RESUMO
BACKGROUND: Dynamic positron emission tomography (PET) images are useful in clinical practice because they can be used to calculate the metabolic parameters (Ki) of tissues using graphical methods (such as Patlak plots). Ki is more stable than the standard uptake value and has a good reference value for clinical diagnosis. However, the long scanning time required for obtaining dynamic PET images, usually an hour, makes this method less useful in some ways. There is a tradeoff between the scan durations and the signal-to-noise ratios (SNRs) of Ki images. The purpose of our study is to obtain approximately the same image as that produced by scanning for one hour in just half an hour, improving the SNRs of images obtained by scanning for 30 min and reducing the necessary 1-h scanning time for acquiring dynamic PET images. METHODS: In this paper, we use U-Net as a feature extractor to obtain feature vectors with a priori knowledge about the image structure of interest and then utilize a parameter generator to obtain five parameters for a two-tissue, three-compartment model and generate a time activity curve (TAC), which will become close to the original 1-h TAC through training. The above-generated dynamic PET image finally obtains the Ki parameter image. RESULTS: A quantitative analysis showed that the network-generated Ki parameter maps improved the structural similarity index measure and peak SNR by averages of 2.27% and 7.04%, respectively, and decreased the root mean square error (RMSE) by 16.3% compared to those generated with a scan time of 30 min. CONCLUSIONS: The proposed method is feasible, and satisfactory PET quantification accuracy can be achieved using the proposed deep learning method. Further clinical validation is needed before implementing this approach in routine clinical applications.
RESUMO
Background: Computed tomography (CT) is now universally applied into clinical practice with its non-invasive quality and reliability for lesion detection, which highly improves the diagnostic accuracy of patients with systemic diseases. Although low-dose CT reduces X-ray radiation dose and harm to the human body, it inevitably produces noise and artifacts that are detrimental to information acquisition and medical diagnosis for CT images. Methods: This paper proposes a Wasserstein generative adversarial network (WGAN) with a convolutional block attention module (CBAM) to realize a method of directly synthesizing high-energy CT (HECT) images through low-energy scanning, which greatly reduces X-ray radiation from high-energy scanning. Specifically, our proposed generator structure in WGAN consists of Visual Geometry Group Network (Vgg16), 9 residual blocks, upsampling and CBAM, a subsequent attention block. The convolutional block attention module is integrated into the generator for improving the denoising ability of the network as verified by our ablation comparison experiments. Results: Experimental results of the generator attention module ablation comparison indicate an optimization boost to the overall generator model, obtaining the synthesized high-energy CT with the best metric and denoising effect. In different methods comparison experiments, it can be clearly observed that our proposed method is superior in the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and most of the statistics (average CT value and its standard deviation) compared to other methods. Because P<0.05, the samples are significantly different. The data distribution at the pixel level between the images synthesized by the method in this paper and the high-energy CT images is also most similar. Conclusions: Experimental results indicate that CBAM is able to suppress the noise and artifacts effectively and suggest that the image synthesized by the proposed method is closest to the high-energy CT image in terms of visual perception and objective evaluation metrics.