Research Article
BibTex RIS Cite

Deep learning-based brain tumor segmentation: A comparison of U-Net and segNet algorithms

Year 2024, Volume: 3 Issue: 2, 99 - 109
https://doi.org/10.70700/bjea.1581404

Abstract

Brain tumors are among the diseases that pose a serious health concern worldwide and can lead to fatal outcomes if left untreated. The segmentation of brain tumors is a critical step for the accurate diagnosis of the disease and effective management of the treatment process. This study was conducted to examine the success rates of deep learning-based U-Net and SegNet algorithms in brain tumor segmentation. MRI brain images and black and white masks belonging to these images were used in the study. Image processing techniques, including histogram equalization, edge detection, noise reduction, contrast enhancement, and Gaussian blurring, were applied. These image processing steps improved the quality of the MRI images, contributing to more accurate segmentation results. As a result of the segmentation operations performed with U-Net and SegNet algorithms, the U-Net algorithm achieved an accuracy rate of 96%, while the SegNet algorithm’s accuracy rate was measured at 94%. The study determined that the U-Net algorithm provided a higher success rate and was more effective in brain tumor segmentation. In particular, the contribution of image processing steps to segmentation success was observed.

Ethical Statement

Our article is outside the scope of ethics, "There is no ethical problem with the publication of this article." The data used in our study is publicly available and is not subject to data confidentiality.

References

  • S. Rasheed, K. Rehman, and M. S. H. Akash, “An insight into the risk factors of brain tumors and their therapeutic interventions,” Biomed. Pharmacother., vol. 143, p. 112119, Nov. 2021, doi: 10.1016/J.BIOPHA.2021.112119.
  • E. Radhi and M. K. Systems, “Breast Tumor Detection Via Active Contour Technique.,” J. Intell. Eng. 2021, Undefined, vol. 14, no. 4, pp. 561–570, 2021, Accessed: Nov. 07, 2024. [Online]. Available: https://www.researchgate.net/profile/Mohammed-Kamil 8/publication/353169254_Breast_Tumor_Detection_Via_Active_Contour_Technique/links/60eb554030e8e50c01fb41b1/Breast-Tumor-Detection-Via-Active-Contour-Technique.pdf
  • T. Magadza and S. Viriri, “Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art,” J. Imaging, vol. 7, no. 2, p. 19, Jan. 2021, doi: 10.3390/JIMAGING7020019.
  • E. S. Biratu, F. Schwenker, Y. M. Ayano, and T. G. Debelee, “A Survey of Brain Tumor Segmentation and Classification Algorithms,” J. Imaging, vol. 7, no. 9, p. 179, Sep. 2021, doi: 10.3390/JIMAGING7090179.
  • Z. Liu, L. Tong, U. Chen, Z. Jiang, F. Zhou, Q. Zhang, X. Zhang, Y. Jin and H. Zhou, “Deep learning based brain tumor segmentation: a survey,” Complex Intell. Syst., vol. 9, no. 1, pp. 1001–1026, Feb. 2023, doi: 10.1007/S40747-022-00815-5/TABLES/5.
  • 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, Dec. 2020, doi: 10.3390/ELECTRONICS9122203.
  • M. A. Ottom, H. A. Rahman, and I. D. Dinov, “Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation,” IEEE J. Transl. Eng. Heal. Med., vol. 10, 2022, doi: 10.1109/JTEHM.2022.3176737.
  • A. R. Khan, S. Khan, M. Harouni, R. Abbasi, S. Iqbal and Z. Mehmood, “Brain tumor segmentation using K-means clustering and deep learning with synthetic data augmentation for classification,” Microsc. Res. Tech., vol. 84, no. 7, pp. 1389–1399, Jul. 2021, doi: 10.1002/JEMT.23694.
  • R. Naseem, Z. A. Khan, N. Satpute, A. Beghdadi, F. A. Cheikh and J. Olivares, “Cross-Modality Guided Contrast Enhancement for Improved Liver Tumor Image Segmentation,” IEEE Access, vol. 9, pp. 118154–118167, 2021, doi: 10.1109/ACCESS.2021.3107473.
  • K. G. Dhal, A. Das, S. Ray, J. Gálvez and S. Das, “Histogram Equalization Variants as Optimization Problems: A Review,” Arch. Comput. Methods Eng., vol. 28, no. 3, pp. 1471–1496, May 2021, doi: 10.1007/S11831-020-09425-1/TABLES/17.
  • A. Lasocki and F. Gaillard, “Non-Contrast-Enhancing Tumor: A New Frontier in Glioblastoma Research,” Am. J. Neuroradiol., vol. 40, no. 5, pp. 758–765, May 2019, doi: 10.3174/AJNR.A6025.
  • O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9351, pp. 234–241, 2015, doi: 10.1007/978-3-319-24574-4_28.
  • V. Badrinarayanan, A. Kendall and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 12, pp. 2481–2495, Dec. 2017, doi: 10.1109/TPAMI.2016.2644615.
  • M. S. Aslanpour, S. S. Gill and A. N. Toosi, “Performance evaluation metrics for cloud, fog and edge computing: A review, taxonomy, benchmarks and standards for future research,” Internet of Things, vol. 12, p. 100273, Dec. 2020, doi: 10.1016/J.IOT.2020.100273.
  • C. J. Needham and R. D. Boyle, “Performance Evaluation Metrics and Statistics for Positional Tracker Evaluation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 2626, pp. 278–289, 2003, doi: 10.1007/3-540-36592-3_27.

