Transfer learning framework for low-dose CT reconstruction based on marginal distribution adaptation in multi-scale.

In recent years, health risks concerning high-dose x-ray radiation have become a major concern in dental computed tomography (CT) examinations. Therefore, adopting low-dose computed tomography (LDCT) technology has become a major focus in the CT imaging field. One of these LDCT technologies is downsampling data acquisition during low-dose x-ray imaging processes. However, reducing the radiation dose can adversely affect CT image quality by introducing noise and artifacts in the resultant image that can compromise diagnostic information. In this paper, we propose an artifact correction method for downsampling CT reconstruction based on deep learning. We used clinical dental CT data with low-dose artifacts reconstructed by conventional filtered back projection (FBP) as inputs to a deep neural network and corresponding high-quality labeled normal-dose CT data during training. We trained a generative adversarial network (GAN) with Wasserstein distance (WGAN) and mean squared error (MSE) loss, called m-WGAN, to remove artifacts and obtain high-quality CT dental images in a clinical dental CT examination environment. The experimental results confirmed that the proposed algorithm effectively removes low-dose artifacts from dental CT scans. In addition, we showed that the proposed method is efficient for removing noise from low-dose CT scan images compared to existing approaches. We compared the performances of the general GAN, convolutional neural networks, and m-WGAN. Through quantitative and qualitative analysis of the results, we concluded that the proposed m-WGAN method resulted in better artifact correction performance preserving the texture in dental CT scanning. The image quality evaluation metrics indicated that the proposed method effectively improves image quality when used as a postprocessing technique for dental CT images. To the best of our knowledge, this work is the first deep learning architecture used with a commercial cone-beam dental CT scanner. The artifact correction performance was rigorously evaluated and demonstrated to be effective. Therefore, we believe that the proposed algorithm represents a new direction in the research area of low-dose dental CT artifact correction.

Markov random field (MRF) model-based penalty is widely used in statistical iterative reconstruction (SIR) of low dose CT (LDCT) reconstruction for noise suppression and edge-preserving. In this strategy, normal dose CT scans are usually used as a priori information to further improve the LDCT quality. However, repeated CT scans are needed and registration or segmentation is usually applied first when misalignment between the low-dose and normal-dose scans exists. The study aims to propose a new MRF prior model of SIR based on the NDCT database without registration. In the proposed model, MRF weights are predicted using optimal similar patch samples from the NDCT database. The patch samples are determined by evaluating the similarity with Euclidean distance between patches from NDCT and the target patch of LDCT. The proposed prior term is incorporated into the SIR cost function, which is to be minimized for LDCT reconstruction. The proposed method is tested on an artificial LDCT data based on a high-dose patient data. Preliminary result has proved its potential performance in edge and structure detail preservation.

This study aimed to evaluate image quality, the detection rate of enlarged lymph nodes, and radiation dose exposure of ultralow-dose and low-dose abdominopelvic computed tomography (CT) in patients with lymphoma. Patients with lymphoma who underwent abdominopelvic CT using dual-source scanner were retrospectively recruited from a single center. CT images were obtained at 90 kVp dual-source mode reformatted in three data sets using the advanced modelled iterative reconstruction algorithm: 100% (standard-dose CT), 66.7% (low-dose CT), and 33.3% (ultralow-dose CT). Two radiologists analyzed subjective image quality and detection of abdominal enlarged lymph nodes on ultralow-dose, low-dose, and standard-dose CT blindly and independently. The results were compared with reference standards. Three readers (two radiologists and one hematologist) reviewed overall image quality and spleen size. In total, 128 consecutive CT scans (77 complete response, 44 partial response, 6 progressive disease, and 1 initial evaluation) from 86 patients (64 B-cell lymphoma, 14 T/NK-cell lymphoma, and 8 Hodgkin’s lymphoma cases) were assessed. The enlarged lymph node-based detection rates for two readers were 97.0% (96/99) and 94.0% (93/99) on standard-dose CT, 97.0% (96/99) and 94.0% (93/99) on low-dose CT, and 94.0% (93/99) and 89.9% (89/99) on ultralow-dose CT. Overall image quality was 3.8 ± 0.5, 3.9 ± 0.5, and 4.1 ± 0.5 on ultralow-dose CT; 4.7 ± 0.4, 4.6 ± 0.5, and 4.8 ± 0.3 on low-dose CT; and 4.8 ± 0.4, 4.7 ± 0.4, and 4.9 ± 0.2 on standard-dose CT, according to two radiologists and one hematologist, respectively. Intraclass correlation coefficients of spleen size were 0.90 (95% confidence interval [CI], 0.87–0.93), 0.91 (95% CI, 0.88–0.93), and 0.91 (95% CI, 0.88–0.93) on ultralow-dose, low-dose, and standard-dose CT, respectively. Mean effective radiation doses of standard-dose, low-dose, and ultralow-dose CT were 5.7 ±1.8 mSv, 3.8 ± 1.2 mSv, and 1.9 ± 0.6 mSv, respectively. Our findings suggest that ultralow-dose and low-dose CT, even with radiation doses reduced by 66.7% and 33.3%, respectively, maintained adequate image quality. These imaging modalities may be employed for follow-up lymphoma evaluation in consideration of the long surveillance periods.

