Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey

Low dose computed tomography reconstruction with momentum-based frequency adjustment network

BACKGROUND AND OBJECTIVE

Recent investigations into Low-Dose Computed Tomography (LDCT) reconstruction methods have brought Model-Based Data-Driven (MBDD) approaches to the forefront. One prominent architecture within MBDD entails the integration of Model-Based Iterative Reconstruction (MBIR) with Deep Learning (DL). While this approach offers the advantage of harnessing information from sinogram and image domains, it also reveals several deficiencies. First and foremost, the efficacy of DL methods within the realm of MBDD necessitates meticulous enhancement, as it directly impacts the computational cost and the quality of reconstructed images. Next, high computational costs and a high number of iterations limit the development of MBDD methods. Last but not least, CT reconstruction is sensitive to pixel accuracy, and the role of loss functions within DL methods is crucial for meeting this requirement.

METHODS

This paper advances MBDD methods through three principal contributions. Firstly, we introduce an innovative Frequency Adjustment Network (FAN) that effectively adjusts both high and low-frequency components during the inference phase, resulting in substantial enhancements in reconstruction performance. Second, we develop the Momentum-based Frequency Adjustment Network (MFAN), which leverages momentum terms as an extrapolation strategy to facilitate the amplification of changes throughout successive iterations, culminating in a rapid convergence framework. Lastly, we delve into the visual properties of CT images and present a unique loss function named Focal Detail Loss (FDL). The FDL function preserves fine details throughout the training phase, significantly improving reconstruction quality.

RESULTS

Through a series of experiments validation on the AAPM-Mayo public dataset and real-world piglet datasets, the aforementioned three contributions demonstrated superior performance. MFAN achieved convergence in 10 iterations as an iteration method, faster than other methods. Ablation studies further highlight the advanced performance of each contribution.

CONCLUSIONS

This paper presents an MBDD-based LDCT reconstruction method using a momentum-based frequency adjustment network with a focal detail loss function. This approach significantly reduces the number of iterations required for convergence while achieving superior reconstruction results in visual and numerical analyses.

Dual-Domain Self-Supervised Deep Learning with Graph Convolution for Low-Dose Computed Tomography Reconstruction

X-ray computed tomography (CT) is a commonly used imaging modality in clinical practice. Recent years have seen increasing public concern regarding the ionizing radiation from CT. Low-dose CT (LDCT) has been proven to be effective in reducing patients' radiation exposure, but it results in CT images with low signal-to-noise ratio (SNR), failing to meet the image quality required for diagnosis. To enhance the SNR of LDCT images, numerous denoising strategies based on deep learning have been introduced, leading to notable advancements. Despite these advancements, most methods have relied on a supervised training paradigm. The challenge in acquiring aligned pairs of low-dose and normal-dose images in a clinical setting has limited their applicability. Recently, some self-supervised deep learning methods have enabled denoising using only noisy samples. However, these techniques are based on overly simplistic assumptions about noise and focus solely on CT sinogram denoising or image denoising, compromising their effectiveness. To address this, we introduce the Dual-Domain Self-supervised framework, termed DDoS, to accomplish effective LDCT denoising and reconstruction. The framework includes denoising in the sinogram domain, filtered back-projection reconstruction, and denoising in the image domain. By identifying the statistical characteristics of sinogram noise and CT image noise, we develop sinogram-denoising and CT image-denoising networks that are fully adapted to these characteristics. Both networks utilize a unified hybrid architecture that combines graph convolution and incorporates multiple channel attention modules, facilitating the extraction of local and non-local multi-scale features. Comprehensive experiments on two large-scale LDCT datasets demonstrate the superiority of DDoS framework over existing state-of-the-art methods.

Self-supervised learning for CT image denoising and reconstruction: a review

This article reviews the self-supervised learning methods for CT image denoising and reconstruction. Currently, deep learning has become a dominant tool in medical imaging as well as computer vision. In particular, self-supervised learning approaches have attracted great attention as a technique for learning CT images without clean/noisy references. After briefly reviewing the fundamentals of CT image denoising and reconstruction, we examine the progress of deep learning in CT image denoising and reconstruction. Finally, we focus on the theoretical and methodological evolution of self-supervised learning for image denoising and reconstruction.