Derin öğrenme tabanlı beyin tümörü segmentasyonu: U-Net ve segNet algoritmalarının karşılaştırılması

Year 2024, Volume: 3 Issue: 2, 99 - 109
https://doi.org/10.70700/bjea.1581404

Abstract

Beyin tümörleri, dünya genelinde ciddi bir sağlık sorunu oluşturan ve tedavi edilmediği takdirde ölümcül sonuçlara yol açabilen hastalıklar arasında yer almaktadır. Beyin tümörlerinin segmentasyonu hastalığın doğru teşhisi ve tedavi sürecinin başarılı bir şekilde yönetilmesi için kritik bir adımdır. Bu çalışma görüntü işleme yöntemleri ve derin öğrenme tabanlı U-Net, SegNet algoritmalarının beyin tümörü segmentasyonundaki başarı oranlarını incelemek amacıyla gerçekleştirilmiştir. Çalışmada MR beyin görüntüleri ve bu görüntülere ait siyah-beyaz maskeler kullanılmıştır. Görüntü işleme teknikleri olarak histogram eşitleme, kenar bulma, gürültü azaltma, kontrast iyileştirme ve Gaussian bulanıklaştırma yöntemleri uygulanmıştır. Bu görüntü işleme adımları MR görüntülerinin kalitesini artırarak segmentasyon işleminde daha doğru sonuçlar elde edilmesine katkı sağlamıştır. U-Net ve SegNet algoritmaları ile yapılan segmentasyon işlemleri sonucunda U-Net algoritması %96 doğruluk oranına ulaşırken SegNet algoritmasının doğruluk oranı %94 olarak ölçülmüştür. Çalışmada U-Net algoritmasının daha yüksek bir başarı oranı sunduğu ve beyin tümörü segmentasyonunda daha etkin olduğu tespit edilmiştir. Özellikle, görüntü işleme adımlarının segmentasyon başarısına katkısı gözlemlenmiştir.

Ethical Statement

Makalemiz etik kapsamının dışındadır, "Bu makalenin yayınlanmasıyla ilgili etik bir sorun yoktur." Çalışmamızda kullanılan veriler kamuya açıktır ve veri gizliliğine tabi değildir.

