The influence of motion-compensated reconstruction on coronary artery analysis for a dual-layer detector CT system: a dynamic phantom study.

OBJECTIVES: Cardiac motion artifacts hinder the assessment of coronary arteries in coronary computed tomography angiography (CCTA). We investigated the impact of motion compensation reconstruction (MCR) on motion artifacts in CCTA at various heart rates (HR) using a dynamic phantom. MATERIALS AND METHODS: An artificial hollow coronary artery (5-mm diameter lumen) filled with iodinated contrast agent (400 HU at 120 kVp), positioned centrally in an anthropomorphic chest phantom, was scanned using a dual-layer spectral detector CT. The artery was translated at constant horizontal velocities (0-80 mm/s, increment of 10 mm/s). For each velocity, five CCTA scans were repeated using a clinical protocol. Motion artifacts were quantified using the in-plane motion area. Regression analysis was performed to calculate the reduction in motion artifacts provided by MCR, by division of the slopes of non-MCR and MCR fitted lines. RESULTS: Reference mean (95% confidence interval) motion artifact area was 24.9 mm2 (23.8, 26.0). Without MCR, motion artifact areas for velocities exceeding 20 mm/s were significantly larger (up to 57.2 mm2 (40.1, 74.2)) than the reference. With MCR, no significant differences compared to the reference were shown for all velocities, except for 70 mm/s (29.0 mm2 (27.0, 31.0)). The slopes of the fitted data were 0.44 and 0.04 for standard and MCR reconstructions, respectively, resulting in an 11-time motion artifact reduction. CONCLUSION: MCR may improve CCTA assessment in patients by reducing coronary artery motion artifacts, especially in those with elevated HR who cannot receive beta blockers or do not attain the targeted HR. CLINICAL RELEVANCE STATEMENT: This vendor-specific motion compensation reconstruction may improve coronary computed tomography angiography assessment in patients by reduction of coronary artery motion artifacts, especially in those with elevated various heart rates (HR) who cannot receive beta blockers or do not attain the targeted HR. KEY POINTS: • Motion artifacts are known to hinder the assessment of coronary arteries on coronary CT angiography (CCTA), leading to more non-diagnostic scans. • This dynamic phantom study shows that motion compensation reconstruction (MCR) reduces motion artifacts at various velocities, which may help to decrease the number of non-diagnostic scans. • MCR in this study showed to reduce motion artifacts 11-fold.

Robustness of pulmonary nodule radiomic features on computed tomography as a function of varying radiation dose levels-a multi-dose in vivo patient study.

OBJECTIVE: Analysis of textural features of pulmonary nodules in chest CT, also known as radiomics, has several potential clinical applications, such as diagnosis, prognostication, and treatment response monitoring. For clinical use, it is essential that these features provide robust measurements. Studies with phantoms and simulated lower dose levels have demonstrated that radiomic features can vary with different radiation dose levels. This study presents an in vivo stability analysis of radiomic features for pulmonary nodules against varying radiation dose levels. METHODS: Nineteen patients with a total of thirty-five pulmonary nodules underwent four chest CT scans at different radiation dose levels (60, 33, 24, and 15 mAs) in a single session. The nodules were manually delineated. To assess the robustness of features, we calculated the intra-class correlation coefficient (ICC). To visualize the effect of milliampere-second variation on groups of features, a linear model was fitted to each feature. We calculated bias and calculated the R2 value as a measure of goodness of fit. RESULTS: A small minority of 15/100 (15%) radiomic features were considered stable (ICC > 0.9). Bias increased and R2 decreased at lower dose, but shape features seemed to be more robust to milliampere-second variations than other feature classes. CONCLUSION: A large majority of pulmonary nodule radiomic features were not inherently robust to radiation dose level variations. For a subset of features, it was possible to correct this variability by a simple linear model. However, the correction became increasingly less accurate at lower radiation dose levels. CLINICAL RELEVANCE STATEMENT: Radiomic features provide a quantitative description of a tumor based on medical imaging such as computed tomography (CT). These features are potentially useful in several clinical tasks such as diagnosis, prognosis prediction, treatment effect monitoring, and treatment effect estimation. KEY POINTS: • The vast majority of commonly used radiomic features are strongly influenced by variations in radiation dose level. • A small minority of radiomic features, notably the shape feature class, are robust against dose-level variations according to ICC calculations. • A large subset of radiomic features can be corrected by a linear model taking into account only the radiation dose level.

Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis.

OBJECTIVES: To evaluate the added value of deep learning (DL) analysis of the left ventricular myocardium (LVM) in resting coronary CT angiography (CCTA) over determination of coronary degree of stenosis (DS), for identification of patients with functionally significant coronary artery stenosis. METHODS: Patients who underwent CCTA prior to an invasive fractional flow reserve (FFR) measurement were retrospectively selected. Highest DS from CCTA was used to classify patients as having non-significant (≤ 24% DS), intermediate (25-69% DS), or significant stenosis (≥ 70% DS). Patients with intermediate stenosis were referred for fully automatic DL analysis of the LVM. The DL algorithm characterized the LVM, and likely encoded information regarding shape, texture, contrast enhancement, and more. Based on these encodings, features were extracted and patients classified as having a non-significant or significant stenosis. Diagnostic performance of the combined method was evaluated and compared to DS evaluation only. Functionally significant stenosis was defined as FFR ≤ 0.8 or presence of angiographic high-grade stenosis (≥ 90% DS). RESULTS: The final study population consisted of 126 patients (77% male, 59 ± 9 years). Eighty-one patients (64%) had a functionally significant stenosis. The proposed method resulted in improved discrimination (AUC = 0.76) compared to classification based on DS only (AUC = 0.68). Sensitivity and specificity were 92.6% and 31.1% for DS only (≥ 50% indicating functionally significant stenosis), and 84.6% and 48.4% for the proposed method. CONCLUSION: The combination of DS with DL analysis of the LVM in intermediate-degree coronary stenosis may result in improved diagnostic performance for identification of patients with functionally significant coronary artery stenosis. KEY POINTS: • Assessment of degree of coronary stenosis on CCTA has consistently high sensitivity and negative predictive value, but has limited specificity for identifying the functional significance of a stenosis. • Deep learning algorithms are able to learn complex patterns and relationships directly from the images without prior specification of which image features represent presence of disease, and thereby may be more sensitive to subtle changes in the LVM caused by functionally significant stenosis. • Addition of deep learning analysis of the left ventricular myocardium to the evaluation of degree of coronary artery stenosis improves diagnostic performance and increases specificity of resting CCTA. This could potentially decrease the number of patients undergoing invasive coronary angiography.

Accuracy of iodine quantification using dual energy CT in latest generation dual source and dual layer CT.

OBJECTIVE: To determine the accuracy of iodine quantification with dual energy computed tomography (DECT) in two high-end CT systems with different spectral imaging techniques. METHODS: Five tubes with different iodine concentrations (0, 5, 10, 15, 20 mg/ml) were analysed in an anthropomorphic thoracic phantom. Adding two phantom rings simulated increased patient size. For third-generation dual source CT (DSCT), tube voltage combinations of 150Sn and 70, 80, 90, 100 kVp were analysed. For dual layer CT (DLCT), 120 and 140 kVp were used. Scans were repeated three times. Median normalized values and interquartile ranges (IQRs) were calculated for all kVp settings and phantom sizes. RESULTS: Correlation between measured and known iodine concentrations was excellent for both systems (R = 0.999-1.000, p < 0.0001). For DSCT, median measurement errors ranged from -0.5% (IQR -2.0, 2.0%) at 150Sn/70 kVp and -2.3% (IQR -4.0, -0.1%) at 150Sn/80 kVp to -4.0% (IQR -6.0, -2.8%) at 150Sn/90 kVp. For DLCT, median measurement errors ranged from -3.3% (IQR -4.9, -1.5%) at 140 kVp to -4.6% (IQR -6.0, -3.6%) at 120 kVp. Larger phantom sizes increased variability of iodine measurements (p < 0.05). CONCLUSION: Iodine concentration can be accurately quantified with state-of-the-art DECT systems from two vendors. The lowest absolute errors were found for DSCT using the 150Sn/70 kVp or 150Sn/80 kVp combinations, which was slightly more accurate than 140 kVp in DLCT. KEY POINTS: • High-end CT scanners allow accurate iodine quantification using different DECT techniques. • Lowest measurement error was found in scans with largest photon energy separation. • Dual-source CT quantified iodine slightly more accurately than dual layer CT.

