General simultaneous motion estimation and image reconstruction (G-SMEIR)

Spatiotemporal denoising of low-dose cardiac CT image sequences using RecycleGAN

Electrocardiogram (ECG)-gated multi-phase computed tomography angiography (MP-CTA) is frequently used for diagnosis of coronary artery disease. Radiation dose may become a potential concern as the scan needs to cover a wide range of cardiac phases during a heart cycle. A common method to reduce radiation is to limit the full-dose acquisition to a predefined range of phases while reducing the radiation dose for the rest. Our goal in this study is to develop a spatiotemporal deep learning method to enhance the quality of low-dose CTA images at phases acquired at reduced radiation dose. Recently, we demonstrated that a deep learning method, Cycle-Consistent generative adversarial networks (CycleGAN), could effectively denoise low-dose CT images through spatial image translation without labeled image pairs in both low-dose and full-dose image domains. As CycleGAN does not utilize the temporal information in its denoising mechanism, we propose to use RecycleGAN, which could translate a series of images ordered in time from the low-dose domain to the full-dose domain through an additional recurrent network. To evaluate RecycleGAN, we use the XCAT phantom program, a highly realistic simulation tool based on real patient data, to generate MP-CTA image sequences for 18 patients (14 for training, 2 for validation and 2 for test). Our simulation results show that RecycleGAN can achieve better denoising performance than CycleGAN based on both visual inspection and quantitative metrics. We further demonstrate the superior denoising performance of RecycleGAN using clinical MP-CTA images from 50 patients.

Texture transformer super-resolution for low-dose computed tomography

Computed tomography (CT) is widely used to diagnose many diseases. Low-dose CT has been actively pursued to lower the ionizing radiation risk. A relatively smoother kernel is typically used in low-dose CT to suppress image noise, which may sacrifice spatial resolution. In this work, we propose a texture transformer network to simultaneously reduce image noise and improve spatial resolution in CT images. This network, referred to as Texture Transformer for Super Resolution (TTSR), is a reference-based deep-learning image super-resolution method built upon a generative adversarial network (GAN). The noisy low-resolution CT (LRCT) image and the routine-dose high-resolution (HRCT) image are severed as the query and key in a transformer, respectively. Image translation is optimized through deep neural network (DNN) texture extraction, correlation embedding, and attention-based texture transfer and synthesis to achieve joint feature learning between LRCT and HRCT images for super-resolution CT (SRCT) images. To evaluate SRCT performance, we use the data from both simulations of the XCAT phantom program and the real patient data. Peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and feature similarity (FSIM) index are used as quantitative metrics. For comparison of SRCT performance, the cubic spline interpolation, SRGAN (a GAN super-resolution with an additional content loss), and GAN-CIRCLE (a GAN super-resolution with cycle consistency) were used. Compared to the other two methods, TTSR can restore more details in SRCT images and achieve better PSNR, SSIM, and FSIM for both simulation and real-patient data. In addition, we show that TTSR can yield better image quality and demand much less computation time than high-resolution low-dose CT images denoised by block-matching and 3D filtering (BM3D) and GAN-CIRCLE. In summary, the proposed TTSR method based on texture transformer and attention mechanism provides an effective and efficient tool to improve spatial resolution and suppress noise of low-dose CT images.

Reducing 4DCBCT imaging dose and time: exploring the limits of adaptive acquisition and motion compensated reconstruction

This study investigates the dose and time limits of adaptive 4DCBCT acquisitions (adaptive-acquisition) compared with current conventional 4DCBCT acquisition (conventional-acquisition). We investigate adaptive-acquisitions as low as 60 projections (∼25 s scan, 6 projections per respiratory phase) in conjunction with emerging image reconstruction methods. 4DCBCT images from 20 patients recruited into the adaptive CT acquisition for personalized thoracic imaging clinical study (NCT04070586) were resampled to simulate faster and lower imaging dose acquisitions. All acquisitions were reconstructed using Feldkamp–Davis–Kress (FDK), McKinnon–Bates (MKB), motion compensated FDK (MCFDK), motion compensated MKB (MCMKB) and simultaneous motion estimation and image reconstruction (SMEIR) algorithms. All reconstructions were compared against conventional-acquisition 4DFDK-reconstruction using Structural SIMilarity Index (SSIM), signal-to-noise ratio (SNR), contrast-to-noise-ratio (CNR), tissue interface sharpness diaphragm (TIS-D), tissue interface sharpness tumor (TIS-T) and center of mass trajectory (COMT) for difference in diaphragm and tumor motion. All reconstruction methods using 110-projection adaptive-acquisition (11 projections per respiratory phase) had a SSIM of greater than 0.92 relative to conventional-acquisition 4DFDK-reconstruction. Relative to conventional-acquisition 4DFDK-reconstruction, 110-projection adaptive-acquisition MCFDK-reconstructions images had 60% higher SNR, 10% higher CNR, 30% higher TIS-T and 45% higher TIS-D on average. The 110-projection adaptive-acquisition SMEIR-reconstruction images had 123% higher SNR, 90% higher CNR, 96% higher TIS-T and 60% higher TIS-D on average. The difference in diaphragm and tumor motion compared to conventional-acquisition 4DFDK-reconstruction was within submillimeter accuracy for all acquisition reconstruction methods. Adaptive-acquisitions resulted in faster scans with lower imaging dose and equivalent or improved image quality compared to conventional-acquisition. Adaptive-acquisition with motion compensated-reconstruction enabled scans with as low as 110 projections to deliver acceptable image quality. This translates into 92% lower imaging dose and 80% less scan time than conventional-acquisition.

Projection-based dynamic tomography

Objective. This paper proposes a 4D dynamic tomography framework that allows a moving sample to be imaged in a tomograph as well as the associated space-time kinematics to be measured with nothing more than a single conventional x-ray scan.Approach. The method exploits the consistency of the projection/reconstruction operations through a multi-scale procedure. The procedure is composed of two main parts solved alternatively: a motion-compensated reconstruction algorithm and a projection-based measurement procedure that estimates the displacement field directly on each projection.Main results. The method is applied to two studies: a numerical simulation of breathing from chest computed tomography (4D-CT) and a clinical cone-beam CT of a breathing patient acquired for image guidance of radiotherapy. The reconstructed volume, initially blurred by the motion, is cleaned from motion artifacts.Significance. Applying the proposed approach results in an improved reconstruction quality showing sharper edges and finer details.