Radiation dose reduction in pediatric computed tomography (CT) using deep convolutional neural network denoising.

Aim: We evaluated the quality of noncontrast chest computed tomography (CT) for pediatric patients at two dose levels with and without denoising using a deep convolutional neural network (CNN).

Materials And Methods: Forty children underwent noncontrast chest CTs for "chronic cough" using a routine dose (RD) protocol. Images were reconstructed using iterative reconstruction (IR).

Feasibility of thin-slice, low noise images created using multi-kernel synthesis to replace multiple image series in head CT.

Background: SynthesiZed Improved Resolution and Concurrent nOise reductioN (ZIRCON) is a multi-kernel synthesis method that creates a single series of thin-slice computed tomography (CT) images displaying low noise and high spatial resolution, increasing reader efficiency and minimizing partial volume averaging.

Purpose: To compare the diagnostic performance of a single set of ZIRCON images to two routine clinical image series using conventional CT head and bone reconstruction kernels for diagnosing intracranial findings and fractures in patients with trauma or suspected acute neurologic deficit.

Material And Methods: In total, 50 patients underwent clinically indicated head CT in the ER (15 normal, 35 abnormal cases).

Learned high-resolution cardiac CT imaging from ultra-high-resolution PCD-CT.

Coronary computed tomography angiography (cCTA) is a widely used non-invasive diagnostic exam for patients with coronary artery disease (CAD). However, most clinical CT scanners are limited in spatial resolution from use of energy-integrating detectors (EIDs). Radiological evaluation of CAD is challenging, as coronary arteries are small (3-4 mm diameter) and calcifications within them are highly attenuating, leading to blooming artifacts.

A Classification-Based Adaptive Segmentation Pipeline: Feasibility Study Using Polycystic Liver Disease and Metastases from Colorectal Cancer CT Images.

Automated segmentation tools often encounter accuracy and adaptability issues when applied to images of different pathology. The purpose of this study is to explore the feasibility of building a workflow to efficiently route images to specifically trained segmentation models. By implementing a deep learning classifier to automatically classify the images and route them to appropriate segmentation models, we hope that our workflow can segment the images with different pathology accurately.

Deep convolutional-neural-network-based metal artifact reduction for CT-guided interventional oncology procedures (MARIO).

Background: Computed tomography (CT) is routinely used to guide cryoablation procedures. Notably, CT-guidance provides 3D localization of cryoprobes and can be used to delineate frozen tissue during ablation. However, metal-induced artifacts from ablation probes can make accurate probe placement challenging and degrade the ice ball conspicuity, which in combination could lead to undertreatment of potentially curable lesions.

Multiple Kernel Synthesis of Head CT Using a Task-Based Loss Function.

In CT imaging of the head, multiple image series are routinely reconstructed with different kernels and slice thicknesses. Reviewing the redundant information is an inefficient process for radiologists. We address this issue with a convolutional neural network (CNN)-based technique, synthesiZed Improved Resolution and Concurrent nOise reductioN (ZIRCON), that creates a single, thin, low-noise series that combines the favorable features from smooth and sharp head kernels.

Supervised Learning for CT Denoising and Deconvolution Without High-Resolution Reference Images.

Purpose: Convolutional neural networks (CNNs) have been proposed for super-resolution in CT, but training of CNNs requires high-resolution reference data. Higher spatial resolution can also be achieved using deconvolution, but conventional deconvolution approaches amplify noise. We develop a CNN that mitigates increasing noise and that does not require higher-resolution reference images.

Technical note: Phantom-based training framework for convolutional neural network CT noise reduction.

Background: Deep artificial neural networks such as convolutional neural networks (CNNs) have been shown to be effective models for reducing noise in CT images while preserving anatomic details. A practical bottleneck for developing CNN-based denoising models is the procurement of training data consisting of paired examples of high-noise and low-noise CT images. Obtaining these paired data are not practical in a clinical setting where the raw projection data is not available.

AI Integration in the Clinical Workflow.

Machine learning and artificial intelligence (AI) algorithms hold significant promise for addressing important clinical needs when applied to medical imaging; however, integration of algorithms into a radiology department is challenging. Vended algorithms are integrated into the workflow, successfully, but are typically closed systems and unavailable for site researchers to deploy algorithms. Rather than AI researchers creating one-off solutions, a general, multi-purpose integration system is desired.

Evaluating a Convolutional Neural Network Noise Reduction Method When Applied to CT Images Reconstructed Differently Than Training Data.

Objective: The aim of this study was to evaluate a narrowly trained convolutional neural network (CNN) denoising algorithm when applied to images reconstructed differently than training data set.

Methods: A residual CNN was trained using 10 noise inserted examinations. Training images were reconstructed with 275 mm of field of view (FOV), medium smooth kernel (D30), and 3 mm of thickness.

CT Noise-Reduction Methods for Lower-Dose Scanning: Strengths and Weaknesses of Iterative Reconstruction Algorithms and New Techniques.

