Super Resolution of Pulmonary Nodules Target Reconstruction Using a Two-Channel GAN Models

•We employed a cascading approach of two 2D networks to achieve the functionality of 3D image pulmonary nodules super-resolution target reconstruction of CT among three axes.•We used a pre-trained model for mapping from normal-resolution CT images to high-resolution CT images, which enhanced the stability and convergence speed of super-resolution results.•In addition to the evaluation of the images, we also used relevant diagnostic indicators, which makes our results more valuable for clinical application. Rationale and ObjectivesTo develop a Dual generative-adversarial-network (GAN) Cascaded Network (DGCN) for generating super-resolution computed tomography (SRCT) images from normal-resolution CT (NRCT) images and evaluate the performance of DGCN in multi-center datasets.Materials and MethodsThis retrospective study included 278 patients with chest CT from two hospitals between January 2020 and June 2023, and each patient had all three NRCT (512 × 512 matrix CT images with a resolution of 0.70 mm, 0.70 mm,1.0 mm), high-resolution CT (HRCT, 1024 × 1024 matrix CT images with a resolution of 0.35 mm, 0.35 mm,1.0 mm), and ultra-high-resolution CT (UHRCT, 1024 × 1024 matrix CT images with a resolution of 0.17 mm, 0.17 mm, 0.5 mm) examinations. Initially, a deep chest CT super-resolution residual network (DCRN) was built to generate HRCT from NRCT. Subsequently, we employed the DCRN as a pre-trained model for the training of DGCN to further enhance resolution along all three axes, ultimately yielding SRCT. PSNR, SSIM, FID, subjective evaluation scores, and objective evaluation parameters related to pulmonary nodule segmentation in the testing set were recorded and analyzed.ResultsDCRN obtained a PSNR of 52.16, SSIM of 0.9941, FID of 137.713, and an average diameter difference of 0.0981 mm. DGCN obtained a PSNR of 46.50, SSIM of 0.9990, FID of 166.421, and an average diameter difference of 0.0981 mm on 39 testing cases. There were no significant differences between the SRCT and UHRCT images in subjective evaluation.ConclusionOur model exhibited a significant enhancement in generating HRCT and SRCT images and outperformed established methods regarding image quality and clinical segmentation accuracy across both internal and external testing datasets. To develop a Dual generative-adversarial-network (GAN) Cascaded Network (DGCN) for generating super-resolution computed tomography (SRCT) images from normal-resolution CT (NRCT) images and evaluate the performance of DGCN in multi-center datasets. This retrospective study included 278 patients with chest CT from two hospitals between January 2020 and June 2023, and each patient had all three NRCT (512 × 512 matrix CT images with a resolution of 0.70 mm, 0.70 mm,1.0 mm), high-resolution CT (HRCT, 1024 × 1024 matrix CT images with a resolution of 0.35 mm, 0.35 mm,1.0 mm), and ultra-high-resolution CT (UHRCT, 1024 × 1024 matrix CT images with a resolution of 0.17 mm, 0.17 mm, 0.5 mm) examinations. Initially, a deep chest CT super-resolution residual network (DCRN) was built to generate HRCT from NRCT. Subsequently, we employed the DCRN as a pre-trained model for the training of DGCN to further enhance resolution along all three axes, ultimately yielding SRCT. PSNR, SSIM, FID, subjective evaluation scores, and objective evaluation parameters related to pulmonary nodule segmentation in the testing set were recorded and analyzed. DCRN obtained a PSNR of 52.16, SSIM of 0.9941, FID of 137.713, and an average diameter difference of 0.0981 mm. DGCN obtained a PSNR of 46.50, SSIM of 0.9990, FID of 166.421, and an average diameter difference of 0.0981 mm on 39 testing cases. There were no significant differences between the SRCT and UHRCT images in subjective evaluation. Our model exhibited a significant enhancement in generating HRCT and SRCT images and outperformed established methods regarding image quality and clinical segmentation accuracy across both internal and external testing datasets.