[A dual-domain cone beam computed tomography reconstruction framework with improved differentiable domain transform for cone-angle artifact correction]

OBJECTIVE

We propose a dual-domain cone beam computed tomography (CBCT) reconstruction framework DualCBR-Net based on improved differentiable domain transform for cone-angle artifact correction.

METHODS

The proposed CBCT dual-domain reconstruction framework DualCBR-Net consists of 3 individual modules: projection preprocessing, differentiable domain transform, and image post-processing. The projection preprocessing module first extends the original projection data in the row direction to ensure full coverage of the scanned object by X-ray. The differentiable domain transform introduces the FDK reconstruction and forward projection operators to complete the forward and gradient backpropagation processes, where the geometric parameters correspond to the extended data dimension to provide crucial prior information in the forward pass of the network and ensure the accuracy in the gradient backpropagation, thus enabling precise learning of cone-beam region data. The image post-processing module further fine-tunes the domain-transformed image to remove residual artifacts and noises.

RESULTS

The results of validation experiments conducted on Mayo's public chest dataset showed that the proposed DualCBR-Net framework was superior to other comparison methods in terms of artifact removal and structural detail preservation. Compared with the latest methods, the DualCBR-Net framework improved the PSNR and SSIM by 0.6479 and 0.0074, respectively.

CONCLUSION

The proposed DualCBR-Net framework for cone-angle artifact correction allows effective joint training of the CBCT dual-domain network and is especially effective for large cone-angle region.

Re-UNet: a novel multi-scale reverse U-shape network architecture for low-dose CT image reconstruction

In recent years, the growing awareness of public health has brought attention to low-dose computed tomography (LDCT) scans. However, the CT image generated in this way contains a lot of noise or artifacts, which make increasing researchers to investigate methods to enhance image quality. The advancement of deep learning technology has provided researchers with novel approaches to enhance the quality of LDCT images. In the past, numerous studies based on convolutional neural networks (CNN) have yielded remarkable results in LDCT image reconstruction. Nonetheless, they all tend to continue to design new networks based on the fixed network architecture of UNet shape, which also leads to more and more complex networks. In this paper, we proposed a novel network model with a reverse U-shape architecture for the noise reduction in the LDCT image reconstruction task. In the model, we further designed a novel multi-scale feature extractor and edge enhancement module that yields a positive impact on CT images to exhibit strong structural characteristics. Evaluated on a public dataset, the experimental results demonstrate that the proposed model outperforms the compared algorithms based on traditional U-shaped architecture in terms of preserving texture details and reducing noise, as demonstrated by achieving the highest PSNR, SSIM and RMSE value. This study may shed light on the reverse U-shaped network architecture for CT image reconstruction, and could investigate the potential on other medical image processing.

Evidence-based uncertainty-aware semi-supervised medical image segmentation

Semi-Supervised Learning (SSL) has demonstrated great potential to reduce the dependence on a large set of annotated data, which is challenging to collect in clinical practice. One of the most important SSL methods is to generate pseudo labels from the unlabeled data using a network model trained with labeled data, which will inevitably introduce false pseudo labels into the training process and potentially jeopardize performance. To address this issue, uncertainty-aware methods have emerged as a promising solution and have gained considerable attention recently. However, current uncertainty-aware methods usually face the dilemma of balancing the additional computational cost, uncertainty estimation accuracy, and theoretical basis in a unified training paradigm. To address this issue, we propose to integrate the Dempster-Shafer Theory of Evidence (DST) into SSL-based medical image segmentation, dubbed EVidential Inference Learning (EVIL). EVIL performs as a novel consistency regularization-based training paradigm, which enforces consistency on predictions perturbed by two networks with different parameters to enhance generalization Additionally, EVIL provides a theoretically assured solution for precise uncertainty quantification within a single forward pass. By discarding highly unreliable pseudo labels after uncertainty estimation, trustworthy pseudo labels can be generated and incorporated into subsequent model training. The experimental results demonstrate that the proposed approach performs competitively when benchmarked against several state-of-the-art methods on public datasets, i.e., ACDC, MM-WHS, and MonuSeg. The code can be found at https://github.com/CYYukio/EVidential-Inference-Learning.

