Sparsier2Sparse: Self-supervised convolutional neural network-based streak artifacts reduction in sparse-view CT images.

BACKGROUND: Sparse-view computed tomography (CT) has attracted a lot of attention for reducing both scanning time and radiation dose. However, sparsely-sampled projection data generate severe streak artifacts in the reconstructed images. In recent decades, many sparse-view CT reconstruction techniques based on fully-supervised learning have been proposed and have shown promising results. However, it is not feasible to acquire pairs of full-view and sparse-view CT images in real clinical practice. PURPOSE: In this study, we propose a novel self-supervised convolutional neural network (CNN) method to reduce streak artifacts in sparse-view CT images. METHODS: We generate the training dataset using only sparse-view CT data and train CNN based on self-supervised learning. Since the streak artifacts can be estimated using prior images under the same CT geometry system, we acquire prior images by iteratively applying the trained network to given sparse-view CT images. We then subtract the estimated steak artifacts from given sparse-view CT images to produce the final results. RESULTS: We validated the imaging performance of the proposed method using extended cardiac-torso (XCAT) and the 2016 AAPM Low-Dose CT Grand Challenge dataset from Mayo Clinic. From the results of visual inspection and modulation transfer function (MTF), the proposed method preserved the anatomical structures effectively and showed higher image resolution compared to the various streak artifacts reduction methods for all projection views. CONCLUSIONS: We propose a new framework for streak artifacts reduction when only the sparse-view CT data are given. Although we do not use any information of full-view CT data for CNN training, the proposed method achieved the highest performance in preserving fine details. By overcoming the limitation of dataset requirements on fully-supervised-based methods, we expect that our framework can be utilized in the medical imaging field.

A streak artifact reduction algorithm in sparse-view CT using a self-supervised neural representation.

PURPOSE: Sparse-view computed tomography (CT) has been attracting attention for its reduced radiation dose and scanning time. However, analytical image reconstruction methods suffer from streak artifacts due to insufficient projection views. Recently, various deep learning-based methods have been developed to solve this ill-posed inverse problem. Despite their promising results, they are easily overfitted to the training data, showing limited generalizability to unseen systems and patients. In this work, we propose a novel streak artifact reduction algorithm that provides a system- and patient-specific solution. METHODS: Motivated by the fact that streak artifacts are deterministic errors, we regenerate the same artifacts from a prior CT image under the same system geometry. This prior image need not be perfect but should contain patient-specific information and be consistent with full-view projection data for accurate regeneration of the artifacts. To this end, we use a coordinate-based neural representation that often causes image blur but can greatly suppress the streak artifacts while having multiview consistency. By employing techniques in neural radiance fields originally proposed for scene representations, the neural representation is optimized to the measured sparse-view projection data via self-supervised learning. Then, we subtract the regenerated artifacts from the analytically reconstructed original image to obtain the final corrected image. RESULTS: To validate the proposed method, we used simulated data of extended cardiac-torso phantoms and the 2016 NIH-AAPM-Mayo Clinic Low-Dose CT Grand Challenge and experimental data of physical pediatric and head phantoms. The performance of the proposed method was compared with a total variation-based iterative reconstruction method, naive application of the neural representation, and a convolutional neural network-based method. In visual inspection, it was observed that the small anatomical features were best preserved by the proposed method. The proposed method also achieved the best scores in the visual information fidelity, modulation transfer function, and lung nodule segmentation. CONCLUSIONS: The results on both simulated and experimental data suggest that the proposed method can effectively reduce the streak artifacts while preserving small anatomical structures that are easily blurred or replaced with misleading features by the existing methods. Since the proposed method does not require any additional training datasets, it would be useful in clinical practice where the large datasets cannot be collected.

Convolutional neural network-based metal and streak artifacts reduction in dental CT images with sparse-view sampling scheme.

PURPOSE: Sparse-view sampling has attracted attention for reducing the scan time and radiation dose of dental cone-beam computed tomography (CBCT). Recently, various deep learning-based image reconstruction techniques for sparse-view CT have been employed to produce high-quality image while effectively reducing streak artifacts caused by the lack of projection views. However, most of these methods do not fully consider the effects of metal implants. As sparse-view sampling strengthens the artifacts caused by metal objects, simultaneously reducing both metal and streak artifacts in sparse-view CT images has been challenging. To solve this problem, in this study, we propose a novel framework. METHODS: The proposed method was based on the normalized metal artifact reduction (NMAR) method, and its performance was enhanced using two convolutional neural networks (CNNs). The first network reduced the initial artifacts while preserving the fine details to generate high-quality priors for NMAR processing. Subsequently, the second network was employed to reduce the streak artifacts after NMAR processing of sparse-view CT data. To validate the proposed method, we generated training and test data by computer simulations using both extended cardiac-torso (XCAT) and clinical data sets. RESULTS: Visual inspection and quantitative evaluations demonstrated that the proposed method effectively reduced both metal and streak artifacts while preserving the details of anatomical structures compared with the conventional metal artifact reduction methods. CONCLUSIONS: We propose a framework for reconstructing accurate CT images in metal-inserted sparse-view CT. The proposed method reduces streak artifacts from both metal objects and sparse-view sampling while recovering the anatomical details, indicating the feasibility of fast-scan dental CBCT imaging.