Feasibility and accuracy of dual-layer spectral detector computed tomography for quantification of gadolinium: a phantom study.

OBJECTIVES: The aim of this study was to evaluate the feasibility and accuracy of dual-layer spectral detector CT (SDCT) for the quantification of clinically encountered gadolinium concentrations. METHODS: The cardiac chamber of an anthropomorphic thoracic phantom was equipped with 14 tubular inserts containing different gadolinium concentrations, ranging from 0 to 26.3 mg/mL (0.0, 0.1, 0.2, 0.4, 0.5, 1.0, 2.0, 3.0, 4.0, 5.1, 10.6, 15.7, 20.7 and 26.3 mg/mL). Images were acquired using a novel 64-detector row SDCT system at 120 and 140 kVp. Acquisitions were repeated five times to assess reproducibility. Regions of interest (ROIs) were drawn on three slices per insert. A spectral plot was extracted for every ROI and mean attenuation profiles were fitted to known attenuation profiles of water and pure gadolinium using in-house-developed software to calculate gadolinium concentrations. RESULTS: At both 120 and 140 kVp, excellent correlations between scan repetitions and true and measured gadolinium concentrations were found (R > 0.99, P < 0.001; ICCs > 0.99, CI 0.99-1.00). Relative mean measurement errors stayed below 10% down to 2.0 mg/mL true gadolinium concentration at 120 kVp and below 5% down to 1.0 mg/mL true gadolinium concentration at 140 kVp. CONCLUSION: SDCT allows for accurate quantification of gadolinium at both 120 and 140 kVp. Lowest measurement errors were found for 140 kVp acquisitions. KEY POINTS: • Gadolinium quantification may be useful in patients with contraindication to iodine. • Dual-layer spectral detector CT allows for overall accurate quantification of gadolinium. • Interscan variability of gadolinium quantification using SDCT material decomposition is excellent.

Accuracy of bone mineral density quantification using dual-layer spectral detector CT: a phantom study.

OBJECTIVES: To investigate the accuracy of bone mineral density (BMD) quantification using dual-layer spectral detector CT (SDCT) at various scan protocols. METHODS: Two validated anthropomorphic phantoms containing inserts of 50-200 mg/cm3 calcium hydroxyapatite (HA) were scanned using a 64-slice SDCT scanner at various acquisition protocols (120 and 140 kVp, and 50, 100 and 200 mAs). Regions of interest (ROIs) were placed in each insert and mean attenuation profiles at monochromatic energy levels (90-200 keV) were constructed. These profiles were fitted to attenuation profiles of pure HA and water to calculate HA concentrations. For comparison, one phantom was scanned using dual energy X-ray absorptiometry (DXA). RESULTS: At both 120 and 140 kVp, excellent correlations (R = 0.97, P < 0.001) were found between true and measured HA concentrations. Mean error for all measurements at 120 kVp was -5.6 ± 5.7 mg/cm3 (-3.6 ± 3.2%) and at 140 kVp -2.4 ± 3.7 mg/cm3 (-0.8 ± 2.8%). Mean measurement errors were smaller than 6% for all acquisition protocols. Strong linear correlations (R2 ≥ 0.970, P < 0.001) with DXA were found. CONCLUSIONS: SDCT allows for accurate BMD quantification and potentially opens up the possibility for osteoporosis evaluation and opportunistic screening in patients undergoing SDCT for other clinical indications. However, patient studies are needed to extend and translate our findings. KEY POINTS: • Dual-layer spectral detector CT allows for accurate bone mineral density quantification. • BMD measurements on SDCT are strongly linearly correlated to DXA. • SDCT, acquired for several indications, may allow for evaluation of osteoporosis. • This potentially opens up the possibility for opportunistic osteoporosis screening.