Iterative reconstruction (IR) algorithms are the most widely used CT noise-reduction method to improve image quality and have greatly facilitated radiation dose reduction within the radiology community. Various IR methods have different strengths and limitations. Because IR algorithms are typically nonlinear, they can modify spatial resolution and image noise texture in different regions of the CT image; hence traditional image-quality metrics are not appropriate to assess the ability of IR to preserve diagnostic accuracy, especially for low-contrast diagnostic tasks.

Clinical evaluation of a phantom-based deep convolutional neural network for whole-body-low-dose and ultra-low-dose CT skeletal surveys.

Objective: This study evaluated the clinical utility of a phantom-based convolutional neural network noise reduction framework for whole-body-low-dose CT skeletal surveys.

Materials And Methods: The CT exams of ten patients with multiple myeloma were retrospectively analyzed. Exams were acquired with routine whole-body-low-dose CT protocol and projection noise insertion was used to simulate 25% dose exams.

Random Search as a Neural Network Optimization Strategy for Convolutional-Neural-Network (CNN)-based Noise Reduction in CT.

In this study, we describe a systematic approach to optimize deep-learning-based image processing algorithms using random search. The optimization technique is demonstrated on a phantom-based noise reduction training framework; however, the techniques described can be applied generally for other deep learning image processing applications. The parameter space explored included number of convolutional layers, number of filters, kernel size, loss function, and network architecture (either U-Net or ResNet).

Magician's Corner: 7. Using Convolutional Neural Networks to Reduce Noise in Medical Images.

This article shows how to train a convolutional neural network to reduce noise in CT images, although the principles apply to medical and nonmedical images; authors also explore mathematical and visually weighted loss functions to adjust the appearance.

Synthesizing images from multiple kernels using a deep convolutional neural network.

Purpose: Filtering measured projections with a particular convolutional kernel is an essential step in analytic reconstruction of computed tomography (CT) images. A tradeoff between noise and spatial resolution exists for different choices of reconstruction kernel. In a clinical setting, this often requires producing multiple images reconstructed with different kernels for a single CT exam, which increases the burden of computation, networking, archival, and reading.

Search for CP Violation in Neutrino and Antineutrino Oscillations by the T2K Experiment with 2.2×10^{21} Protons on Target.

The T2K experiment measures muon neutrino disappearance and electron neutrino appearance in accelerator-produced neutrino and antineutrino beams. With an exposure of 14.7(7.

Combined Analysis of Neutrino and Antineutrino Oscillations at T2K.

T2K reports its first results in the search for CP violation in neutrino oscillations using appearance and disappearance channels for neutrino- and antineutrino-mode beams. The data include all runs from January 2010 to May 2016 and comprise 7.482×10^{20} protons on target in neutrino mode, which yielded in the far detector 32 e-like and 135  μ-like events, and 7.

Measurement of Coherent π^{+} Production in Low Energy Neutrino-Carbon Scattering.

We report the first measurement of the flux-averaged cross section for charged current coherent π^{+} production on carbon for neutrino energies less than 1.5 GeV, and with a restriction on the final state phase space volume in the T2K near detector, ND280. Comparisons are made with predictions from the Rein-Sehgal coherent production model and the model by Alvarez-Ruso et al.

Measurement of Muon Antineutrino Oscillations with an Accelerator-Produced Off-Axis Beam.

T2K reports its first measurements of the parameters governing the disappearance of ν[over ¯]_{μ} in an off-axis beam due to flavor change induced by neutrino oscillations. The quasimonochromatic ν[over ¯]_{μ} beam, produced with a peak energy of 0.6 GeV at J-PARC, is observed at the far detector Super-Kamiokande, 295 km away, where the ν[over ¯]_{μ} survival probability is expected to be minimal.

Measurement of the inclusive electron neutrino charged current cross section on carbon with the T2K near detector.

The T2K off-axis near detector ND280 is used to make the first differential cross-section measurements of electron neutrino charged current interactions at energies ∼1  GeV as a function of electron momentum, electron scattering angle, and four-momentum transfer of the interaction. The total flux-averaged ν(e) charged current cross section on carbon is measured to be ⟨σ⟩(ϕ)=1.11±0.

Precise measurement of the neutrino mixing parameter θ23 from muon neutrino disappearance in an off-axis beam.

New data from the T2K neutrino oscillation experiment produce the most precise measurement of the neutrino mixing parameter θ23. Using an off-axis neutrino beam with a peak energy of 0.6 GeV and a data set corresponding to 6.

Observation of electron neutrino appearance in a muon neutrino beam.

The T2K experiment has observed electron neutrino appearance in a muon neutrino beam produced 295 km from the Super-Kamiokande detector with a peak energy of 0.6 GeV. A total of 28 electron neutrino events were detected with an energy distribution consistent with an appearance signal, corresponding to a significance of 7.

Measurement of neutrino oscillation parameters from muon neutrino disappearance with an off-axis beam.

The T2K Collaboration reports a precision measurement of muon neutrino disappearance with an off-axis neutrino beam with a peak energy of 0.6 GeV. Near detector measurements are used to constrain the neutrino flux and cross section parameters.

Indication of electron neutrino appearance from an accelerator-produced off-axis muon neutrino beam.

The T2K experiment observes indications of ν(μ) → ν(e) appearance in data accumulated with 1.43×10(20) protons on target. Six events pass all selection criteria at the far detector.