Weakly-supervised progressive denoising with unpaired CT images.

Although low-dose CT imaging has attracted a great interest due to its reduced radiation risk to the patients, it suffers from severe and complex noise. Recent fully-supervised methods have shown impressive performances on CT denoising task. However, they require a huge amount of paired normal-dose and low-dose CT images, which is generally unavailable in real clinical practice. To address this problem, we propose a weakly-supervised denoising framework that generates paired original and noisier CT images from unpaired CT images using a physics-based noise model. Our denoising framework also includes a progressive denoising module that bypasses the challenges of mapping from low-dose to normal-dose CT images directly via progressively compensating the small noise gap. To quantitatively evaluate diagnostic image quality, we present the noise power spectrum and signal detection accuracy, which are well correlated with the visual inspection. The experimental results demonstrate that our method achieves remarkable performances, even superior to fully-supervised CT denoising with respect to the signal detectability. Moreover, our framework increases the flexibility in data collection, allowing us to utilize any unpaired data at any dose levels.

A performance comparison of convolutional neural network-based image denoising methods: The effect of loss functions on low-dose CT images.

PURPOSE: Convolutional neural network (CNN)-based image denoising techniques have shown promising results in low-dose CT denoising. However, CNN often introduces blurring in denoised images when trained with a widely used pixel-level loss function. Perceptual loss and adversarial loss have been proposed recently to further improve the image denoising performance. In this paper, we investigate the effect of different loss functions on image denoising performance using task-based image quality assessment methods for various signals and dose levels. METHODS: We used a modified version of U-net that was effective at reducing the correlated noise in CT images. The loss functions used for comparison were two pixel-level losses (i.e., the mean-squared error and the mean absolute error), Visual Geometry Group network-based perceptual loss (VGG loss), adversarial loss used to train the Wasserstein generative adversarial network with gradient penalty (WGAN-GP), and their weighted summation. Each image denoising method was applied to reconstructed images and sinogram images independently and validated using the extended cardiac-torso (XCAT) simulation and Mayo Clinic datasets. In the XCAT simulation, we generated fan-beam CT datasets with four different dose levels (25%, 50%, 75%, and 100% of a normal-dose level) using 10 XCAT phantoms and inserted signals in a test set. The signals had two different shapes (spherical and spiculated), sizes (4 and 12 mm), and contrast levels (60 and 160 HU). To evaluate signal detectability, we used a detection task SNR (tSNR) calculated from a non-prewhitening model observer with an eye filter. We also measured the noise power spectrum (NPS) and modulation transfer function (MTF) to compare the noise and signal transfer properties. RESULTS: Compared to CNNs without VGG loss, VGG-loss-based CNNs achieved a more similar tSNR to that of the normal-dose CT for all signals at different dose levels except for a small signal at the 25% dose level. For a low-contrast signal at 25% or 50% dose, adding other losses to the VGG loss showed more improved performance than only using VGG loss. The NPS shapes from VGG-loss-based CNN closely matched that of normal-dose CT images while CNN without VGG loss overly reduced the mid-high-frequency noise power at all dose levels. MTF also showed VGG-loss-based CNN with better-preserved high resolution for all dose and contrast levels. It is also observed that additional WGAN-GP loss helps improve the noise and signal transfer properties of VGG-loss-based CNN. CONCLUSIONS: The evaluation results using tSNR, NPS, and MTF indicate that VGG-loss-based CNNs are more effective than those without VGG loss for natural denoising of low-dose images and WGAN-GP loss improves the denoising performance of VGG-loss-based CNNs, which corresponds with the qualitative evaluation.

Predictive Modeling and Categorizing Likelihoods of Quarantine Pest Introduction of Imported Propagative Commodities from Different Countries.