Systematic Review on Learning-based Spectral CT

Spectral computed tomography (CT) has recently emerged as an advanced version of medical CT and significantly improves conventional (single-energy) CT. Spectral CT has two main forms: dual-energy computed tomography (DECT) and photon-counting computed tomography (PCCT), which offer image improvement, material decomposition, and feature quantification relative to conventional CT. However, the inherent challenges of spectral CT, evidenced by data and image artifacts, remain a bottleneck for clinical applications. To address these problems, machine learning techniques have been widely applied to spectral CT. In this review, we present the state-of-the-art data-driven techniques for spectral CT.

Dynamic Corrected Split Federated Learning With Homomorphic Encryption for U-Shaped Medical Image Networks

U-shaped networks have become prevalent in various medical image tasks such as segmentation, and restoration. However, most existing U-shaped networks rely on centralized learning which raises privacy concerns. To address these issues, federated learning (FL) and split learning (SL) have been proposed. However, achieving a balance between the local computational cost, model privacy, and parallel training remains a challenge. In this articler, we propose a novel hybrid learning paradigm called Dynamic Corrected Split Federated Learning (DC-SFL) for U-shaped medical image networks. To preserve data privacy, including the input, model parameters, label and output simultaneously, we propose to split the network into three parts hosted by different parties. We propose a Dynamic Weight Correction Strategy (DWCS) to stabilize the training process and avoid the model drift problem due to data heterogeneity. To further enhance privacy protection and establish a trustworthy distributed learning paradigm, we propose to introduce additively homomorphic encryption into the aggregation process of client-side model, which helps prevent potential collusion between parties and provides a better privacy guarantee for our proposed method. The proposed DC-SFL is evaluated on various medical image tasks, and the experimental results demonstrate its effectiveness. In comparison with state-of-the-art distributed learning methods, our method achieves competitive performance.

Sparse2Noise: Low-dose synchrotron X-ray tomography without high-quality reference data

BACKGROUND

Synchrotron radiation computed tomography (SR-CT) holds promise for high-resolution in vivo imaging. Notably, the reconstruction of SR-CT images necessitates a large set of data to be captured with sufficient photons from multiple angles, resulting in high radiation dose received by the object. Reducing the number of projections and/or photon flux is a straightforward means to lessen the radiation dose, however, compromises data completeness, thus introducing noises and artifacts. Deep learning (DL)-based supervised methods effectively denoise and remove artifacts, but they heavily depend on high-quality paired data acquired at high doses. Although algorithms exist for training without high-quality references, they struggle to effectively eliminate persistent artifacts present in real-world data.

METHODS

This work presents a novel low-dose imaging strategy namely Sparse2Noise, which combines the reconstruction data from paired sparse-view CT scan (normal-flux) and full-view CT scan (low-flux) using a convolutional neural network (CNN). Sparse2Noise does not require high-quality reconstructed data as references and allows for fresh training on data with very small size. Sparse2Noise was evaluated by both simulated and experimental data.

RESULTS

Sparse2Noise effectively reduces noise and ring artifacts while maintaining high image quality, outperforming state-of-the-art image denoising methods at same dose levels. Furthermore, Sparse2Noise produces impressive high image quality for ex vivo rat hindlimb imaging with the acceptable low radiation dose (i.e., 0.5 Gy with the isotropic voxel size of 26 μm).

CONCLUSIONS

This work represents a significant advance towards in vivo SR-CT imaging. It is noteworthy that Sparse2Noise can also be used for denoising in conventional CT and/or phase-contrast CT.

CAIR: Combining integrated attention with iterative optimization learning for sparse-view CT reconstruction

Sparse-view CT is an efficient way for low dose scanning but degrades image quality. Inspired by the successful use of non-local attention in natural image denoising and compression artifact removal, we proposed a network combining integrated attention and iterative optimization learning for sparse-view CT reconstruction (CAIR). Specifically, we first unrolled the proximal gradient descent into a deep network and added an enhanced initializer between the gradient term and the approximation term. It can enhance the information flow between different layers, fully preserve the image details, and improve the network convergence speed. Secondly, the integrated attention module was introduced into the reconstruction process as a regularization term. It adaptively fuses the local and non-local features of the image which are used to reconstruct the complex texture and repetitive details of the image, respectively. Note that we innovatively designed a one-shot iteration strategy to simplify the network structure and reduce the reconstruction time while maintaining image quality. Experiments showed that the proposed method is very robust and outperforms state-of-the-art methods in terms of both quantitative and qualitative, greatly improving the preservation of structures and the removal of artifacts.