한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

Medical Image Denoising using Wavelet Transform-Based CNN Model

  • Seoyun Jang (Dept. of Information and Statistics, Gyeongsang National University) ;
  • Dong Hoon Lim (Dept. of Information and Statistics, RINS, Gyeongsang National University)
  • 투고 : 2024.07.09
  • 심사 : 2024.10.09
  • 발행 : 2024.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

MRI(Magnetic Resonance Imaging) 영상과 CT(Computed Tomography) 영상과 같은 의료영상에서 잡음제거는 의료영상 시스템의 성능에 중요한 영향을 미친다. 최근 영상처리 기술에 딥러닝(Deep Learning)의 도입으로 잡음제거 방법들의 성능이 향상되고 있다. 그러나 영상영역에서 디테일을 보존하면서 잡음만을 제거하는 것은 한계가 있다. 본 논문에서는 웨이블렛 변환 기반 CNN(Convolutional Neural Network) 모형, 즉 WT-DnCNN(Wavelet Transform-Denoising Convolutional Neural Network) 모형을 통해 잡음제거 성능을 높이고자 한다. 이는 잡음 영상에 웨이블렛 변환을 사용하여 주파수 대역별로 구분하여 일차적으로 잡음을 제거하고, 해당 주파수 대역에서 기존 DnCNN 모형을 적용하여 최종적으로 잡음을 제거하고자 한다. 본 논문에서 제안된 WT-DnCNN 모형의 성능평가를 위해 다양한 잡음, 즉, 가우시안 잡음(Gaussian Noise), 포아송 잡음(Poisson Noise) 그리고 스펙클 잡음(Speckle Noise)에 의해 훼손된 MRI 영상과 CT 영상을 대상으로 실험하였다. 성능 실험 결과, WT-DnCNN 모형은 정성적 비교에서 전통적인 필터 즉, BM3D(Block-Matching and 3D Filtering) 필터뿐만 아니라 기존의 딥러닝 모형인 DnCNN, CDAE(Convolution Denoising AutoEncoder) 모형보다 우수하고, 정량적 비교에서 PSNR(Peak Signal-to-Noise Ratio) 과 SSIM(Structural Similarity Index Measure) 수치는 MRI 영상에서 각각 36~43과 0.93~0.98, CT 영상에서 각각 38~43과 0.95~0.98 정도로 우수한 결과를 보였다. 또한, 모형의 실행 속도 비교에서 DnCNN 모형은 BM3D 모형보다는 훨씬 적게 결렸으나 DnCNN 모형과의 비교에서는 웨이블렛 변환 추가로 인해 오래 걸림을 알 수 있었다.

In medical images such as MRI(Magnetic Resonance Imaging) and CT(Computed Tomography) images, noise removal has a significant impact on the performance of medical imaging systems. Recently, the introduction of deep learning in image processing technology has improved the performance of noise removal methods. However, there is a limit to removing only noise while preserving details in the image domain. In this paper, we propose a wavelet transform-based CNN(Convolutional Neural Network) model, namely the WT-DnCNN(Wavelet Transform-Denoising Convolutional Neural Network) model, to improve noise removal performance. This model first removes noise by dividing the noisy image into frequency bands using wavelet transform, and then applies the existing DnCNN model to the corresponding frequency bands to finally remove noise. In order to evaluate the performance of the WT-DnCNN model proposed in this paper, experiments were conducted on MRI and CT images damaged by various noises, namely Gaussian noise, Poisson noise, and speckle noise. The performance experiment results show that the WT-DnCNN model is superior to the traditional filter, i.e., the BM3D(Block-Matching and 3D Filtering) filter, as well as the existing deep learning models, DnCNN and CDAE(Convolution Denoising AutoEncoder) model in qualitative comparison, and in quantitative comparison, the PSNR(Peak Signal-to-Noise Ratio) and SSIM(Structural Similarity Index Measure) values were 36~43 and 0.93~0.98 for MRI images and 38~43 and 0.95~0.98 for CT images, respectively. In addition, in the comparison of the execution speed of the models, the DnCNN model was much less than the BM3D model, but it took a long time due to the addition of the wavelet transform in the comparison with the DnCNN model.

키워드

과제정보

This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. NRF-2022R1A2C1011140).

