Korean Journal of Artificial Intelligence (한국인공지능학회지)

Korea Artificial Intelligence Association (한국인공지능학회)
권호 표지
DOI QR코드

DOI QR Code

Feasibility Study of CNN-based Super-Resolution Algorithm Applied to Low-Resolution CT Images

  • Doo Bin KIM (Department of Radiology, Uijeongbu Eulji Medical Center) ;
  • Mi Jo LEE (Department of Radiation Oncology, Catholic Kwandong University International ST.MARY's Hospital) ;
  • Joo Wan HONG (Department of Radiological Science, Eulji University)
  • Received : 2024.01.08
  • Accepted : 2024.02.14
  • Published : 2024.03.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, various techniques are being applied through the development of medical AI, and research has been conducted on the application of super-resolution AI models. In this study, evaluate the results of the application of the super-resolution AI model to brain CT as the basic data for future research. Acquiring CT images of the brain, algorithm for brain and bone windowing setting, and the resolution was downscaled to 5 types resolution image based on the original resolution image, and then upscaled to resolution to create an LR image and used for network input with the original imaging. The SRCNN model was applied to each of these images and analyzed using PSNR, SSIM, Loss. As a result of quantitative index analysis, the results were the best at 256×256, the brain and bone window setting PSNR were the same at 33.72, 35.2, and SSIM at 0.98 respectively, and the loss was 0.0004 and 0.0003, respectively, showing relatively excellent performance in the bone window setting CT image. The possibility of future studies aimed image quality and exposure dose is confirmed, and additional studies that need to be verified are also presented, which can be used as basic data for the above studies.

Keywords

Acknowledgement

This paper was supported by Eulji University in 2023(EJRG-23-15)

References

  1. Brenner, D. J., & Hall, E. J. (2007). Computed tomography-an increasing source of radiation exposure. New England journal of medicine, 357(22), 2277-2284.
  2. Brownlee, J. (2016). Deep learning with Python: develop deep learning models on Theano and TensorFlow using Keras. Machine Learning Mastery.
  3. Cubuk, E. D., Zoph, B., Mane, D., Vasudevan, V., & Le, Q. V. (2018). Autoaugment: Learning augmentation policies from data. arXiv preprint arXiv:1805.09501.
  4. Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE transactions on pattern analysis and machine intelligence, 38(2), 295-307.
  5. Georgescu, M. I., Ionescu, R. T., & Verga, N. (2020). Convolutional neural networks with intermediate loss for 3D super-resolution of CT and MRI scans. IEEE Access, 8, 49112-49124.
  6. Gudivada, V., Apon, A., & Ding, J. (2017). Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations. International Journal on Advances in Software, 10(1), 1-20.
  7. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision (pp. 1026-1034).
  8. Hsieh, J., Nett, B., Yu, Z., Sauer, K., Thibault, J. B., & Bouman, C. A. (2013). Recent advances in CT image reconstruction. Current Radiology Reports, 1, 39-51.
  9. Jhnson, D. H. (2006). Signal-to-noise ratio. Scholarpedia, 1(12), 2088.
  10. Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  11. Mathieu, M., Couprie, C., & LeCun, Y. (2015). Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440.
  12. National Health Insurance Service. (2022). 2022 Major Health Insurance Statistics. Retrived from: https://www.hira.or.kr/bbsDummy.do?pgmid=HIRAJ030000007001&brdScnBltNo=4&brdBltNo=7&pageIndex=1&pageIndex2=1#none
  13. Protection, R. (2007). ICRP publication 103. Ann ICRP, 37(2.4), 2.
  14. Shen, D., Wu, G., & Suk, H. I. (2017). Deep learning in medical image analysis. Annual review of biomedical engineering, 19, 221-248.
  15. Wang, J., Chen, Y., Wu, Y., Shi, J., & Gee, J. (2020). Enhanced generative adversarial network for 3D brain MRI super-resolution. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 3627-3636).
  16. Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4), 600-612.
  17. Whiting, B. R. (2002, May). Signal statistics in x-ray computed tomography. In Medical Imaging 2002: Physics of Medical Imaging (Vol. 4682, pp. 53-60). SPIE.
  18. Zhang, Y., & An, M. (2017). Deep learning-and transfer learning-based super resolution reconstruction from single medical image. Journal of healthcare engineering, 2017.