In the comparative analysis, Attention UNet achieved the best predictive performance with a 0.886 dice score, 0.795 IoU score, 0.881 sensitivity, 0.993 specificity, 0.891 precision, and 0.986 accuracy.
📌 3 Key Takeaways
🎯
Objective & Hypothesis:The prevalence of brain tumor is quite high.
📊
Key Findings & Data:For this purpose, state-of-art architectures, such as UNet, Attention UNet, Residual UNet, Attention Residual UNet, Residual UNet++, Inception UNet, LinkNet, and SegNet were used for segmentation. 592 magnetic resonance (MR) images were utilized in the training and testing of segmentation architectures.
💡
Conclusion & Impact:In the comparative analysis, Attention UNet achieved the best predictive performance with a 0.886 dice score, 0.795 IoU score, 0.881 sensitivity, 0.993 specificity, 0.891 precision, and 0.986 accuracy.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Brain · Tumor · Segmentation
Abstract
The prevalence of brain tumor is quite high. Brain tumor causes critical diseases. Also, brain tumor causes a variety of symptoms in most people. This study aims to segmentation of the tumor in the brain. For this purpose, state-of-art architectures, such as UNet, Attention UNet, Residual UNet, Attention Residual UNet, Residual UNet++, Inception UNet, LinkNet, and SegNet were used for segmentation. 592 magnetic resonance (MR) images were utilized in the training and testing of segmentation architectures. In the comparative analysis, Attention UNet achieved the best predictive performance with a 0.886 dice score, 0.795 IoU score, 0.881 sensitivity, 0.993 specificity, 0.891 precision, and 0.986 accuracy.
E. Dandil, M. Çakiroǧlu, Z. Ekşi, Computer-Aided Diagnosis of Malign and Benign Brain Tumors on MR Images, in: Adv. Intell. Syst. Comput., Springer Verlag, 2015: pp. 157–166. doi:10.1007/978-3-319-09879-1_16/COVER. R. Tufel, The National Brain Tumor Foundation: Giving Help, Giving Hope, Neoplasia. 3 (2001) 264–265. doi:10.1038/sj.neo.7900159. O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in: Lect. Notes Comput. Sci. (Including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), Springer Verlag, 2015: pp. 234–241. doi:10.1007/978-3-319-24574-4_28/COVER. O. Oktay, J. Schlemper, L. Le Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N.Y. Hammerla, B. Kainz, B. Glocker, D. Rueckert, Attention U-Net: Learning Where to Look for the Pancreas, (2018). doi:10.48550/arxiv.1804.03999. Z. Zhang, Q. Liu, Y. Wang, Road Extraction by Deep Residual U-Net, IEEE Geosci. Remote Sens. Lett. 15 (2018) 749–753. doi:10.1109/LGRS.2018.2802944. X. Chen, L. Yao, Y. Zhang, Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images, (2020). doi:10.48550/arxiv.2004.05645. D. Jha, P.H. Smedsrud, M.A. Riegler, D. Johansen, T. De Lange, P. Halvorsen, H.D. Johansen, ResUNet++: An Advanced Architecture for Medical Image Segmentation, in: Proc. - 2019
IEEE Int. Symp. Multimedia, ISM 2019, Institute of Electrical and Electronics Engineers Inc., 2019: pp. 225–230. doi:10.1109/ISM46123.2019.00049. I. Delibasoglu, M. Cetin, Improved U-Nets with inception blocks for building detection, J. Appl. Remote Sens. 14 (2020) 044512. doi:10.1117/1.jrs.14.044512. A. Chaurasia, E. Culurciello, LinkNet: Exploiting encoder representations for efficient semantic segmentation, in: 2017 IEEE Vis. Commun. Image Process. VCIP 2017, Institute of Electrical and Electronics Engineers Inc., 2018: pp. 1–4. doi:10.1109/VCIP.2017.8305148. V. Badrinarayanan, A. Kendall, R. Cipolla, SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, IEEE Trans. Pattern Anal. Mach. Intell. 39 (2017) 2481–2495. doi:10.1109/TPAMI.2016.2644615. A. Derin, A.F. Bayram, C. Gurkan, A. Budak, H. Karatas, Automatic Skull Stripping and Brain Segmentation with U-Net in MRI Database, Eur. J. Sci. Technol. 40 (2022) 75–81. doi:10.31590/ejosat.1173065. A.F. Bayram, A. Derin, C. Gurkan, A. Budak, H. Karatas, Analysis of the Effects of Segmentation Networks and Loss Functions in Ischemic Stroke Lesion Segmentatio