Search

Background Photon-counting detector (PCD) CT and deep learning noise reduction may improve spatial resolution at lower radiation doses compared with energy-integrating detector (EID) CT. Purpose To demonstrate the diagnostic impact of improved spatial resolution in whole-body low-dose CT scans for viewing multiple myeloma by using PCD CT with deep learning denoising compared with conventional EID CT. Materials and Methods Between April and July 2021, adult participants who underwent a whole-body EID CT scan were prospectively enrolled and scanned with a PCD CT system in ultra-high-resolution mode at matched radiation dose (8 mSv for an average adult) at an academic medical center. EID CT and PCD CT images were reconstructed with Br44 and Br64 kernels at 2-mm section thickness. PCD CT images were also reconstructed with Br44 and Br76 kernels at 0.6-mm section thickness. The thinner PCD CT images were denoised by using a convolutional neural network. Image quality was objectively quantified in two phantoms and a randomly selected subset of participants (10 participants; median age, 63.5 years; five men). Two radiologists scored PCD CT images relative to EID CT by using a five-point Likert scale to detect findings reflecting multiple myeloma. The scoring for the matched reconstruction series was blinded to scanner type. Reader-averaged scores were tested with the null hypothesis of equivalent visualization between EID and PCD. Results Twenty-seven participants (median age, 68 years; IQR, 61-72 years; 16 men) were included. The blinded assessment of 2-mm images demonstrated improvement in viewing lytic lesions, intramedullary lesions, fatty metamorphosis, and pathologic fractures for PCD CT versus EID CT (

To evaluate the diagnostic quality of photon-counting detector (PCD) computed tomography (CT) in patients undergoing lung cancer screening compared with conventional energy-integrating detector (EID) CT in a prospective multireader study.Patients undergoing lung cancer screening with conventional EID-CT were prospectively enrolled and scanned on a PCD-CT system using similar automatic exposure control settings and reconstruction kernels. Three thoracic radiologists blinded to CT system compared PCD-CT and EID-CT images and scored examinations using a 5-point Likert comparison score (-2 [left image is worse] to +2 [left image is better]) for artifacts, sharpness, image noise, diagnostic image quality, emphysema visualization, and lung nodule evaluation focusing on the border. Post hoc correction of Likert scores was performed such that they reflected PCD-CT performance in comparison to EID-CT. A nonreader radiologist measured objective image noise.Thirty-three patients (mean, 66.9 ± 5.6 years; 11 female; body mass index; 30.1 ± 5.1 kg/m2) were enrolled. Mean volume CT dose index for PCD-CT was lower (0.61 ± 0.21 vs 0.73 ± 0.22; P0.001). Pooled reader results showed significant differences between imaging modalities for all comparative rankings (P0.001), with PCD-CT favored for sharpness, image noise, image quality, and emphysema visualization and lung nodule border, but not artifacts. Photon-counting detector CT had significantly lower image noise (74.4 ± 10.5 HU vs 80.1 ± 8.6 HU; P = 0.048).Photon-counting detector CT with similar acquisition and reconstruction settings demonstrated improved image quality and less noise despite lower radiation dose, with improved ability to depict pulmonary emphysema and lung nodule borders compared with EID-CT at low-dose lung cancer CT screening.

A comparison of high-resolution photon-counting detector computed tomography (PCD-CT) versus energy-integrating detector (EID) CT via a phantom study using low-dose chest CT to evaluate nodule volume and airway wall thickness quantification.Twelve solid and ground-glass lung nodule phantoms with 3 diameters (5 mm, 8 mm, and 10 mm) and 2 shapes (spherical and star-shaped) and 12 airway tube phantoms (wall thicknesses, 0.27-1.54 mm) were placed in an anthropomorphic chest phantom. The phantom was scanned with EID-CT and PCD-CT at 5 dose levels (CTDIvol = 0.1-0.8 mGy at Sn-100 kV, 7.35 mGy at 120 kV). All images were iteratively reconstructed using matched kernels for EID-CT and medium-sharp kernel (MK) PCD-CT and an ultra-sharp kernel (USK) PCD-CT kernel, and image noise at each dose level was quantified. Nodule volumes were measured using semiautomated segmentation software, and the accuracy was expressed as the percentage error between segmented and reference volumes. Airway wall thicknesses were measured, and the root-mean-square error across all tubes was evaluated.MK PCD-CT images had the lowest noise. At 0.1 mGy, the mean volume accuracy for the solid and ground-glass nodules was improved in USK PCD-CT (3.1% and 3.3% error) compared with MK PCD-CT (9.9% and 10.2% error) and EID-CT images (11.4% and 9.2% error), respectively. At 0.2 mGy and 0.8 mGy, the wall thickness root-mean-square error values were 0.42 mm and 0.41 mm for EID-CT, 0.54 mm and 0.49 mm for MK PCD-CT, and 0.23 mm and 0.16 mm for USK PCD-CT.USK PCD-CT provided more accurate lung nodule volume and airway wall thickness quantification at lower radiation dose compared with MK PCD-CT and EID-CT.

