Objective. Low-dose computed tomography (LDCT) denoising is an important problem in CT research. Compared to the normal dose CT, LDCT images are subjected to severe noise and artifacts. Recently in many studies, vision transformers have shown superior feature representation ability over the convolutional neural networks (CNNs). However, unlike CNNs, the potential of vision transformers in LDCT denoising was little explored so far. Our paper aims to further explore the power of transformer for the LDCT denoising problem. Approach. In this paper, we propose a Convolution-free Token2Token Dilated Vision Transformer (CTformer) for LDCT denoising. The CTformer uses a more powerful token rearrangement to encompass local contextual information and thus avoids convolution. It also dilates and shifts feature maps to capture longer-range interaction. We interpret the CTformer by statically inspecting patterns of its internal attention maps and dynamically tracing the hierarchical attention flow with an explanatory graph. Furthermore, overlapped inference mechanism is employed to effectively eliminate the boundary artifacts that are common for encoder-decoder-based denoising models. Main results. Experimental results on Mayo dataset suggest that the CTformer outperforms the state-of-the-art denoising methods with a low computational overhead. Significance. The proposed model delivers excellent denoising performance on LDCT. Moreover, low computational cost and interpretability make the CTformer promising for clinical applications.
Cardiac computed tomography (CT) has emerged as a major imaging modality for the diagnosis and monitoring of cardiovascular diseases. High temporal resolution is essential to ensure diagnostic accuracy. Limited-angle data acquisition can reduce scan time and improve temporal resolution, but typically leads to severe image degradation and motivates for improved reconstruction techniques. In this paper, we propose a novel physics-informed score-based diffusion model (PSDM) for limited-angle reconstruction of cardiac CT. At the sampling time, we combine a data prior from a diffusion model and a model prior obtained via an iterative algorithm and Fourier fusion to further enhance the image quality. Specifically, our approach integrates the primal-dual hybrid gradient (PDHG) algorithm with score-based diffusion models, thereby enabling us to reconstruct high-quality cardiac CT images from limited-angle data. The numerical simulations and real data experiments confirm the effectiveness of our proposed approach.
15 November 2021 in IEEE Transactions on Artificial Intelligence
In established network architectures, shortcut connections are often used to take the outputs of earlier layers as additional inputs to later layers. Despite the extraordinary effectiveness of shortcuts, there remain open questions on the mechanism and characteristics. For example, why are shortcuts powerful? Why do shortcuts generalize well? In this article, we investigate the expressivity and generalizability of a novel sparse shortcut topology. First, we demonstrate that this topology can empower a one-neuron-wide deep network to approximate any univariate continuous function. Then, we present a novel width-bounded universal approximator in contrast to depth-bounded universal approximators and extend the approximation result to a family of equally competent networks. Furthermore, with generalization bound theory, we show that the proposed shortcut topology enjoys excellent generalizability. Finally, we corroborate our theoretical analyses by comparing the proposed topology with popular architectures, including ResNet and DenseNet, on well-known benchmarks and perform a saliency map analysis to interpret the proposed topology. Our work helps understand the role of shortcuts and suggests further opportunities to innovate neural architectures.
6 November 2023 in IEEE Transactions on Instrumentation and Measurement
Due to the potential harmful risks caused by the excessive X-ray radiation dose, low-dose has emerged as one of the major rules of computed tomography (CT) for clinical applications. However, reducing radiation dose severely leads to degraded reconstructed CT image quality with noises and artifacts, and it may seriously hamper clinical diagnosis. Currently, model-driven deep learning (DL)-based dual-domain learning with the expert knowledge can reconstruct CT images from projections acquired in non-ideal conditions, and they have been demonstrated with inspired performance in Low-dose CT (LDCT) reconstruction. However, because of domain-progressive strategy, these dual-domain methods are prone to produce seriously secondary artifacts and suffer from subtle structural degeneration. In this paper, we propose a novel deep dual-domain united guiding learning framework, i.e., DUGL-Net. First, we put forward a domain-guiding strategy. The projection-domain network plays the guiding role on image-domain network to effectively enhance overall network stability and powerfully avoid secondary artifacts. Second, we elaborately design a Global-Local Transformer-Convolution U-Net, i.e., GL-TCUNet, as the base network in both projection-domain and image-domain for reinforcing dual-domain model learning. This efficiently leverage the advantages of Swin Transformer and CNN to suppress noises and artifacts. Finally, the proposed DUGL-Net is evaluated on the 2016 NIH- AAPM-Mayo clinic LDCT Grand Challenge dataset and real data, and our results validate that the proposed method outperforms the state-of-the-art competing methods. This efficient, accurate, and reliable LDCT denoising technique has a great potential for clinical applications.
5 September 2024 in IEEE Journal of Biomedical and Health Informatics
Low-dose computed tomography (LDCT) offers reduced X-ray radiation exposure but at the cost of compromised image quality, characterized by increased noise and artifacts. Recently, transformer models emerged as a promising avenue to enhance LDCT image quality. However, the success of such models relies on a large amount of paired noisy and clean images, which are often scarce in clinical settings. In computer vision and natural language processing, masked autoencoders (MAE) have been recognized as a powerful self-pretraining method for transformers, due to their exceptional capability to extract representative features. However, the original pretraining and fine-tuning design fails to work in low-level vision tasks like denoising. In response to this challenge, we redesign the classical encoder-decoder learning model and facilitate a simple yet effective streamlined low-level vision MAE, referred to as LoMAE, tailored to address the LDCT denoising problem. Moreover, we introduce an MAE-GradCAM method to shed light on the latent learning mechanisms of the MAE/LoMAE. Additionally, we explore the LoMAE's robustness and generability across a variety of noise levels. Experimental findings show that the proposed LoMAE enhances the denoising capabilities of the transformer and substantially reduce their dependency on high-quality, ground-truth data. It also demonstrates remarkable robustness and generalizability over a spectrum of noise levels. In summary, the proposed LoMAE provides promising solutions to the major issues in LDCT including interpretability, ground truth data dependency, and model robustness/generalizability.