The resurgence of deep neural networks has created an alternative pathway for low-dose computed tomography denoising by learning a nonlinear transformation function between low-dose CT (LDCT) and normal-dose CT (NDCT) image pairs. However, those paired LDCT and NDCT images are rarely available in the clinical environment, making deep neural network deployment infeasible. This study proposes a novel method for self-supervised low-dose CT denoising to alleviate the requirement of paired LDCT and NDCT images. Specifically, we have trained an invertible neural network to minimize the pixel-based mean square distance between a noisy slice and the average of its two immediate adjacent noisy slices. We have shown the aforementioned is similar to training a neural network to minimize the distance between clean NDCT and noisy LDCT image pairs. Again, during the reverse mapping of the invertible network, the output image is mapped to the original input image, similar to cycle consistency loss. Finally, the trained invertible network’s forward mapping is used for denoising LDCT images. Extensive experiments on two publicly available datasets showed that our method performs favourably against other existing unsupervised methods.

Deep learning based denoising techniques have effectively reduced noise in low-dose computed tomography (LDCT) images. However, the need for pairs of LDCT and normal-dose CT (NDCT) training images is the main reason that makes the use of deep learning networks difficult. Therefore, we propose a method of generating synthesized LDCT images by adding synthesized quantum noise to the NDCT images. For this, we estimate the quantum noise power spectrum (NPS) of patient CT images by modeling anatomical NPS and quantum NPS, respectively. We use the quantum NPS as a noise filter and generate synthesized quantum noise by filtering random Gaussian noise. Using the proposed method, LDCT denoiser can be trained without using pairs of LDCT and NDCT images, and the trained denoiser effectively reduces noise in LDCT images. The proposed method facilitates data acquisition for training deep learning networks and reduces the risk of radiation exposure to patients.

A number of blind Image Quality Evaluation Metrics (IQEMs) for Unmanned Aerial Vehicle (UAV) photograph application are presented. Nowadays, the visible light camera is widely used for UAV photograph application because of its vivid imaging effect; however, the outdoor environment light will produce great negative influences on its imaging output unfortunately. In this paper, to conquer this problem above, we design and reuse a series of blind IQEMs to analyze the imaging quality of UAV application. The Human Visual System (HVS) based IQEMs, including the image brightness level, the image contrast level, the image noise level, the image edge blur level, the image texture intensity level, the image jitter level, and the image flicker level, are all considered in our application. Once these IQEMs are calculated, they can be utilized to provide a computational reference for the following image processing application, such as image understanding and recognition. Some preliminary experiments for image enhancement have proved the correctness and validity of our proposed technique.

Deep learning has recently attracted widespread interest as a means of reducing noise in low-dose CT (LDCT) images. Deep convolutional neural networks (CNNs) are typically trained to transfer high-quality image features of normal-dose CT (NDCT) images to LDCT images. However, existing deep learning approaches for denoising LDCT images often overlook the statistical property of CT images. In this paper, we propose an approach to statistical image restoration for LDCT using deep learning. We introduce a loss function to incorporate the noise property in image domain derived from the noise statistics in sinogram domain. In order to capture the spatially-varying statistics of CT images, we increase the receptive fields of the neural network to cover full-size CT slices. In addition, the proposed network utilizes z-directional correlation by taking multiple consecutive CT slices as input. For performance evaluation, the proposed networks are trained and validated with a public dataset consisting of LDCT-NDCT image pairs. We also perform a retrospective study by testing the networks with clinical LDCT images. The experimental results show that the denoising networks successfully reduce the noise level and restore the image details without adding artifacts. This study demonstrates that the statistical deep learning approach can restore the image quality of LDCT without loss of anatomical information.

Convolutional neural networks (CNN) have been used for a wide variety of deep learning applications, especially in computer vision. For medical image processing, researchers have identified certain challenges associated with CNNs. These challenges encompass the generation of less informative features, limitations in capturing both high and low-frequency information within feature maps, and the computational cost incurred when enhancing receptive fields by deepening the network. Transformers have emerged as an approach aiming to address and overcome these specific limitations of CNNs in the context of medical image analysis. Preservation of all spatial details of medical images is necessary to ensure accurate patient diagnosis. Hence, this research introduced the use of a pure Vision Transformer (ViT) for a denoising artificial neural network for medical image processing specifically for low-dose computed tomography (LDCT) image denoising. The proposed model follows a U-Net framework that contains ViT modules with the integration of Noise2Neighbor (N2N) interpolation operation. Five different datasets containing LDCT and normal-dose CT (NDCT) image pairs were used to carry out this experiment. To test the efficacy of the proposed model, this experiment includes comparisons between the quantitative and visual results among CNN-based (BM3D, RED-CNN, DRL-E-MP), hybrid CNN-ViT-based (TED-Net), and the proposed pure ViT-based denoising model. The findings of this study showed that there is about 15-20% increase in SSIM and PSNR when using self-attention transformers than using the typical pure CNN. Visual results also showed improvements especially when it comes to showing fine structural details of CT images.