A common rule of thumb for object detection is the Rose criterion, which states that a signal must be five standard deviations above background to be detectable to a human observer. The validity of the Rose criterion in CT imaging is limited due to the presence of correlated noise. Recent reconstruction and denoising methodologies are also able to restore apparent image quality in very noisy conditions, and the ultimate limits of these methodologies are not yet known.To establish a lower bound on the minimum achievable signal-to-noise ratio (SNR) for object detection, below which detection performance is poor regardless of reconstruction or denoising methodology.We consider a numerical observer that operates on projection data and has perfect knowledge of the background and the objects to be detected, and determine the minimum projection SNR that is necessary to achieve predetermined lesion-level sensitivity and case-level specificity targets. We define a set of discrete signal objectsWhenEven with perfect knowledge of the background and target objects, the ideal observer still requires an SNR of approximately 5. This is a lower bound on the SNR that would be required in real conditions, where the background and target objects are not known perfectly. Algorithms that denoise lesions with less than 5 projection SNR, regardless of the denoising methodology, are expected to show vanishing effects or false positive lesions.

Assessing the reliability of convolutional neural network (CNN)-based CT imaging techniques is critical for reliable deployment in practice. Some evaluation methods exist but require full access to target CNN architecture and training data, something not available for proprietary or commercial algorithms. Moreover, there is a lack of systematic evaluation methods. To address these issues, we propose a patient-specific uncertainty and bias quantification (UNIQ) method that integrates knowledge distillation and Bayesian deep learning. Knowledge distillation creates a transparent CNN (“Student CNN”) to approximate the target non-transparent CNN (“Teacher CNN”). Student CNN is built as a Bayesian-deep-learning-based probabilistic CNN that, for each input, always generates statistical distribution of the corresponding outputs, and characterizes predictive mean and two major uncertainties – data and model uncertainty. UNIQ was evaluated using a low-dose CT denoising task. Patient and phantom scans with routine-dose and synthetic quarter-dose were used to create training, validation, and testing sets. To demonstrate, Unet and Resnet were used as backbones of Teacher CNN and Student CNN respectively and were trained using independent training sets. Student Resnet was qualitatively and quantitatively evaluated. The pixel-wise predictive mean, data uncertainty, and model uncertainty from Student Resnet were very similar to the counterparts from Teacher Unet (mean-absolute-error: predictive mean 1.5HU, data uncertainty 1.8HU, model uncertainty 1.3HU; mean 2D correlation coefficient: total uncertainty 0.90, data uncertainty 0.86, model uncertainty 0.83). The proposed UNIQ can potentially systematically characterize the reliability of non-transparent CNN models used in CT.

Deep convolutional neural network (DCNN)-based noise reduction methods have been increasingly deployed in clinical CT. Accurate assessment of their spatial resolution properties is required. Spatial resolution is typically measured on physical phantoms, which may not represent the true performance of DCNN in patients as it is typically trained and tested with patient images and the generalizability of DNN to physical phantoms is questionable. In this work, we proposed a patient-data-based framework to measure the spatial resolution of DCNN methods, which involves lesion- and noise-insertion in projection domain, lesion ensemble averaging, and modulation transfer function measurement using an oversampled edge spread function from the cylindrical lesion signal. The impact of varying lesion contrast, dose levels, and CNN denoising strengths were investigated for a ResNet-based DCNN model trained using patient images. The spatial resolution degradation of DCNN reconstructions becomes more severe as the contrast or radiation dose decreased, or DCNN denoising strength increased. The measured 50%/10% MTF spatial frequencies of DCNN with highest denoising strength were (−500 HU:0.36/0.72 mm(−1); −100 HU:0.32/0.65 mm(−1); −50 HU:0.27/0.53 mm(−1); −20 HU:0.18/0.36 mm(−1); −10 HU:0.15/0.30 mm(−1)), while the 50%/10% MTF values of FBP were almost kept constant of 0.38/0.76 mm(−1).

