CNLNet Enhancing MRI Brain Image Denoising Using a Convolutional Neural Network with Integrated Non-Local Means Layer - Figure 3
Authors/Creators
- 1. Karunya Institute of Technology and Sciences
- 2. Samara State Medical University
Description
The dataset consists of 3,072 MRI brain images sourced from a publicly accessible Kaggle
dataset at https://www.kaggle.com/datasets/abhranta/brain-tumor-detection-mri. Images were
resized to a uniform resolution of 128×128×3 and normalised to the range [0, 1] for consistent
scaling and improved convergence during training. To construct noisy-clean image pairs, 3 SD of
Gaussian noise (0.1, 0.3, and 0.5) were applied. Figure 3 displays sample images of clean and noisy
images with SD of 0.1, 0.3, and 0.5, respectively.
Notes
Files
CNLNet Enhancing MRI Brain Image Denoising Using a Convolutional Neural Network with Integrated Non-Local Means Layer - Figure 3.png
Files
(443.5 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:1618706cdb3206fd80202cca87cf957f
|
443.5 kB | Preview Download |