The present study investigates U.S. Department of Agriculture inspection records in the Agricultural Quarantine Activity System database to estimate the probability of quarantine pests on propagative plant materials imported from various countries of origin and to develop a methodology ranking the risk of country-commodity combinations based on quarantine pest interceptions. Data collected from October 2014 to January 2016 were used for developing predictive models and validation study. A generalized linear model with Bayesian inference and a generalized linear mixed effects model were used to compare the interception rates of quarantine pests on different country-commodity combinations. Prediction ability of generalized linear mixed effects models was greater than that of generalized linear models. The estimated pest interception probability and confidence interval for each country-commodity combination was categorized into one of four compliance levels: "High," "Medium," "Low," and "Poor/Unacceptable," Using K-means clustering analysis. This study presents risk-based categorization for each country-commodity combination based on the probability of quarantine pest interceptions and the uncertainty in that assessment.

Human and model observer performance for lesion detection in breast cone beam CT images with the FDK reconstruction.

We investigate the detectability of breast cone beam computed tomography images using human and model observers and the variations of exponent, ß, of the inverse power-law spectrum for various reconstruction filters and interpolation methods in the Feldkamp-Davis-Kress (FDK) reconstruction. Using computer simulation, a breast volume with a 50% volume glandular fraction and a 2mm diameter lesion are generated and projection data are acquired. In the FDK reconstruction, projection data are apodized using one of three reconstruction filters; Hanning, Shepp-Logan, or Ram-Lak, and back-projection is performed with and without Fourier interpolation. We conduct signal-known-exactly and background-known-statistically detection tasks. Detectability is evaluated by human observers and their performance is compared with anthropomorphic model observers (a non-prewhitening observer with eye filter (NPWE) and a channelized Hotelling observer with either Gabor channels or dense difference-of-Gaussian channels). Our results show that the NPWE observer with a peak frequency of 7cyc/degree attains the best correlation with human observers for the various reconstruction filters and interpolation methods. We also discover that breast images with smaller ß do not yield higher detectability in the presence of quantum noise.

Anisotropic superfluidity of (4)He on a C36 fullerene molecule.

We have performed path-integral Monte Carlo calculations to study the adsorption of (4)He atoms on two different C36 isomers with the D6h and the D2d symmetries. The radial (4)He density distributions reveal layer-by-layer growth with the first layer being located at a distance of ∼5.5 Å from the C36 molecular center and the second layer at ∼8.3 Å. From the angular density profiles of (4)He, we find different quantum states as the number of (4)He adatoms N varies. For N = 20, we observe commensurate solid structures on both D6h and D2d isomers, where each of 8 hexagon and 12 pentagon centers of the fullerene surfaces is occupied by a single (4)He atom. The second-layer promotion starts beyond N = 38 on both isomers, where a compressible incommensurate structure is observed on the D6h isomer and another commensurate structure on D2d. Between N = 20 and N = 38, the (4)He monolayer on D6h shows several distinct rings of delocalized (4)He atoms along with strongly anisotropic superfluid responses at low temperatures, while isotropic but weak superfluid responses are observed in the (4)He layer on D2d.

A shorter treatment duration may be sufficient for patients with Mycobacterium massiliense lung disease than with Mycobacterium abscessus lung disease.

BACKGROUND: Mycobacterium abscessus complex is the second most common organism isolated from patients with nontuberculous mycobacterial (NTM) lung disease in South Korea. This study aimed to compare clinical features and treatment outcomes of M. abscessus and Mycobacterium massiliense lung disease. METHODS: We retrospectively identified stored clinical isolates of M. abscessus complex as either M. abscessus or M. massiliense and reviewed medical records to compare clinical characteristics and treatment responses. All patients were treated empirically over several months with multidrug regimens, including a macrolide and one or more parenteral agents. RESULTS: Of the 249 patient isolates tested, 128 (59 with M. abscessus and 69 with M. massiliense) met the American Thoracic Society diagnostic criteria for NTM pulmonary disease, and treatment outcomes were analyzed in 48 patients (26 with M. abscessus and 22 with M. massiliense). The clinical and radiologic findings were similar between the two groups. Although the durations of parenteral and total treatment were significantly shorter in patients with M. massiliense than in those with M. abscessus (4.7 months vs 7.4 months, P = .006, and 12.1 months vs 16.3 months, P = .043), the treatment success rate was significantly higher in patients with M. massiliense (95.5%) than in M. abscessus cases (42.3%, P < .001). CONCLUSION: Patients with M. massiliense pulmonary infection responded better to this antibiotic strategy than those with M. abscessus infection. A shortened duration of treatment may be sufficient for M. massiliense pulmonary infection.