Purpose Conventional model observers (MO) in CT are often limited to a uniform background or varying background that is random and can be modelled in an analytical form. It is unclear if these conventional MOs can be readily generalized to predict human observer performance in clinical CT tasks that involve realistic anatomical background. Deep-learning-based model observers (DL-MO) have recently been developed, but have not been validated for challenging low contrast diagnostic tasks in abdominal CT. We consequently sought to validate a DL-MO for a low-contrast hepatic metastases localization task. Methods We adapted our recently-developed DL-MO framework for the liver metastases localization task. Our previously-validated projection-domain lesion- / noise-insertion techniques were used to synthesize realistic positive and low-dose abdominal CT exams, using the archived patient projection data. Ten experimental conditions were generated, which involved different lesion sizes / contrasts, radiation dose levels, and image reconstruction types. Each condition included 100 trials generated from a patient cohort of 7 cases. Each trial was presented as liver image patches (160×160×5 voxels). The DL-MO performance was calculated for each condition and was compared with human observer performance, which was obtained by 3 sub-specialized radiologists in an observer study. The performance of DL-MO and radiologists was gauged by the area under localization receiver-operating-characteristic curves. The generalization performance of the DL-MO was estimated with the repeated 2-fold cross-validation method over the same set of trials used in human observer study. A multi-slice Channelized Hoteling Observers (CHO) was compared with the DL-MO across the same experimental conditions. Results The performance of DL-MO was highly correlated to that of radiologists (Pearson's correlation coefficient: 0.987; 95% C.I.: 0.942, 0.997). The performance level of DL-MO was comparable to that of the grouped radiologists, i.e. the mean performance difference was -3.3%. The CHO performance was poorer than the grouped radiologist performance, before internal noise could be added. The correlation between CHO and radiologists was weaker (Pearson's correlation coefficient: 0.812, and 95% C.I.: [0.378, 0.955]), and the corresponding performance bias (-29.5%) was statistically significant. Conclusion The presented study demonstrated the potential of using the DL-MO for image quality assessment in patient abdominal CT tasks. This article is protected by copyright. All rights reserved.

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. This work outlines a technique to optimize CNN denoising models using methods that are available in a routine clinical setting.To demonstrate a phantom-based training framework for CNN noise reduction that can be efficiently implemented on any CT scanner.The 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.When 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.The 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.

Photon-counting detector (PCD) CT has emerged as a novel imaging modality that represents a fundamental shift in the way that CT systems detect X-rays. Following preclinical and clinical investigations showing benefits of PCD CT for a range of imaging tasks, the first commercial PCD CT system was approved by the U.S. FDA for clinical use in 2021. The technologic features of PCD CT are particularly well suited for musculoskeletal imaging applications. Advantages of PCD CT compared with conventional energy-integrating detector CT include smaller detector pixels and excellent geometric dose efficiency that enable ultra-high-spatial resolution imaging of large joints and central skeletal anatomy; advanced multi-energy spectral postprocessing that allows quantification of gouty deposits and generation of virtual non-calcium images to visualize bone edema; improved metal artifact reduction for imaging of orthopedic implants; as well as higher CNR and suppression of electronic noise. Given substantially improved cortical and trabecular detail, PCD CT images more clearly depict skeletal pathologies including fractures, lytic lesions, and mineralized tumor matrix. This article reviews the technical features of PCD CT and their associated impact for musculoskeletal imaging applications, using clinical examples to compare EID CT and PCD CT.

Background Substantial interreader variability exists for common tasks in CT imaging, such as detection of hepatic metastases. This variability can undermine patient care by leading to misdiagnosis. Purpose To determine the impact of interreader variability associated with

Modern high-performance CT scanners are unparalleled among three-dimensional imaging systems in data acquisition speed and spatial resolution.

