SavedAdd your journal

Journals / El-Cezeri / 2022 / Cilt: 9 Sayı: 4 Özel Sayı

Segmentation of Brain Tumor MRI Images with U-Net Architecture

U-Net Mimarisi ile Beyin Tümörü MRI Görüntülerinin Segmentasyonu

Süleyman Uzun(SAKARYA UNIVERSITY OF APPLIED SCIENCES, FACULTY OF TECHNOLOGY, DEPARTMENT OF COMPUTER ENGINEERING, COMPUTER ENGINEERING PR.)0000-0001-8246-6733
Emin Güney(SAKARYA UYGULAMALI BİLİMLER ÜNİVERSİTESİ)0000-0003-0098-9018
Bünyamin Bingöl(SAKARYA UYGULAMALI BİLİMLER ÜNİVERSİTESİ, TEKNOLOJİ FAKÜLTESİ, ELEKTRİK-ELEKTRONİK MÜHENDİSLİĞİ BÖLÜMÜ, ELEKTRİK-ELEKTRONİK MÜHENDİSLİĞİ PR.)0000-0001-7003-8416
Journal
El-Cezeri
Pages
1583–1590
Publication Date
2022-12-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of the survey, a dice score of 91.38% was obtained, which can be accepted as reliable.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:With the development of deep learning methods in recent years, image processing has gained importance in health.
📊
Key Findings & Data:One of the most common studies in this field is the rapid and accurate diagnosis of cancerous brain tumors.
💡
Conclusion & Impact:As a result of the survey, a dice score of 91.38% was obtained, which can be accepted as reliable.
🔬Design:Survey & Empirical Study
📍Scope:Comprehensive Sample
⚙️Variables:Beyin tümörü segmentasyonu · derin sinir ağları · görüntü işleme

Abstract

With the development of deep learning methods in recent years, image processing has gained importance in health. One of the most common studies in this field is the rapid and accurate diagnosis of cancerous brain tumors. Brain tumors are one of the leading causes of death in cancer patients, especially in children and the elderly. Especially in the last ten years, the development of GPU computing technologies and the increase in studies in deep learning also contributed to this field. In this study, a system that detects brain tumor cells by using U-Net architecture with 512x512 filter sizes on MRI images has been implemented. In the study, the BRATS dataset, one of the global datasets frequently used in the literature, was used. As a result of the survey, a dice score of 91.38% was obtained, which can be accepted as reliable.

Özet

Son yıllarda derin öğrenme yöntemlerinin gelişmesiyle birlikte, sağlık alanında görüntü işleme konusu oldukça önem kazanmıştır. Bu alanda yapılan en yaygın çalışmalardan birisi de kanserli beyin tümörlerinin hızlı ve doğru teşhis edilmesine yöneliktir. Beyin tümörleri başta çocuklar ve yaşlılar olmak üzere kanser hastalarının önde gelen ölüm nedenlerinden biridir. Özellikle son on yılda GPU hesaplama teknolojilerinin gelişmesi ve buna bağlı olarak derin öğrenme alanında yapılan çalışmaların artması da bu alana katkı sağlamıştır. Bu çalışmada MRI görüntüleri üzerinde 512x512 filtre boyutlarına sahip U-Net mimarisi kullanılarak beyin tümör hücrelerinin tespit edilmesini sağlayan bir sistem gerçekleştirilmiştir. Çalışmada literatürde sıkça kullanılan global verisetlerinden BRATS veriseti kullanılmıştır. Yapılan çalışma sonucunda güvenilirliği kabul edilebilen %91,38’lik bir dice skoru elde edilmiştir.

🔖

Cite This Article

Uzun, S., Güney, E., Bingöl, B. (2022). Segmentation of Brain Tumor MRI Images with U-Net Architecture. El-Cezeri, Cilt: 9 Sayı: 4 Özel Sayı, 1583–1590. https://doi.org/10.31202/ecjse.1169424

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (13)

  1. A. McNeill, “Epidemiology of Brain Tumors,” Neurologic Clinics, vol. 34, no. 4. W.B. Saunders, pp. 981–998, Nov. 01, 2016.
  2. Sazzad, M. Hoque, M. Rahman, and T. Ahmmed, Development of Automated Brain Tumor Identification Using MRI Images. IEEE, 2019.
  3. A. Zeineldin, M. E. Karar, J. Coburger, C. R. Wirtz, and O. Burgert, “DeepSeg: deep neural network framework for automatic brain tumor segmentation using magnetic resonance FLAIR images,” International Journal of Computer Assisted Radiology and Surgery, vol. 15, no. 6, pp. 909, 2020.
  4. Amin, M. Sharif, M. Yasmin, and S. L. Fernandes, “A distinctive approach in brain tumor detection and classification using MRI,” Pattern Recognition Letters, vol. 139, pp. 118–127, 2020.
  5. Atban and H. O. Ilhan, “MR görüntüleri üzerinden Alzheimer hastaliǧinin tespiti için Evrişimli Sinir Aǧ tasarimi ve performans kiyaslamasi,” in ISMSIT 2021 - 5th International Symposium on Multidisciplinary Studies and Innovative Tech., Proceedings, 2021.
  6. Deepak and P. M. Ameer, “Brain tumor classification using deep CNN features via transfer learning,” Computers in Biology and Medicine, vol. 111, no. June, p. 103345, 2019.
  7. Ito, K. Nakae, J. Hata, H. Okano, and S. Ishii, “Semi-supervised deep learning of brain tissue segmentation,” Neural Networks, vol. 116, pp. 25–34, 2019.
  8. T. Kebir and S. Mekaoui, “An Efficient Methodology of Brain Abnormalities Detection using CNN Deep Learning Network,” Proceedings of the 2018 International Conference on Applied Smart Systems, ICASS 2018, no. November, pp. 1–5, 2019.
  9. Mittal, L. M. Goyal, S. Kaur, I. Kaur, A. Verma, and D. Jude Hemanth, “Deep learning based enhanced tumor segmentation approach for MR brain images,” Applied Soft Computing Journal, vol. 78, pp. 346–354, 2019.
  10. M. Talo, U. B. Baloglu, Ö. Yıldırım, and U. Rajendra Acharya, “Application of deep transfer learning for automated brain abnormality classification using MR images,” Cognitive Systems Research, vol. 54, pp. 176–188, 2019.
  11. B. Niepceron, A. Nait-Sidi-Moh, and F. Grassia, “Moving Medical Image Analysis to GPU Embedded Systems: Application to Brain Tumor Segmentation,” Applied Artificial Intelligence, vol. 34, no. 12, pp. 1–14, 2020.
  12. W. Zhang et al., “Deep convolutional neural networks for multi-modality isointense infant brain image segmentation,” NeuroImage, vol. 108, pp. 214–224, 2015.
  13. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” 2015.