A cross-type multi-dimensional network based on feature enhancement and triple interactive attention for LDCT denoising

BackgroundNumerous deep leaning methods for low-dose computed technology (CT) image denoising have been proposed, achieving impressive results. However, issues such as loss of structure and edge information and low denoising efficiency still exist.ObjectiveTo improve image denoising quality, an enhanced multi-dimensional hybrid attention LDCT image denoising network based on edge detection is proposed in this paper.MethodsIn our network, we employ a trainable Sobel convolution to design an edge enhancement module and fuse an enhanced triplet attention network (ETAN) after each <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mn>3</mml:mn><mml:mo>×</mml:mo><mml:mn>3</mml:mn></mml:math> convolutional layer to extract richer features more comprehensively and suppress useless information. During the training process, we adopt a strategy that combines total variation loss (TVLoss) with mean squared error (MSE) loss to reduce high-frequency artifacts in image reconstruction and balance image denoising and detail preservation.ResultsCompared with other advanced algorithms (CT-former, REDCNN and EDCNN), our proposed model achieves the best PSNR and SSIM values in CT image of the abdomen, which are 34.8211and 0.9131, respectively.ConclusionThrough comparative experiments with other related algorithms, it can be seen that the algorithm proposed in this article has achieved significant improvements in both subjective vision and objective indicators.