OBJECTIVE To investigate reader performance as a function of patient size for the detection of hepatic metastases when an automatic exposure control (AEC) system is used, which varies image noise as a function of patient size. METHODS Abdominal computed tomograhy examinations across 100, 120, 160, and 200 quality reference tube current-time product were collected, involving a cohort of 83 patients. Three radiologists identified hepatic metastases across all dose levels. Partial Spearman rank correlation and multivariate logistic regression were used to evaluate correlations between reader performance and patient size and lesion size/contrast while accounting for potential confounding effects. Analyses were repeated on an emulated less-variable noise AEC. RESULTS No statistically significant correlation was observed between patient size and radiologist performance (for variable-noise AEC: range of partial Spearman ρ, -0.157 to -0.035]; range of adjusted odds ratios, 0.987, 1.006). CONCLUSIONS Reader performance was independent of patient size, suggesting that variable-noise AEC provides better modulation for larger patients than constant-noise AEC.

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. Six examinations were reserved for testing; these were reconstructed with 100 to 450 mm of FOV, smooth to sharp kernels, and 1 to 5 mm of thickness. RESULTS: When test and training reconstruction settings were not matched, there was either reduced denoising efficiency or resolution degradation. Denoising efficiency was reduced when FOV was decreased or a smoother kernel was used. Resolution loss occurred when the network was applied to an increased FOV, sharper kernel, or decreased image thickness. CONCLUSIONS: The CNN denoising performance was degraded with variations in FOV, kernel, or decreased thickness. Denoising performance was not affected by increased thickness.

Recently developed x-ray transmittance modeling-based three-step algorithm compensates for the spectral distortion in the photon-counting detector (PCD) and estimates the line-integrals of the basis materials. The x-ray transmittance modeling linearizes the nonlinear forward imaging model and derives a computationally efficient three-step algorithm that achieves almost unbiased and minimum variance estimator. In this article, we apply the algorithm to the experimental data from a research whole-body PCD-computed tomography (CT) system. We perform pixel-by-pixel calibration using water-equivalent phantoms to fit the output of the scanner to the forward model and then feed the calibrated data into the three-step algorithm. Experimental data from iodine phantom and swine abdomen scans demonstrate that the proposed algorithm compensates for the spectral distortion effectively and estimates the line-integrals of two basis materials, water and iodine, efficiently. The proposed method substantially reduces the beam hardening and ring artifacts present in the test phantom compared to those of the image-based material decomposition method and the images directly reconstructed from the raw data of the system. The algorithm also exhibits less bias and comparable noise to those of the other methods for various x-ray energies.

The use of a photon counting detector in CT (PCD CT) is currently the subject of intense investigation and development. In this review article, we will describe potential clinical applications of this technology with a particular focus on the experience of our own institution with a prototype PCD CT scanner. Photon counting detectors (PCDs) have three primary advantages over conventional, energy integrating detectors (EIDs): 1) they provide spectral information without need for a dedicated dual-energy protocol; 2) they are immune to electronic noise; and 3) they can be made very high resolution without significant compromises to quantum efficiency. These advantages translate into several clinical applications. Metal artifacts, beam hardening artifacts, and noise streaks from photon starvation can be better mitigated using PCD CT. Certain incidental findings can be better characterized using the spectral information from PCD CT. High-contrast, high-resolution structures, such as the temporal bone can be better visualized using PCD CT and at greatly reduced dose. We also discuss new possibilities on the horizon, including new contrast agents, and how anticipated improvements in PCD CT will translate to performance in these applications.

The Brody II score uses chest CT to guide therapeutic changes in children with cystic fibrosis; however, patients and providers are often reticent to undergo chest CT given concerns about radiation.We sought to determine the ability of a reduced-dose photon-counting detector (PCD) chest CT protocol to reproducibly display pulmonary disease severity using the Brody II score for children with cystic fibrosis (CF) scanned at radiation doses similar to those of a chest radiograph.Pediatric patients with CF underwent non-contrast reduced-dose chest PCD-CT. Volumetric inspiratory and expiratory scans were obtained without sedation or anesthesia. Three pediatric radiologists with Certificates of Added Qualification scored each scan on an ordinal scale and assigned a Brody II score to grade bronchiectasis, peribronchial thickening, parenchymal opacity, air trapping and mucus plugging. We report image-quality metrics using descriptive statistics. To calculate inter-rater agreement for Brody II scoring, we used the Krippendorff alpha and intraclass correlation coefficient (ICC).Fifteen children with CF underwent reduced-dose PCD chest CT in both inspiration and expiration (mean age 8.9 years, range, 2.5-17.5 years; 4 girls). Mean volumetric CT dose index (CTDIReduced-dose PCD-CT permits diagnostic image quality and reproducible identification of Brody II scoring imaging findings at radiation doses similar to those for chest radiography.