References

  • S. Rasheed, K. Rehman, and M. S. H. Akash, “An insight into the risk factors of brain tumors and their therapeutic interventions,” Biomed. Pharmacother., vol. 143, p. 112119, Nov. 2021, doi: 10.1016/J.BIOPHA.2021.112119.
  • E. Radhi and M. K. Systems, “Breast Tumor Detection Via Active Contour Technique.,” J. Intell. Eng. 2021, Undefined, vol. 14, no. 4, pp. 561–570, 2021, Accessed: Nov. 07, 2024. [Online]. Available: https://www.researchgate.net/profile/Mohammed-Kamil 8/publication/353169254_Breast_Tumor_Detection_Via_Active_Contour_Technique/links/60eb554030e8e50c01fb41b1/Breast-Tumor-Detection-Via-Active-Contour-Technique.pdf
  • T. Magadza and S. Viriri, “Deep Learning for Brain Tumor Segmentation: A Survey of State-of-the-Art,” J. Imaging, vol. 7, no. 2, p. 19, Jan. 2021, doi: 10.3390/JIMAGING7020019.
  • E. S. Biratu, F. Schwenker, Y. M. Ayano, and T. G. Debelee, “A Survey of Brain Tumor Segmentation and Classification Algorithms,” J. Imaging, vol. 7, no. 9, p. 179, Sep. 2021, doi: 10.3390/JIMAGING7090179.
  • Z. Liu, L. Tong, U. Chen, Z. Jiang, F. Zhou, Q. Zhang, X. Zhang, Y. Jin and H. Zhou, “Deep learning based brain tumor segmentation: a survey,” Complex Intell. Syst., vol. 9, no. 1, pp. 1001–1026, Feb. 2023, doi: 10.1007/S40747-022-00815-5/TABLES/5.
  • 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, Dec. 2020, doi: 10.3390/ELECTRONICS9122203.
  • M. A. Ottom, H. A. Rahman, and I. D. Dinov, “Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation,” IEEE J. Transl. Eng. Heal. Med., vol. 10, 2022, doi: 10.1109/JTEHM.2022.3176737.
  • A. R. Khan, S. Khan, M. Harouni, R. Abbasi, S. Iqbal and Z. Mehmood, “Brain tumor segmentation using K-means clustering and deep learning with synthetic data augmentation for classification,” Microsc. Res. Tech., vol. 84, no. 7, pp. 1389–1399, Jul. 2021, doi: 10.1002/JEMT.23694.
  • R. Naseem, Z. A. Khan, N. Satpute, A. Beghdadi, F. A. Cheikh and J. Olivares, “Cross-Modality Guided Contrast Enhancement for Improved Liver Tumor Image Segmentation,” IEEE Access, vol. 9, pp. 118154–118167, 2021, doi: 10.1109/ACCESS.2021.3107473.
  • K. G. Dhal, A. Das, S. Ray, J. Gálvez and S. Das, “Histogram Equalization Variants as Optimization Problems: A Review,” Arch. Comput. Methods Eng., vol. 28, no. 3, pp. 1471–1496, May 2021, doi: 10.1007/S11831-020-09425-1/TABLES/17.
  • A. Lasocki and F. Gaillard, “Non-Contrast-Enhancing Tumor: A New Frontier in Glioblastoma Research,” Am. J. Neuroradiol., vol. 40, no. 5, pp. 758–765, May 2019, doi: 10.3174/AJNR.A6025.
  • O. Ronneberger, P. Fischer and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9351, pp. 234–241, 2015, doi: 10.1007/978-3-319-24574-4_28.
  • V. Badrinarayanan, A. Kendall and R. Cipolla, “SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 12, pp. 2481–2495, Dec. 2017, doi: 10.1109/TPAMI.2016.2644615.
  • M. S. Aslanpour, S. S. Gill and A. N. Toosi, “Performance evaluation metrics for cloud, fog and edge computing: A review, taxonomy, benchmarks and standards for future research,” Internet of Things, vol. 12, p. 100273, Dec. 2020, doi: 10.1016/J.IOT.2020.100273.
  • C. J. Needham and R. D. Boyle, “Performance Evaluation Metrics and Statistics for Positional Tracker Evaluation,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 2626, pp. 278–289, 2003, doi: 10.1007/3-540-36592-3_27.
There are 15 citations in total.

Details

Primary Language English
Subjects Electronics
Journal Section Research Articles
Authors

Talip Çay 0000-0002-5490-1651

Early Pub Date December 26, 2024
Publication Date
Submission Date November 8, 2024
Acceptance Date November 25, 2024
Published in Issue Year 2024 Volume: 3 Issue: 2

Cite

APA Çay, T. (2024). Deep learning-based brain tumor segmentation: A comparison of U-Net and segNet algorithms. Bozok Journal of Engineering and Architecture, 3(2), 99-109. https://doi.org/10.70700/bjea.1581404
AMA Çay T. Deep learning-based brain tumor segmentation: A comparison of U-Net and segNet algorithms. BJEA. December 2024;3(2):99-109. doi:10.70700/bjea.1581404
Chicago Çay, Talip. “Deep Learning-Based Brain Tumor Segmentation: A Comparison of U-Net and SegNet Algorithms”. Bozok Journal of Engineering and Architecture 3, no. 2 (December 2024): 99-109. https://doi.org/10.70700/bjea.1581404.
EndNote Çay T (December 1, 2024) Deep learning-based brain tumor segmentation: A comparison of U-Net and segNet algorithms. Bozok Journal of Engineering and Architecture 3 2 99–109.
IEEE T. Çay, “Deep learning-based brain tumor segmentation: A comparison of U-Net and segNet algorithms”, BJEA, vol. 3, no. 2, pp. 99–109, 2024, doi: 10.70700/bjea.1581404.
ISNAD Çay, Talip. “Deep Learning-Based Brain Tumor Segmentation: A Comparison of U-Net and SegNet Algorithms”. Bozok Journal of Engineering and Architecture 3/2 (December 2024), 99-109. https://doi.org/10.70700/bjea.1581404.
JAMA Çay T. Deep learning-based brain tumor segmentation: A comparison of U-Net and segNet algorithms. BJEA. 2024;3:99–109.
MLA Çay, Talip. “Deep Learning-Based Brain Tumor Segmentation: A Comparison of U-Net and SegNet Algorithms”. Bozok Journal of Engineering and Architecture, vol. 3, no. 2, 2024, pp. 99-109, doi:10.70700/bjea.1581404.
Vancouver Çay T. Deep learning-based brain tumor segmentation: A comparison of U-Net and segNet algorithms. BJEA. 2024;3(2):99-109.