Department of Nuclear Medicine, All India Institute of Medical Sciences.
Maulana Azad Medical College.
Nucl Med Commun. 2023 Aug 1;44(8):682-690. doi: 10.1097/MNM.0000000000001712. Epub 2023 Jun 5.
A DnCNN for image denoising trained with natural images is available in MATLAB. For Tc-99m DMSA images, any loss of clinical details during the denoising process will have serious consequences since denoised image is to be used for diagnosis. The objective of the study was to find whether this pre-trained DnCNN can be used for denoising Tc-99m DMSA images and compare its performance with block matching 3D (BM3D) filter.
Two hundred forty-two Tc-99m DMSA images were denoised using BM3D filter (at sigma = 5, 10, 15, 20, and 25) and DnCNN. The original and denoised images were reviewed by two nuclear medicine physicians and also assessed objectively using the image quality metrics: SSIM, FSIM, MultiSSIM, PIQE, Blur, GCF, and Brightness. Wilcoxon signed-rank test was applied to find the statistically significant difference between the value of image quality metrics of the denoised images and the corresponding original images.
Nuclear medicine physicians observed no loss of clinical information in DnCNN denoised image and superior image quality compared to its original and BM3D denoised images. Edges/boundaries of the scar were found to be well preserved, and doubtful scar became obvious in the denoised image. Objective assessment also showed that the quality of DnCNN denoised images was significantly better than that of original images at P -value <0.0001.
The pre-trained DnCNN available with MATLAB Deep Learning Toolbox can be used for denoising Tc-99m DMSA images, and the performance of DnCNN was found to be superior in comparison with BM3D filter.
MATLAB 中提供了一种使用自然图像训练的 DnCNN 用于图像去噪。对于 Tc-99m DMSA 图像，由于去噪后的图像将用于诊断，因此在去噪过程中任何临床细节的丢失都将产生严重后果。本研究的目的是确定这种预训练的 DnCNN 是否可用于去噪 Tc-99m DMSA 图像，并将其性能与块匹配 3D（BM3D）滤波器进行比较。
使用 BM3D 滤波器（sigma = 5、10、15、20 和 25）和 DnCNN 对 242 张 Tc-99m DMSA 图像进行去噪。两位核医学医师对原始图像和去噪图像进行了审查，并使用图像质量指标（SSIM、FSIM、MultiSSIM、PIQE、Blur、GCF 和 Brightness）进行了客观评估。应用 Wilcoxon 符号秩检验来发现去噪图像的图像质量指标值与相应原始图像值之间的统计学显著差异。
核医学医师观察到 DnCNN 去噪图像没有丢失临床信息，并且与原始图像和 BM3D 去噪图像相比具有更好的图像质量。发现疤痕的边缘/边界得到了很好的保留，并且在去噪图像中可疑的疤痕变得明显。客观评估还表明，DnCNN 去噪图像的质量明显优于原始图像，P 值<0.0001。
MATLAB 深度学习工具箱中提供的预训练 DnCNN 可用于 Tc-99m DMSA 图像去噪，并且与 BM3D 滤波器相比，DnCNN 的性能更优。