참고문헌

  1. M. Ameen, and S. A. Ahmed, "An Extensive Review of Medical Image Denoising Techniques," International Journal of Electronics and Communication Engineering and Technology, Vol. 7, No. 6, pp. 85-90, December 2016. 
  2. S. M. Boby, and S. Sharmin, "Medical Image Denoising Techniques against Hazardous Noises: An IQA Metrics Based Comparative Analysis," International Journal of Image, Graphics and Signal Processing, Vol. 14, No. 2, pp. 25-43, April 2021. DOI: 10.5815/ijigsp.2021.02.03. 
  3. S. Anitha, L. Kola, P. Sushma, and S. Archana, "Analysis of filtering and novel technique for noise removal in MRI and CT images," Proceedings of the 2017 International Conference on Electrical, Electronics, Communication, Computer, and Optimization Techniques, pp. 815-827, February 2017, DOI: 10.1109/ICEECCOT.2017.8284618. 
  4. K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, "Image denoising by sparse 3-D transform-domain collaborative filtering," IEEE Transactions on Image Processing, Vol. 16, No. 8, pp. 2080-2095, July 2007, DOI: 10.1109/TIP.2007.901238. 
  5. L. Fan, F. Zhang, H. Fan, and C. Zhang, "Brief review of image denoising techniques," Visual Computing for Industry, Biomedicine, and Art, Vol. 2, No. 7, pp 1-12, July 2019, DOI: 10.1186/s42492-019-0016-7. 
  6. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising," IEEE Transactions on Image Processing, Vol. 26, No. 7, pp 3142-3155, July 2017, DOI: 10.1109/TIP.2017.2662206. 
  7. W. H. Lee, M. Ozger, U. Challita, and K. W. Sung, "Noise Learning-Based Denoising Autoencoder," IEEE Communications Letters, Vol. 25, No. 9, pp. 2983 - 2987, September 2021. DOI: 10.1109/LCOMM.2021.3091800. 
  8. P. S. S. Prasad, K. S. V. Vamsi, M. Ameeruddin, A.Lakshmanarao, and M. Singampalli, "Image Denoising using CNN in Deep Learning," Proceedings of the 8th International Conference on Communication and Electronics Systems (ICCES), pp. 1343-1346, June 2023, DOI: 10.1109/ICCES57224.2023.10192784. 
  9. C. Yang, J. Ye, Y. Wang, and C. Song, "X-Ray Breast Images Denoising Method Based on the Convolutional Autoencoder," Mathematical Problems in Engineering, Vol. 2022, pp. 1-10, November 2022, DOI: 10.1155/2022/2362851. 
  10. Y. Farooq, and S. Savas, "Noise Removal from the Image Using Convolutional Neural Networks-Based Denoising Auto Encoder," Journal of Emerging Computer Technologies, Vol. 3, No. 1, pp. 21-28. December 2023, DOI: 10.57020/ject.1390428. 
  11. S. Ruikar, and D. D. Doye, "Image Denoising using Wavelet Transform," Proceedings of the 2010 International Conference on Mechanical and Electrical Technology, pp. 509-515, September 2010, DOI: 10.1109/ICMET.2010.5598411. 
  12. S. Khedkar, K. Akant, and M. M. Khanapurkar, "Image Denoising using Wavelet Transform," International Journal of Research in Engineering and Technology, Vol. 5, No. 4, pp. 206-212, April 2016. 
  13. P. Hedaoo, and S. S. Godbole, "Wavelet Thresholding Approach For Image Denoising," International Journal of Network Security & Its Applications, Vol. 3, No. 4, pp. 16-21, July 2011, DOI: 10.5121/ijnsa.2011.3402. 
  14. H. C. Jeong, and D. H. Lim, "An Efficient CT Image Denoising using WT-GAN Model," Journal of The Korea Society of Computer and Information, Vol. 29 No. 5, pp. 21-29, May 2024, DOI: 10.9708/jksci.2024.29.05.021. 
  15. Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image Quality Assessment: From Error Visibility to Structural Similarity," IEEE Transactions on Image Processing, Vol. 13, No. 4, pp. 600-612, April 2004, DOI: 10.1109/TIP.2003.819861. 
  16. U. Sara, M. Akter, and M. Uddin, "Image Quality Assessment through FSIM, SSIM, MSE and PSNR-A Comparative Study," Journal of Computer and Communications, Vol. 7, No. 3, pp. 8-18, March 2019, DOI: 10.4236/jcc.2019.73002. 
  17. A. Makandar, D. Mulimani, and M. Jevoor, "Comparative Study of Different Noise Models and Effective Filtering Techniques," International Journal of Science and Research, Vol. 3, pp. 458-464. August 2014. 
  18. S. G. Mallat, "A Theory for Multiresolution Signal Decomposition: The Wavelet Representation," IEEE Transactions on Pattern Analysis & Machine Intelligence, Vol. 11, No. 4, pp. 674-693, July 1989, DOI: 10.1109/34.192463. 