Pulmonary Nodule Volumetry at Different Low Computed Tomography Radiation Dose Levels With Hybrid and Model-Based Iterative Reconstruction: A Within Patient Analysis.

OBJECTIVE: The aim of the study was to determine the effects of dose reduction and iterative reconstruction (IR) on pulmonary nodule volumetry. METHODS: In this prospective study, 25 patients scheduled for follow-up of pulmonary nodules were included. Computed tomography acquisitions were acquired at 4 dose levels with a median of 2.1, 1.2, 0.8, and 0.6 mSv. Data were reconstructed with filtered back projection (FBP), hybrid IR, and model-based IR. Volumetry was performed using semiautomatic software. RESULTS: At the highest dose level, more than 91% (34/37) of the nodules could be segmented, and at the lowest dose level, this was more than 83%. Thirty-three nodules were included for further analysis. Filtered back projection and hybrid IR did not lead to significant differences, whereas model-based IR resulted in lower volume measurements with a maximum difference of -11% compared with FBP at routine dose. CONCLUSIONS: Pulmonary nodule volumetry can be accurately performed at a submillisievert dose with both FBP and hybrid IR.

Cardiac valve calcifications on low-dose unenhanced ungated chest computed tomography: inter-observer and inter-examination reliability, agreement and variability.

OBJECTIVES: To determine inter-observer and inter-examination variability for aortic valve calcification (AVC) and mitral valve and annulus calcification (MC) in low-dose unenhanced ungated lung cancer screening chest computed tomography (CT). METHODS: We included 578 lung cancer screening trial participants who were examined by CT twice within 3 months to follow indeterminate pulmonary nodules. On these CTs, AVC and MC were measured in cubic millimetres. One hundred CTs were examined by five observers to determine the inter-observer variability. Reliability was assessed by kappa statistics (κ) and intra-class correlation coefficients (ICCs). Variability was expressed as the mean difference ± standard deviation (SD). RESULTS: Inter-examination reliability was excellent for AVC (κ = 0.94, ICC = 0.96) and MC (κ = 0.95, ICC = 0.90). Inter-examination variability was 12.7 ± 118.2 mm(3) for AVC and 31.5 ± 219.2 mm(3) for MC. Inter-observer reliability ranged from κ = 0.68 to κ = 0.92 for AVC and from κ = 0.20 to κ = 0.66 for MC. Inter-observer ICC was 0.94 for AVC and ranged from 0.56 to 0.97 for MC. Inter-observer variability ranged from -30.5 ± 252.0 mm(3) to 84.0 ± 240.5 mm(3) for AVC and from -95.2 ± 210.0 mm(3) to 303.7 ± 501.6 mm(3) for MC. CONCLUSIONS: AVC can be quantified with excellent reliability on ungated unenhanced low-dose chest CT, but manual detection of MC can be subject to substantial inter-observer variability. Lung cancer screening CT may be used for detection and quantification of cardiac valve calcifications. KEY POINTS: • Low-dose unenhanced ungated chest computed tomography can detect cardiac valve calcifications. • However, calcified cardiac valves are not reported by most radiologists. • Inter-observer and inter-examination variability of aortic valve calcifications is sufficient for longitudinal studies. • Volumetric measurement variability of mitral valve and annulus calcifications is substantial.

Statistical shape model of the talus bone morphology: A comparison between impinged and nonimpinged ankles.

