Deep learning enabled ultra-fast-pitch acquisition in clinical X-ray computed tomography

STEDNet: Swin transformer-based encoder-decoder network for noise reduction in low-dose CT

BACKGROUND

Low-dose computed tomography (LDCT) can reduce the dose of X-ray radiation, making it increasingly significant for routine clinical diagnosis and treatment planning. However, the noise introduced by low-dose X-ray exposure degrades the quality of CT images, affecting the accuracy of clinical diagnosis. Purpose The noises, artifacts, and high-frequency components are similarly distributed in LDCT images. Transformer can capture global context information in an attentional manner to create distant dependencies on targets and extract more powerful features. In this paper, we reduce the impact of image errors on the ability to retain detailed information and improve the noise suppression performance by fully mining the distribution characteristics of image information.

METHODS

This paper proposed an LDCT noise and artifact suppressing network based on Swin Transformer. The network includes a noise extraction sub-network and a noise removal sub-network. The noise extraction and removal capability are improved using a coarse extraction network of high-frequency features based on full convolution. The noise removal sub-network improves the network's ability to extract relevant image features by using a Swin Transformer with a shift window as an encoder-decoder and skip connections for global feature fusion. Also, the perceptual field is extended by extracting multi-scale features of the images to recover the spatial resolution of the feature maps. The network uses a loss constraint with a combination of L1 and MS-SSIM to improve and ensure the stability and denoising effect of the network.

RESULTS

The denoising ability and clinical applicability of the methods were tested using clinical datasets. Compared with DnCNN, RED-CNN, CBDNet and TSCN, the STEDNet method shows a better denoising effect on RMSE and PSNR. The STEDNet method effectively removes image noise and preserves the image structure to the maximum extent, making the reconstructed image closest to the NDCT image. The subjective and objective analysis of several sets of experiments shows that the method in this paper can effectively maintain the structure, edges, and textures of the denoised images while having good noise suppression performance. In the real data evaluation, the RMSE of this method is reduced by 18.82%, 15.15%, 2.25%, and 1.10% on average compared with DnCNN, RED-CNN, CBDNet, and TSCNN, respectively. The average improvement of PSNR is 9.53%, 7.33%, 2.65%, and 3.69%, respectively.

CONCLUSIONS

This paper proposed a LDCT image denoising algorithm based on end-to-end training. The method in this paper can effectively improve the diagnostic performance of CT images by constraining the details of the images and restoring the LDCT image structure. The problem of increased noise and artifacts in CT images can be solved while maintaining the integrity of CT image tissue structure and pathological information. Compared with other algorithms, this method has better denoising effects both quantitatively and qualitatively.

Origins of and lessons from quantitative functional X-ray computed tomography of the lung

Functional CT of the lung has emerged from quantitative CT (qCT). Structural details extracted at multiple lung volumes offer indices of function. Additionally, single volumetric images, if acquired at standardized lung volumes and body posture, can be used to model function by employing such engineering techniques as computational fluid dynamics. With the emergence of multispectral CT imaging including dual energy from energy integrating CT scanners and multienergy binning using the newly released photon counting CT technology, function is tagged via use of contrast agents. Lung disease phenotypes have previously been lumped together by the limitations of spirometry and plethysmography. QCT and its functional embodiment have been imbedded into studies seeking to characterize chronic obstructive pulmonary disease, severe asthma, interstitial lung disease and more. Reductions in radiation dose by an order of magnitude or more have been achieved. At the same time, we have seen significant increases in spatial and density resolution along with methodologic validations of extracted metrics. Together, these have allowed attention to turn towards more mild forms of disease and younger populations. In early applications, clinical CT offered anatomic details of the lung. Functional CT offers regional measures of lung mechanics, the assessment of functional small airways disease, as well as regional ventilation-perfusion matching (V/Q) and more. This paper will focus on the use of quantitative/functional CT for the non-invasive exploration of dynamic three-dimensional functioning of the breathing lung and beating heart within the unique negative pressure intrathoracic environment of the closed chest.

Improving coronary artery imaging in single source CT with cardiac motion correction using attention and spatial transformer based neural networks

Motion artifact is a major challenge in cardiac CT which hampers accurate delineation of key anatomic (e.g. coronary lumen) and pathological features (e.g. stenosis). Conventional motion correction techniques are limited on patients with high / irregular heart rate, due to simplified modeling of CT systems and cardiac motion. Emerging deep learning based cardiac motion correction techniques have demonstrated the potential of further quality improvement. Yet, many methods require CT projection data or advanced motion simulation tools that are not readily available. We aim to develop an image-domain motion-correction method, using convolutional neural network (CNN) integrated with customized attention and spatial transformer techniques. Forty cardiac CT exams acquired from a clinical dual-source CT system were retrospectively collected to generate training (n=26) and testing (n=14) sets. Dual-source data uniquely allow image reconstruction with different temporal resolutions from the same patient scan. Slow temporal resolution (140ms; equivalent to single-source CT (SSCT) half scan) and fast temporal resolution (75ms; dual source) images were reconstructed to generate paired samples of motion-corrupted and reference images. The combinations of 2 training-inference strategies and 3 CNNs were evaluated: strategy #1 - whole-heart images in training / inference; strategy #2 - vessel patches in training / inference; CNN #1 - attention only; CNN #2 - spatial-transformer (STN) only; CNN #3 - attention & STN synergy. Testing data showed that CNN #3 with strategy #2 provided relatively better performance: improving vessel delineation, increasing structural similarity index from 0.85 to 0.91, and reducing mean CT number error of lumen by 71.0%. Our method could improve the image quality in cardiac exams with SSCT.