A cycle generative adversarial network for improving the quality of four-dimensional cone-beam computed tomography images.

BACKGROUND: Four-dimensional cone-beam computed tomography (4D-CBCT) can visualize moving tumors, thus adaptive radiation therapy (ART) could be improved if 4D-CBCT were used. However, 4D-CBCT images suffer from severe imaging artifacts. The aim of this study is to investigate the use of synthetic 4D-CBCT (sCT) images created by a cycle generative adversarial network (CycleGAN) for ART for lung cancer. METHODS: Unpaired thoracic 4D-CBCT images and four-dimensional multislice computed tomography (4D-MSCT) images of 20 lung-cancer patients were used for training. High-quality sCT lung images generated by the CycleGAN model were tested on another 10 cases. The mean and mean absolute errors were calculated to assess changes in the computed tomography number. The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) were used to compare the sCT and original 4D-CBCT images. Moreover, a volumetric modulation arc therapy plan with a dose of 48 Gy in four fractions was recalculated using the sCT images and compared with ideal dose distributions observed in 4D-MSCT images. RESULTS: The generated sCT images had fewer artifacts, and lung tumor regions were clearly observed in the sCT images. The mean and mean absolute errors were near 0 Hounsfield units in all organ regions. The SSIM and PSNR results were significantly improved in the sCT images by approximately 51% and 18%, respectively. Moreover, the results of gamma analysis were significantly improved; the pass rate reached over 90% in the doses recalculated using the sCT images. Moreover, each organ dose index of the sCT images agreed well with those of the 4D-MSCT images and were within approximately 5%. CONCLUSIONS: The proposed CycleGAN enhances the quality of 4D-CBCT images, making them comparable to 4D-MSCT images. Thus, clinical implementation of sCT-based ART for lung cancer is feasible.

Quantitative evaluation of deep convolutional neural network-based image denoising for low-dose computed tomography.

To minimize radiation risk, dose reduction is important in the diagnostic and therapeutic applications of computed tomography (CT). However, image noise degrades image quality owing to the reduced X-ray dose and a possible unacceptably reduced diagnostic performance. Deep learning approaches with convolutional neural networks (CNNs) have been proposed for natural image denoising; however, these approaches might introduce image blurring or loss of original gradients. The aim of this study was to compare the dose-dependent properties of a CNN-based denoising method for low-dose CT with those of other noise-reduction methods on unique CT noise-simulation images. To simulate a low-dose CT image, a Poisson noise distribution was introduced to normal-dose images while convoluting the CT unit-specific modulation transfer function. An abdominal CT of 100 images obtained from a public database was adopted, and simulated dose-reduction images were created from the original dose at equal 10-step dose-reduction intervals with a final dose of 1/100. These images were denoised using the denoising network structure of CNN (DnCNN) as the general CNN model and for transfer learning. To evaluate the image quality, image similarities determined by the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) were calculated for the denoised images. Significantly better denoising, in terms of SSIM and PSNR, was achieved by the DnCNN than by other image denoising methods, especially at the ultra-low-dose levels used to generate the 10% and 5% dose-equivalent images. Moreover, the developed CNN model can eliminate noise and maintain image sharpness at these dose levels and improve SSIM by approximately 10% from that of the original method. In contrast, under small dose-reduction conditions, this model also led to excessive smoothing of the images. In quantitative evaluations, the CNN denoising method improved the low-dose CT and prevented over-smoothing by tailoring the CNN model.

Intravenous contrast agent influence on thoracic computed tomography simulation investigated through a heterogeneous dose calculation method using 5-bulk densities.

OBJECTIVE: Using 5-bulk-density heterogeneous dose calculation, we investigated whether contrast-enhanced (CE+) computed tomography (CT) will affect dose-calculation accuracy in the thoracic area. METHODS: We analyzed 17 radiation-oncology patients who underwent thoracic CE+ CTs. Full-resolution CT and 5-bulk-density plans were generated using an adaptive convolution algorithm. Bulk densities for air, lung, fat, soft tissue, and bone were applied to regions identified by an isodensity segmentation tool. The population-averaged physical density of each region was calculated and compared with the reference value calculated from 66 noncontrast-enhanced (CE-) thoracic CT images. Using the 5-bulk densities, we created a new plan in which the physical densities of each area were forced to be the same as the CE- reference value, and we compared the dose-volume histograms (DVH). RESULTS: Average physical density for the segmented air, lung, fat, soft tissue, and bone for CE+ were 0.14, 0.29, 0.90, 1.03, and 1.13 g/cm(3), and the reference values for CE- were 0.14, 0.26, 0.89, 1.02, and 1.12 g/cm(3), respectively. In all the cases, the normal-tissue DVH agreed to better than 1%. In 15 cases, DVH of the planning target volume (PTV) agreed to better than 3%. In 2 patients, >3% difference in the PTV dose was observed. CONCLUSIONS: Only 2 patients with a strong injection artifact in the PTV or beam showed >3% discrepancy in the target dose. When using CE+ CT for treatment planning, strong injection artifacts must be excluded.

Posterior hypoperfusion in Parkinson's disease with and without dementia measured with arterial spin labeling MRI.

PURPOSE: To determine whether quantitative arterial spin labeling (ASL) can be used to evaluate regional cerebral blood flow in Parkinson's disease with dementia (PDD) and without dementia (PD). MATERIALS AND METHODS: Thirty-five PD patients, 11 PDD patients, and 35 normal controls were scanned by using a quantitative ASL method with a 3 Tesla MRI unit. Regional cerebral blood flow was compared in the posterior cortex using region-of-interest analysis. RESULTS: PD and PDD patients showed lower regional cerebral blood flow in the posterior cortex than normal controls (P = 0.002 and P = 0.001, respectively, analysis of variance with a Bonferroni post hoc test). CONCLUSION: This is the first study to detect hypoperfusion in the posterior cortex in PD and PDD patients using ASL perfusion MRI. Because ASL perfusion MRI is completely noninvasive and can, therefore, safely be used for repeated assessments, this method can be used to monitor treatment effects or disease progression in PD.