Huber, Nathan R.

Introduction: This study aimed to develop and evaluate a deep learning (DL) deblurring algorithm for computed tomography (CT). Phantom testing assessed whether DL deblurring could improve CT image quality and coronary artery calcium (CAC) detectability. Materials and Methods: The algorithm consisted of 2 sequential convolutional neural networks (CNNs): one for denoising and one for deblurring. After deblurring, the estimated noise from the first model was reintroduced to preserve image texture. The CNN denoising model was trained to map high-noise images to routine low-noise ones. The CNN deblurring model was trained using natural images—blurred inputs paired with sharp targets. To assess performance, an anthropomorphic phantom with 100 small calcifications was scanned on a CT system using a CAC scoring protocol. Data were acquired at clinical and high doses, then reconstructed with and without DL deblurring, using 25% of the maximum denoising strength. Detectability was defined as the ability to calculate an Agatston score (≥3 adjacent voxels >130 HU). Results: At high dose, CAC detectability increased from 39% (standard reconstruction) to 48% with deblurring. Similar detectability (39%) was achieved at the routine dose with deblurring, representing a 6% improvement compared with the original routine dose data. Discussion: Quantitative results from phantom testing demonstrate that DL deblurring can improve image quality, based on a clinically relevant, task-based CAC detection metric at clinical dose levels.

Objective: The purpose of this study was to evaluate the potential clinical value of spectral CT for image guidance during percutaneous thermal ablation, particularly investigating high monoenergetic (MonoE) for metal artifact reduction. Materials and Methods: A phantom experiment was performed in which an ablation probe was scanned in “continuous CT” (CCT) mode on a spectral CT scanner. ROI measurements quantified metal artifacts for conventional and MonoE CCT images. Subsequently, a retrospective reader study was conducted with 10 patient cases. Three radiologists reviewed cases to select the optimal MonoE setting and perform a Likert score rating (+2: MonoE preferred, −2: conventional preferred). Results: Phantom measurements indicated a reduction in metal artifact for high MonoE (150 keV: −46 HU) relative to conventional CCT (−122 HU). The MonoE setting preference was 151±21 keV. The mean Likert score was 1.2±0.7. Radiologists indicated a perceived benefit of high MonoE CCT when probe placement was near a critical structure. Conclusions: This study indicates a clinical preference for high MonoE CCT compared with conventional CCT. Insofar as spectral CCT can be offered at a clinically feasible time frame, our results support the assessment of 150 keV image to reduce metal artifact while maintaining satisfactory soft tissue contrast.

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). A non-reader neuroradiologist established the reference standard. Three neuroradiologists reviewed two routine clinical series (head and bone kernels) and a single ZIRCON series, detecting intracranial findings or fractures and rating confidence (0–100). Sensitivity, specificity, and jackknife free-response receiver operating characteristic (JAFROC) figure of merit (FOM) were compared (limit of non-inferiority: −0.10). Results ZIRCON and conventional images demonstrated comparable performance for fractures (sensitivity: 51.5% vs. 54.5%; specificity: 40.2% vs. 34.2%) and intracranial findings (sensitivity: 88.2% vs. 91.4%; specificity: 77.2% vs. 73.7%).The estimated difference of JAFROC FOM demonstrated ZIRCON non-inferiority for acute pathologies overall (0.003 [95% CI=−0.051–0.057]) and fractures (0.048 [95% CI=−0.050–0.145]) but not for intracranial findings alone (−0.024 [95% CI=−0.100–0.052]). Conclusion Thin-slice, low noise, and high spatial resolution images can be created to display intracranial findings and fractures replacing multiple images series in head CT with similar performance. Future studies in more patients and further algorithmic development are warranted.

Objective Noise quantification is fundamental to computed tomography (CT) image quality assessment and protocol optimization. This study proposes a deep learning–based framework, Single-scan Image Local Variance EstimatoR (SILVER), for estimating the local noise level within each region of a CT image. The local noise level will be referred to as a pixel-wise noise map. Methods The SILVER architecture resembled a U-Net convolutional neural network with mean-square-error loss. To generate training data, 100 replicate scans were acquired of 3 anthropomorphic phantoms (chest, head, and pelvis) using a sequential scan mode; 120,000 phantom images were allocated into training, validation, and testing data sets. Pixel-wise noise maps were calculated for the phantom data by taking the per-pixel SD from the 100 replicate scans. For training, the convolutional neural network inputs consisted of phantom CT image patches, and the training targets consisted of the corresponding calculated pixel-wise noise maps. Following training, SILVER noise maps were evaluated using phantom and patient images. For evaluation on patient images, SILVER noise maps were compared with manual noise measurements at the heart, aorta, liver, spleen, and fat. Results When tested on phantom images, the SILVER noise map prediction closely matched the calculated noise map target (root mean square error <8 Hounsfield units). Within 10 patient examinations, SILVER noise map had an average percent error of 5% relative to manual region-of-interest measurements. Conclusion The SILVER framework enabled accurate pixel-wise noise level estimation directly from patient images. This method is widely accessible because it operates in the image domain and requires only phantom data for training.