Recently, one promising approach to suppress noise/artifacts in low-dose CT (LDCT) images is the CNN-based approach, which learns the mapping function from LDCT to normal-dose CT (NDCT). However, most CNN-based methods are purely data-driven, thus lacking sufficient interpretability and often losing details. To solve this problem, we propose a deep convolutional dictionary learning method for LDCT denoising, in which a novel convolutional dictionary learning model with adaptive window (CDL-AW) is designed, and a corresponding enhancement-based convolutional dictionary learning network (called ECDAW-Net) is constructed to unfold the CDL-AW model iteratively using the proximal gradient descent technique. In detail, the adaptive window-constrained convolutional dictionary atom is proposed to alleviate spectrum leakage caused by data truncation during convolution. Furthermore, in the ECDAW-Net, a multi-scale edge extraction module that consists of LoG and Sobel convolution layers is proposed in the unfolding iteration, to supplement lost textures and details. Additionally, to further improve the detail retention ability, the ECDAW-Net is trained by the compound loss function of the pixel-level MSE loss and the proposed patch-level loss, which can assist to retain richer structural information. Applying ECDAW-Net to the Mayo dataset, we obtained the highest peak signal-to-noise ratio (33.94) and sub-optimal structural similarity (0.92). Compared with some state-of-art methods, the interpretable ECDAW-Net performs well in suppressing noise/artifacts and preserving textures of tissue.

Deep learning image reconstruction (DLIR) is a new reconstruction method for maintaining image quality at reduced radiation dose. The purpose of this study was to compare image quality of reduced-dose DLIR images with the standard-dose adaptive statistical iterative reconstruction (ASIR-V) images in chest CT. Our prospective study included 48 adult patients (30 women and 18 men, mean age ±SD, 49.8 ± 14.3 years) who underwent both the standard-dose CT (SDCT) and low-dose CT (LDCT) on a GE Revolution CT scanner. All patients gave written informed consent. All scans were reconstructed with ASIR-V40%. Additionally, LDCT scans were reconstructed with DLIR with high-setting (DLIR-H) and medium-setting (DLIR-M). Image noise and contrast-noise-ratio (CNR) of thoracic aorta with different reconstruction modes were measured and compared. LDCT reduced radiation dose by 96% compared with SDCT (CTDIvol: 0.54mGy vs 12.46mGy). In LDCT, DLIR significantly reduced image noise compared with the state-of-the-art ASIR-V40% with DLIR-H provided the lowest image noise and highest image quality score. In addition, the image noise, CNR of aorta and overall image quality of the low-dose DLIR-H images did not have significant difference compared with the SDCT ASIR-V40% images (all p > 0.05). DLIR significantly reduces image noise in LDCT chest scans and provides similar image quality as the SDCT ASIR-V images at 4% of the radiation dose. DLIR uses high-quality FBP data to train deep neural networks to learn how to distinguish between signal and noise, and effectively suppresses noise without affecting anatomical and pathological structures. It opens a new era of CT image reconstruction. DLIR significantly reduces image noise and improves image quality compared with ASIR-V40% under same radiation dose condition. DLIR-H achieves similar image quality at 4% radiation dose as ASIR-V40% at standard-dose level in non-contrast chest CT.

It is well-known that speckle is a multiplicative noise that degrades the visual evaluation in ultrasound imaging. The recent advancements in ultrasound instrumentation and portable ultrasound devices necessitate the need of more robust despeckling techniques for enhanced ultrasound medical imaging for both routine clinical practice and teleconsultation. The objective of this work was to carry out a comparative evaluation of despeckle filtering based on texture analysis, image quality evaluation metrics, and visual evaluation by medical experts in the assessment of 440 (220 asymptomatic and 220 symptomatic) ultrasound images of the carotid artery bifurcation. In this paper a total of 10 despeckle filters were evaluated based on local statistics, median filtering, pixel homogeneity, geometric filtering, homomorphic filtering, anisotropic diffusion, nonlinear coherence diffusion, and wavelet filtering. The results of this study suggest that the first order statistics filter lsmv, gave the best performance, followed by the geometric filter gf4d, and the homogeneous mask area filter lsminsc. These filters improved the class separation between the asymptomatic and the symptomatic classes based on the statistics of the extracted texture features, gave only a marginal improvement in the classification success rate, and improved the visual assessment carried out by the two experts. More specifically, filters lsmv or gf4d can be used for despeckling asymptomatic images in which the expert is interested mainly in the plaque composition and texture analysis; and filters lsmv, gf4d, or lsminsc can be used for the despeckling of symptomatic images in which the expert is interested in identifying the degree of stenosis and the plaque borders. The proper selection of a despeckle filter is very important in the enhancement of ultrasonic imaging of the carotid artery. Further work is needed to evaluate at a larger scale and in clinical practice the performance of the proposed despeckle filters in the automated segmentation, texture analysis, and classification of carotid ultrasound imaging.

