11726-9_32.
- [8] X. Cheng, Z. Jiang, Q. Sun, and J. Zhang, “Memory-efficient cascade 3D U-Net for brain tumor segmentation,” in International Miccai Brainlesion Workshop, 2019, pp. 242–253.
- [9] M. U. Rehman, S. Cho, J. H. Kim, and K. T. Chong, “Bu-net: Brain tumor segmentation using modified u-net architecture,” Electronics, vol. 9, no. 12, p. 2203, 2020.
- [10] A. G. Eker and N. Duru, “Medikal Görüntü İşlemede Derin Öğrenme Uygulamaları,” Acta Infologica, vol. 5, no. 2, Art. no. 2, Dec. 2021, doi: 10.26650/acin.927561.
- [11] B. H. Menze et al., “The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS),” IEEE Trans. Med. Imaging, vol. 34, no. 10, pp. 1993–2024, Oct. 2015, doi: 10.1109/TMI.2014.2377694.
- [12] S. Bakas et al., “Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features,” Sci. Data, vol. 4, no. 1, p. 170117, Dec. 2017, doi: 10.1038/sdata.2017.117.
- [13] S. Bakas et al., “Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge,” ArXiv Prepr. ArXiv181102629, 2018.
- [14] C. Zhang et al., “ErbB2/HER2-Specific NK Cells for Targeted Therapy of Glioblastoma,” JNCI J. Natl. Cancer Inst., vol. 108, no. 5, p. djv375, May 2016, doi: 10.1093/jnci/djv375.
- [15] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” ArXiv150504597 Cs, May 2015, Accessed: May 01, 2021. [Online]. Available: http://arxiv.org/abs/1505.04597
- [16] P. Ahmad, H. Jin, S. Qamar, R. Zheng, and A. Saeed, “RD2A: densely connected residual networks using ASPP for brain tumor segmentation,” Multimed. Tools Appl., vol. 80, no. 18, pp. 27069–27094, Jul. 2021, doi: 10.1007/s11042-021-10915-y.
- [17] N. M. AboElenein, S. Piao, A. Noor, and P. N. Ahmed, “MIRAU-Net: An improved neural network based on U-Net for gliomas segmentation,” Signal Process. Image Commun., vol. 101, p. 116553, 2022.
- [18] N. Sheng et al., “Second-order ResU-Net for automatic MRI brain tumor segmentation,” Math. Biosci. Eng., vol. 18, no. 5, pp. 4943–4960, 2021, doi: 10.3934/mbe.2021251.
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Makaleler |
| Authors | |
| Project Number | 0786-YL-21 |
| Publication Date | December 31, 2022 |
| Submission Date | July 6, 2022 |
| Acceptance Date | November 7, 2022 |
| Published in Issue | Year 2022 Volume: 9 Issue: 4 |