As deep-learning-based denoising and reconstruction methods are gaining more popularity in clinical CT, it is of vital importance that these new algorithms undergo rigorous and objective image quality assessment beyond traditional metrics to ensure diagnostic information is not sacrificed. Channelized Hotelling observer (CHO), which has been shown to be well correlated with human observer performance in many clinical CT tasks, has a great potential to become the method of choice for objective image quality assessment for these non-linear methods. However, practical use of CHO beyond research labs have been quite limited, mostly due to the strict requirement on a large number of repeated scans to ensure sufficient accuracy and precision in CHO computation and the lack of efficient and widely acceptable phantom-based method. In our previous work, we developed an efficient CHO model observer for accurate and precise measurement of low-contrast detectability with only 1–3 repeated scans on the most widely used ACR accreditation phantom. In this work, we applied this optimized CHO model observer to evaluating the low-contrast detectability of a deep learning-based reconstruction (DLIR) equipped on a GE Revolution scanner. The commercially available DLIR reconstruction method showed consistent increase in low-contrast detectability over the FBP and the IR method at routine dose levels, which suggests potential dose reduction to the FBP reconstruction by up to 27.5%.

This study evaluated the clinical utility of a phantom-based convolutional neural network noise reduction framework for whole-body-low-dose CT skeletal surveys. 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. Images were reconstructed with either iterative reconstruction or filtered back projection with convolutional neural network post-processing. Diagnostic quality and structure visualization were blindly rated (subjective scale ranging from 0 [poor] to 100 [excellent]) by three musculoskeletal radiologists for iterative reconstruction and convolutional neural network images at routine whole-body-low-dose and 25% dose CT. For the diagnostic quality rating, the convolutional neural network outscored iterative reconstruction at routine whole-body-low-dose CT (convolutional neural network: 95 ± 5, iterative reconstruction: 85 ± 8) and at the 25% dose level (convolutional neural network: 79 ± 10, iterative reconstruction: 22 ± 13). Convolutional neural network applied to 25% dose was rated inferior to iterative reconstruction applied to routine dose. Similar trends were observed in rating experiments focusing on structure visualization. Results indicate that the phantom-based convolutional neural network noise reduction framework can improve visualization of critical structures within CT skeletal surveys. At matched dose level, the convolutional neural network outscored iterative reconstruction for all conditions studied. The image quality improvement of convolutional neural network applied to 25% dose indicates a potential for dose reduction; however, the 75% dose reduction condition studied is not currently recommended for clinical implementation.

Eye-tracking techniques can be used to understand the visual search process in diagnostic radiology. Nonetheless, most prior eye-tracking studies in CT only involved single cross-sectional images or video playback of the reconstructed volume and meanwhile applied strong constraints to reader-image interactivity, yielding a disconnection between the corresponding experimental setup and clinical reality. To overcome this limitation, we developed an eye-tracking system that integrates eye-tracking hardware with in-house-built image viewing software. This system enabled recording of radiologists’ real-time eye-movement and interactivity with the displayed images in clinically relevant tasks. In this work, the system implementation was demonstrated, and the spatial accuracy of eye-tracking data was evaluated using digital phantom images and patient CT angiography exam. The measured offset between targets and gaze points was comparable to that of many prior eye-tracking systems (The median offset: phantom – visual angle ~0.8°; patient CTA – visual angle ~0.7 – 1.3°). Further, the eye-tracking system was used to record radiologists’ visual search in a liver lesion detection task with contrast-enhanced abdominal CT. From the measured data, several variables were found to correlate with radiologists’ sensitivity, e.g., mean sensitivity of readers with longer interpretation time was higher than that of the others (88 ± 3% vs 78 ± 10%; p < 0.001). In summary, the proposed eye-tracking system has the potential of providing high-quality data to characterize radiologists’ visual-search process in clinical CT tasks.