Diagnosis of ankle impingement is performed primarily by clinical examination, whereas medical imaging is used for severity staging and treatment guidance. The association of impingement symptoms with regional three-dimensional (3D) bone shape variaties visible in medical images has not been systematically explored, nor do we know the type and magnitude of this relation. In this cross-sectional case-control study, we hypothesized that 3D talus bone shape could be used to quantitatively formulate the discriminating shape variations between ankles with impingement from ankles without impingement, and we aimed to characterize and quantify these variations. We used statistical shape modeling (SSM) methods to determine the most prevalent modes of shape variations that discriminate between the impinged and nonimpinged ankles. Results of the compactness and parallel analysis test on the statistical shape model identify 8 prominent shape modes of variations (MoVs) representing approximately 78% of the total 3D variations in the population of shapes, among which two modes captured discriminating features between impinged and nonimpinged ankles (p value of 0.023 and 0.042). Visual inspection confirms that these two shape modes, capturing abnormalities in the anterior and posterior parts of talus, represent the two main bony risk factors in anterior and posterior ankle impingement. In conclusion, in this research using SSM we have identified shape MoVs that were found to correlate significantly with bony ankle impingement. We also illustrated potential guidance from SSMs for surgical planning.

Coronary Artery Calcium Scoring: Toward a New Standard.

OBJECTIVES: Although the Agatston score is a commonly used quantification method, rescan reproducibility is suboptimal, and different CT scanners result in different scores. In 2007, McCollough et al (Radiology 2007;243:527-538) proposed a standard for coronary artery calcium quantification. Advancements in CT technology over the last decade, however, allow for improved acquisition and reconstruction methods. This study aims to investigate the feasibility of a reproducible reduced dose alternative of the standardized approach for coronary artery calcium quantification on state-of-the-art CT systems from 4 major vendors. MATERIALS AND METHODS: An anthropomorphic phantom containing 9 calcifications and 2 extension rings were used. Images were acquired with 4 state-of-the-art CT systems using routine protocols and a variety of tube voltages (80-120 kV), tube currents (100% to 25% dose levels), slice thicknesses (3/2.5 and 1/1.25 mm), and reconstruction techniques (filtered back projection and iterative reconstruction). Every protocol was scanned 5 times after repositioning the phantom to assess reproducibility. Calcifications were quantified as Agatston scores. RESULTS: Reducing tube voltage to 100 kV, dose to 75%, and slice thickness to 1 or 1.25 mm combined with higher iterative reconstruction levels resulted in an on average 36% lower intrascanner variability (interquartile range) compared with the standard 120 kV protocol. Interscanner variability per phantom size decreased by 34% on average. With the standard protocol, on average, 6.2 ± 0.4 calcifications were detected, whereas 7.0 ± 0.4 were detected with the proposed protocol. Pairwise comparisons of Agatston scores between scanners within the same phantom size demonstrated 3 significantly different comparisons at the standard protocol (P < 0.05), whereas no significantly different comparisons arose at the proposed protocol (P > 0.05). CONCLUSIONS: On state-of-the-art CT systems of 4 different vendors, a 25% reduced dose, thin-slice calcium scoring protocol led to improved intrascanner and interscanner reproducibility and increased detectability of small and low-density calcifications in this phantom. The protocol should be extensively validated before clinical use, but it could potentially improve clinical interscanner/interinstitutional reproducibility and enable more consistent risk assessment and treatment strategies.

Diagnostic performance and clinical implications for enhancing a hybrid quantitative flow ratio-FFR revascularization decision-making strategy.

