Research Article

Generating Synthetic Images from Real MR Images Using Deep Learning Methods

Volume: 9 Number: 4 December 31, 2023
TR EN

Generating Synthetic Images from Real MR Images Using Deep Learning Methods

Abstract

Different technological methods are utilized today for diagnosing various diseases in tissues and organs within the human body. The most crucial ones among these are Computed Tomography (CT) and Magnetic Resonance (MR) imaging techniques. The process of MR imaging enables the identification of the size and shapes of tumor regions in the body's tissues, facilitating experts in determining the type of tumor as well as whether it is benign or malignant. To aid professionals in this regard, several deep learning-based computer software have been developed to accurately pinpoint tumor areas on the tissue. Due to the lack of image data used in deep learning studies, a limitation naturally arises in studies in this field. In order to eliminate the lack of image data in these studies, image augmentation can be performed using deep learning methods as well as data augmentation methods using various image processing techniques. In this study, Generative Adversarial Networks (GAN), a deep learning technique, were employed to duplicate brain MR images and generate synthetic images. After the resulting MR images were made usable by undergoing various pre-processing, similarity rates to real images were calculated using metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural similarity index (SSIM) and Mean Square Error (MSE), and by looking at these rates, realistic images were added to the data set and the data set was expanded.

Keywords

References

  1. [1] A.G. Eker and N. Duru, “Medikal görüntü işlemede derin öğrenme uygulamaları,” Acta Infologıca, vol. 5, no. 2, pp. 459-474, 2021. doi:10.26650/acin.927561
  2. [2] U. Kaya, A. Yılmaz and Y. Dikmen, “Sağlık alanında kullanılan derin öğrenme yöntemleri,” Avrupa Bilim ve Teknoloji Dergisi, vol. 16, pp. 792-808, August 2019. doi:10.31590/ejosat.573248
  3. [3] H. Chen, Z. Qin, Y. Ding, L. Tian and Z. Qin, “Brain tumor segmentation with deep convolutional symmetric neural network,” Neurocomputing, vol. 392, pp. 305-313, 2020. doi: 10.1016/j.neucom.2019.01.111
  4. [4] G. Çelik and M. F. Talu, “Çekişmeli üretken ağ modellerinin görüntü üretme performanslarının incelenmesi,” BAUN Fen Bil. Enst. Dergisi, vol. 22, pp. 181-192, 2020. doi: 10.25092/baunfbed.679608
  5. [5] I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, Aaron Courville and Yoshua Bengio, “Generative adversarial nets,” Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014, Available: NeurIPS Proceedings, https://proceedings.neurips.cc/paper_files/paper/2014/hash/5ca3e9b122f61f8f06494c97b1afccf3-Abstract.html. [Accessed: 20 August. 2023].
  6. [6] C. Shorten and T. M. Khoshgoftaar, “A survey on ımage data augmentation for deep learning”, J Big Data, vol. 6, pp. 60, 2019. doi: 10.1186/s40537-019-0197-0
  7. [7] Y. Liu, J. Zhang, T. Zhao and Z. Wang, “Reconstruction of the meso-scale concrete model using a deep convolutional generative adversarial network (DCGAN)”, Construction and Building Materials, vol. 370, 2023. doi:10.1016/j.conbuildmat.2023.130704
  8. [8] R. Gonzalez and R. Woods, Digital Image Processing, Edition. 3, NJ: Pearson, 2008.

Details

Primary Language

English

Subjects

Software Engineering (Other)

Journal Section

Research Article

Publication Date

December 31, 2023

Submission Date

November 19, 2023

Acceptance Date

December 22, 2023

Published in Issue

Year 2023 Volume: 9 Number: 4

APA
Güvenç, E., Çetin, G., & Ersoy, M. (2023). Generating Synthetic Images from Real MR Images Using Deep Learning Methods. Gazi Journal of Engineering Sciences, 9(4), 230-239. https://izlik.org/JA65MK57CK
AMA
1.Güvenç E, Çetin G, Ersoy M. Generating Synthetic Images from Real MR Images Using Deep Learning Methods. GJES. 2023;9(4):230-239. https://izlik.org/JA65MK57CK
Chicago
Güvenç, Ercüment, Gürcan Çetin, and Mevlüt Ersoy. 2023. “Generating Synthetic Images from Real MR Images Using Deep Learning Methods”. Gazi Journal of Engineering Sciences 9 (4): 230-39. https://izlik.org/JA65MK57CK.
EndNote
Güvenç E, Çetin G, Ersoy M (December 1, 2023) Generating Synthetic Images from Real MR Images Using Deep Learning Methods. Gazi Journal of Engineering Sciences 9 4 230–239.
IEEE
[1]E. Güvenç, G. Çetin, and M. Ersoy, “Generating Synthetic Images from Real MR Images Using Deep Learning Methods”, GJES, vol. 9, no. 4, pp. 230–239, Dec. 2023, [Online]. Available: https://izlik.org/JA65MK57CK
ISNAD
Güvenç, Ercüment - Çetin, Gürcan - Ersoy, Mevlüt. “Generating Synthetic Images from Real MR Images Using Deep Learning Methods”. Gazi Journal of Engineering Sciences 9/4 (December 1, 2023): 230-239. https://izlik.org/JA65MK57CK.
JAMA
1.Güvenç E, Çetin G, Ersoy M. Generating Synthetic Images from Real MR Images Using Deep Learning Methods. GJES. 2023;9:230–239.
MLA
Güvenç, Ercüment, et al. “Generating Synthetic Images from Real MR Images Using Deep Learning Methods”. Gazi Journal of Engineering Sciences, vol. 9, no. 4, Dec. 2023, pp. 230-9, https://izlik.org/JA65MK57CK.
Vancouver
1.Ercüment Güvenç, Gürcan Çetin, Mevlüt Ersoy. Generating Synthetic Images from Real MR Images Using Deep Learning Methods. GJES [Internet]. 2023 Dec. 1;9(4):230-9. Available from: https://izlik.org/JA65MK57CK

Gazi Journal of Engineering Sciences (GJES) publishes open access articles under a Creative Commons Attribution 4.0 International License (CC BY 4.0)  1366_2000-copia-2.jpg