AbstractBackgroundSmall coronary arteries containing stents pose a challenge in CT imaging due to metal‐induced blooming artifact. High spatial resolution imaging capability is as the presence of highly attenuating materials limits noninvasive assessment of luminal patency.PurposeThe purpose of this study was to quantify the effective lumen diameter within coronary stents using a clinical photon‐counting‐detector (PCD) CT in concert with a convolutional neural network (CNN) denoising algorithm, compared to an energy‐integrating‐detector (EID) CT system.MethodsSeven coronary stents of different materials and inner diameters between 3.43 and 4.72 mm were placed in plastic tubes of diameters 3.96–4.87 mm containing 20 mg/mL of iodine solution, mimicking stented contrast‐enhanced coronary arteries. Tubes were placed parallel with or perpendicular to the scanner's z‐axis in an anthropomorphic phantom emulating an average‐sized patient and scanned with a clinical EID‐CT and PCD‐CT. EID scans were performed using our standard coronary computed tomography angiography (cCTA) protocol (120 kV, 180 quality reference mAs). PCD scans were performed using the ultra‐high‐resolution (UHR) mode (120 × 0.2 mm collimation) at 120 kV with tube current adjusted so that CTDIvol was matched to that of EID scans. EID images were reconstructed per our routine clinical protocol (Br40, 0.6 mm thickness), and with the sharpest available kernel (Br69). PCD images were reconstructed at a thickness of 0.6 mm and a dedicated sharp kernel (Br89) which is only possible with the PCD UHR mode. To address increased image noise introduced by the Br89 kernel, an image‐based CNN denoising algorithm was applied to the PCD images of stents scanned parallel to the scanner's z‐axis. Stents were segmented based on full‐width half maximum thresholding and morphological operations, from which effective lumen diameter was calculated and compared to reference sizes measured with a caliper.ResultsSubstantial blooming artifacts were observed on EID Br40 images, resulting in larger stent struts and reduced lumen diameter (effective diameter underestimated by 41% and 47% for parallel and perpendicular orientations, respectively). Blooming artifacts were observed on EID Br69 images with 19% and 31% underestimation of lumen diameter compared to the caliper for parallel and perpendicular scans, respectively. Overall image quality was substantially improved on PCD, with higher spatial resolution and reduced blooming artifacts, resulting in the clearer delineation of stent struts. Effective lumen diameters were underestimated by 9% and 19% relative to the reference for parallel and perpendicular scans, respectively. CNN reduced image noise by about 50% on PCD images without impacting lumen quantification (<0.3% difference).ConclusionThe PCD UHR mode improved in‐stent lumen quantification for all seven stents as compared to EID images due to decreased blooming artifacts. Implementation of CNN denoising algorithms to PCD data substantially improved image quality.

AbstractBackgroundPhoton‐counting‐detector CT (PCD‐CT) enables the production of virtual monoenergetic images (VMIs) at a high spatial resolution (HR) via simultaneous acquisition of multi‐energy data. However, noise levels in these HR VMIs are markedly increased.PurposeTo develop a deep learning technique that utilizes a lower noise VMI as prior information to reduce image noise in HR, PCD‐CT coronary CT angiography (CTA).MethodsCoronary CTA exams of 10 patients were acquired using PCD‐CT (NAEOTOM Alpha, Siemens Healthineers). A prior‐information‐enabled neural network (Pie‐Net) was developed, treating one lower‐noise VMI (e.g., 70 keV) as a prior input and one noisy VMI (e.g., 50 keV or 100 keV) as another. For data preprocessing, noisy VMIs were reconstructed by filtered back‐projection (FBP) and iterative reconstruction (IR), which were then subtracted to generate “noise‐only” images. Spatial decoupling was applied to the noise‐only images to mitigate overfitting and improve randomization. Thicker slice averaging was used for the IR and prior images. The final training inputs for the convolutional neural network (CNN) inside the Pie‐Net consisted of thicker‐slice signal images with the reinsertion of spatially decoupled noise‐only images and the thicker‐slice prior images. The CNN training labels consisted of the corresponding thicker‐slice label images without noise insertion. Pie‐Net's performance was evaluated in terms of image noise, spatial detail preservation, and quantitative accuracy, and compared to a U‐net‐based method that did not include prior information.ResultsPie‐Net provided strong noise reduction, by 95 ± 1% relative to FBP and by 60 ± 8% relative to IR. For HR VMIs at different keV (e.g., 50 keV or 100 keV), Pie‐Net maintained spatial and spectral fidelity. The inclusion of prior information from the PCD‐CT data in the spectral domain was able to improve a robust deep learning‐based denoising performance compared to the U‐net‐based method, which caused some loss of spatial detail and introduced some artifacts.ConclusionThe proposed Pie‐Net achieved substantial noise reduction while preserving HR VMI's spatial and spectral properties.

AbstractBackgroundDeep 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. This work outlines a technique to optimize CNN denoising models using methods that are available in a routine clinical setting.PurposeTo demonstrate a phantom‐based training framework for CNN noise reduction that can be efficiently implemented on any CT scanner.MethodsThe phantom‐based training framework uses supervised learning in which training data are synthesized using an image‐based noise insertion technique. Ten patient image series were used for training and validation (9:1) and noise‐only images obtained from anthropomorphic phantom scans. Phantom noise‐only images were superimposed on patient images to imitate low‐dose CT images for use in training. A modified U‐Net architecture was used with mean‐squared‐error and feature reconstruction loss. The training framework was tested for clinically indicated whole‐body‐low‐dose CT images, as well as routine abdomen‐pelvis exams for which projection data was unavailable. Performance was assessed based on root‐mean‐square error, structural similarity, line profiles, and visual assessment.ResultsWhen the CNN was tested on five reserved quarter‐dose whole‐body‐low‐dose CT images, noise was reduced by 75%, root‐mean‐square‐error reduced by 34%, and structural similarity increased by 60%. Visual analysis and line profiles indicated that the method significantly reduced noise while maintaining spatial resolution of anatomic features.ConclusionThe proposed phantom‐based training framework demonstrated strong noise reduction while preserving spatial detail. Because this method is based within the image domain, it can be easily implemented without access to projection data.