Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison

Various types of noise may affect the visual quality of images during capturing and transmitting procedures. Finding a proper technique to remove the possible noise and improve both quantitative and qualitative results is always considered as one of the most important and challenging pre-processing tasks in image and signal processing. In this paper, we made a short comparison between two well-known approaches called thresholding neural network (TNN) and deep neural network (DNN) based methods for image de-noising. De-noising results of TNNs, Dn-CNNs, Flashlight CNN (FLCNN) and Diamond de-noising networks (DmDN) have been compared with each other. In this regard, several experiments have been performed in terms of Peak Signal to Noise Ratio (PSNR) to validate the performance analysis of various de-noising methods. The analysis indicates that DmDNs perform better than other learning-based algorithms for de-noising brain MR images. DmDN achieved a PSNR value of 29.85 dB, 30.74 dB, 29.15 dB, and 29.45 dB for de-noising MR image 1, MR image 2, MR image 3 and MR Image 4, respectively for a standard deviation of 15.

@article{Rahimi2024,
  title     = {Deep Neural Network-based Methods for Brain Image De-noising: A Short Comparison},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {15},
  number    = {2},
  year      = {2024},
  publisher = {The Science and Information Organization},
  author    = {Keyan Rahimi and Noorbakhsh Amiri Golilarz},
  doi       = {10.14569/IJACSA.2024.0150201},
  url       = {https://doi.org/10.14569/IJACSA.2024.0150201}
}