The goal of this paper is to investigate and evaluate image quality, based on quality metrics and visual perception in ultrasound imaging under different imaging conditions. We first generate and simulate Bmode ultrasound images of various objects, using Field-II simulation toolbox [1]. Then we implement and embed front-end functional modules, mid-end functions including beamforming, receive beamforming, envelop detection and log compression, and back-end image processing methods (filtering and image enhancement techniques). Ultrasound images are evaluated as pairs using various image quality evaluation metrics and visual perception evaluation. The experimental results of this study show that: (1) better image quality is significantly obtained using over-sampling and signal emphasizing (high-signal level); (2) normalized images with speckle filters are rated better in terms of index-quality; and (3) enhanced images show better visual perception on all simulation datasets. This paper shows the utility of our MATLAB test-bench favoring simulated image quality and further demonstrates that the evaluation design is an important pre-processing step especially for the hardware design of ultrasound system.

Ultrasound imaging is a widely used and safe medical diagnostic technique, due to its noninvasive nature, low cost, capability of forming real time imaging, and the continuing improvements in image quality. However; the usefulness of ultrasound imaging is degraded by the presence of signal dependant noise known as speckle. It is well-known that speckle is a multiplicative noise that degrades the visual evaluation in ultrasound imaging. In ultrasound (US) imaging, denoising is intended to improve quantitative image analysis techniques. In this paper, a new version of the Non Local (NL-) means filter adapted for US images is proposed based on Similarity function depend on specific characteristics of the variance speckle noise in ultrasound images. The proposed method has been compared with Median, Wavelet, Mean and variance local statistics, Geometric, Anisotropic diffusion filtering, and Non ' local means filter using quantitative parameters. From the visual results and image quality evaluation metrics obtained over real images we can conclude that the modified(NL-) means filter can be successfully used for ultrasound image denoising, and performs better results than all other methods while still retaining the structural details and retains the edges and textures very well while removing speckle noise.

FADFNet: A fine-tunable and adaptive decomposition-fusion network for cross-dataset low-dose CT and low-dose PET image reconstruction.

Low-dose computed tomography (LDCT) is an effective way to reduce radiation exposure for patients. However, it will increase the noise of reconstructed CT images and affect the precision of clinical diagnosis. The majority of the current deep learning-based denoising methods are built on convolutional neural networks (CNNs), which concentrate on local information and have little capacity for multiple structures modeling. Transformer structures are capable of computing each pixel's response on a global scale, but their extensive computation requirements prevent them from being widely used in medical image processing. To reduce the impact of LDCT scans on patients, this paper aims to develop an image post-processing method by combining CNN and Transformer structures. This method can obtain a high-quality images from LDCT. A hybrid CNN-Transformer (HCformer) codec network model is proposed for LDCT image denoising. A neighborhood feature enhancement (NEF) module is designed to introduce the local information into the Transformer's operation, and the representation of adjacent pixel information in the LDCT image denoising task is increased. The shifting window method is utilized to lower the computational complexity of the network model and overcome the problems that come with computing the MSA (Multi-head self-attention) process in a fixed window. Meanwhile, W/SW-MSA (Windows/Shifted window Multi-head self-attention) is alternately used in two layers of the Transformer to gain the information interaction between various Transformer layers. This approach can successfully decrease the Transformer's overall computational cost. The AAPM 2016 LDCT grand challenge dataset is employed for ablation and comparison experiments to demonstrate the viability of the proposed LDCT denoising method. Per the experimental findings, HCformer can increase the image quality metrics SSIM, HuRMSE and FSIM from 0.8017, 34.1898, and 0.6885 to 0.8507, 17.7213, and 0.7247, respectively. Additionally, the proposed HCformer algorithm will preserves image details while it reduces noise. In this paper, an HCformer structure is proposed based on deep learning and evaluated by using the AAPM LDCT dataset. Both the qualitative and quantitative comparison results confirm that the proposed HCformer outperforms other methods. The contribution of each component of the HCformer is also confirmed by the ablation experiments. HCformer can combine the advantages of CNN and Transformer, and it has great potential for LDCT image denoising and other tasks.