  19. A. Khmag, A. R. Ramli, S. A. R. Al-Haddad, and S. J. Hashim, "A Detailed Study on Image Denoising Algorithms by Using the Discrete Wavelet Transformation," International Journal of Computer Science And Technology, Vol. 5, pp. 17-24, March 2014, DOI: 10.1109/TIP.2003.819861. 
  20. C. Tian, M. Zheng, W. Zuoc, B. Zhang, and Y. Zhang, "Multi-stage image denoising with the wavelet transform," Pattern Recognition, Vol. 134, pp. 1-12, February 2023, DOI: 10.1016/j.patcog.2022.109050. 
  21. W. Wang, "An improved denoising model for convolutional neural network," Journal of Physics: Conference Series, Vol. 1982, pp. 1-7, March 2021, DOI: 10.1088/1742-6596/1982/1/012169. 
  22. G. Y. Chen, W. Xie, and A. Krzyzak, "Improved Blind Image Denoising with DnCNN," Advanced Intelligent Computing Technology and Applications, pp. 263-271, August 2023, DOI: 10.1007/978-981-99-4742-3-21. 
  23. L. Cheplanov, S. Avidan, D. J. Bonfil, and I. Klapp, "Hyperspectral image dynamic range reconstruction using deep neural network-based denoising methods," Machine Vision and Applications, Vol. 35, No. 39, pp. 1-14, March 2024, DOI: 10.1007/s00138-024-01523-5. 
  24. R. Patil and S. Bhosale, "Multi-Modal Medical Image Denoising using Wavelets: A Comparative Study," Biomedical & Pharmacology Journal, Vol. 16, No. 4, pp. 2271-2281, December 2023, DOI: 10.13005/bpj/2803. 
  25. B. Li, Y. Cong, and H. Mo, "Image denoising method integrating ridgelet transform and improved wavelet threshold," PLoS One, Vol. 19, No. 9, pp. 1-22, September 2024, DOI: 10.1371/journal.pone.0306706. 
  26. M. Talbi, R. Baazaoui, and B. Nasraoui, "A novel method of image denoising based on 2D dual-tree DWT and SWT," International Journal of Wavelets, Multiresolution and Information Processing, Vol. 22, No. 04, pp. 1-20, July 2024, DOI: 10.1142/S0219691324500097. 
  27. A. Shukla, K. Seethalakshmi, P. Hema, and J. C. Musale, "An Effective Approach for Image Denoising Using Wavelet Transform Involving Deep Learning Techniques," Proceedings of the 4th International Conference on Smart Electronics and Communication, pp. 1381-1386, September 2023, DOI: 10.1109/ICOSEC58147.2023.10275904. 
  28. K. Liu, Y. Guo, and B. Su, "Image Denoising Network Based on Subband Information Sharing Using Dual-Tree Complex Wavelet," Neural Processing Letters, Vol. 55, No. 8, pp. 10975-10991, July, 2023, DOI: 10.1007/s11063-023-11359-1. 
  29. R. Xu, Y. Xu, X. Yang, H. Huang, Z. Lei, and Y. Quan,"Wavelet analysis model inspired convolutional neural networks for image denoising," Applied Mathematical Modelling, Vol. 125, pp. 798-811, January 2024, DOI: 10.1016/j.apm.2023.10.023. 
  30. P. Singh, E. Sizikova, and J. Cirrone, "CASS: Cross architectural self-supervision for medical image analysis," arXiv, pp. 1-16, 2022, DOI: 10.48550/arXiv.2206.04170. 
  31. Y. Chen, Z. He, M. A. Ashraf, X. Chen, Y. Liu, X. Ding, B. Tong, and Y. Chen, "Performance evaluation of attention-deep hashing based medical image retrieval in brain MRI datasets," Journal of Radiation Research and Applied Sciences, Vol.17, No. 3, pp. 1-10, September 2024, DOI: 10.1016/j.jrras.2024.100968. 
  32. M. Chetoui and M. A. Akhloufi, "Explainable vision transformers and radiomics for COVID-19 detection in chest X-rays," Journal of Clinical Medicine. Vol. 11, No. 11. pp. 1-11. May 2022, DOI: 10.3390/jcm11113013. 
  33. I. Hamdi, M. Ridzuan, and M. Yaqub, "Hyperparameter optimization for COVID-19 chest X-ray classification," arXiv, pp. 1-15, January 2022, DOI: 10.48550/arXiv.2201.10885. 
  34. C. Tian, Y. Xu, L. Fei, J. Wang, Wen, and N. Luo, "Enhanced CNN for image denoising," CAAI Transactions on Intelligence Technology, Vol. 4, No. 1, pp. 17-23, March, 2019, DOI: 10.1049/trit.2018.1054. 
  35. C. Tian, L. Fei, W. Zheng, Y. Xu, W. Zuo, and C. W. Lin, "Deep learning on image denoising: An overview," Neural Networks, Vol. 131, pp. 251-275, November 2020, DOI: 10.1016/j.neunet.2020.07.025. 
  36. W. Vickers, B. Milner, D. Risch, and R. Lee, "Robust North Atlantic Right Whale Detection using Deep Learning Models for Denoising," Journal of the Acoustical Society of America, Vol. 149, No. 6, pp. 3797-3812, June 2021, DOI: 10.1121/10.0005128.