Invasive fractional flow reserve (FFR) adoption remains low mainly due to procedural and operator related factors as well as costs. Alternatively, quantitative flow ratio (QFR) achieves a high accuracy mainly outside the intermediate zone without the need for hyperaemia and wire-use. We aimed to determine the diagnostic performance of QFR and to evaluate a QFR-FFR hybrid strategy in which FFR is measured only in the intermediate zone. This retrospective study included 289 consecutive patients who underwent invasive coronary angiography and FFR. QFR was calculated for all vessels in which FFR was measured. The QFR-FFR hybrid approach was modelled using the intermediate zone of 0.77-0.87 in which FFR-measurements are recommended. The sensitivity, specificity, and accuracy on a per vessel-based analysis were 84.6%, 86.3% and 85.6% for QFR and 88.0%, 92.9% and 90.3% for the QFR-FFR hybrid approach. The diagnostic accuracy of QFR-FFR hybrid strategy with invasive FFR measurement was 93.4% and resulted in a 56.7% reduction in the need for FFR. QFR has a good correlation and agreement with invasive FFR. A hybrid QFR-FFR approach could extend the use of QFR and reduces the proportion of invasive FFR-measurements needed while improving accuracy.

Quantitative analysis of metal artifact reduction in total hip arthroplasty using virtual monochromatic imaging and orthopedic metal artifact reduction, a phantom study.

OBJECTIVE: To quantify metal artifact reduction using 130 keV virtual monochromatic imaging (VMI) with and without orthopedic metal artifact reduction (O-MAR) in total hip arthroplasty. METHODS: Conventional polychromatic images and 130 keV VMI of a phantom with pellets representing bone with unilateral or bilateral prostheses were reconstructed with and without O-MAR on a dual-layer CT. Pellets were categorized as unaffected, mildly affected and severely affected. RESULTS: When 130 keV VMI with O-MAR was compared to conventional imaging with O-MAR, a relative metal artifact reduction in CT values, contrast-to-noise (CNR), signal-to-noise (SNR) and noise in mildly affected pellets (67%, 74%, 48%, 68%, respectively; p < 0.05) was observed but no significant relative metal artifact reduction in severely affected pellets. Comparison between 130 keV VMI without O-MAR and conventional imaging with O-MAR showed relative metal artifact reduction in CT values, CNR, SNR and noise in mildly affected pellets (92%, 72%, 38%, 51%, respectively; p < 0.05) but negative relative metal artifact reduction in CT values and noise in severely affected pellets (- 331% and -223%, respectively; p < 0.05), indicating aggravation of metal artifacts. CONCLUSION: Overall, VMI of 130 keV with O-MAR provided the strongest metal artifact reduction.

Suboptimal Quality and High Risk of Bias in Diagnostic Test Accuracy Studies at Chest Radiography and CT in the Acute Setting of the COVID-19 Pandemic: A Systematic Review.

PURPOSE: To synthesize the literature on diagnostic test accuracy of chest radiography, CT, and US for the diagnosis of coronavirus disease 2019 (COVID-19) in patients suspected of having COVID-19 in a hospital setting and evaluate the extent of suboptimal reporting and risk of bias. MATERIALS AND METHODS: A systematic search was performed (April 26, 2020) in EMBASE, PubMed, and Cochrane to identify chest radiographic, CT, or US studies in adult patients suspected of having COVID-19, using reverse-transcription polymerase chain reaction test or clinical consensus as the standard of reference. Two × two contingency tables were reconstructed, and test sensitivity, specificity, positive predictive values, and negative predictive values were recalculated. Reporting quality was evaluated by adherence to the Standards for Reporting of Diagnostic Accuracy Studies (STARD), and risk of bias was evaluated by adherence to the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS: Thirteen studies were eligible (CT = 12; chest radiography = 1; US = 0). Recalculated CT sensitivity and specificity ranged between 0.57 and 0.97, and 0.37 and 0.94, respectively, and positive predictive values and negative predictive values ranged between 0.59 and 0.92 and 0.57 and 0.96, respectively. On average, studies complied with only 35% of the STARD-guideline items. No study scored low risk of bias for all QUADAS-2 domains (patient selection, index test, reference test, and flow and timing). High risk of bias in more than one domain was scored in 10 of 13 studies (77%). CONCLUSION: Reported CT test accuracy for COVID-19 diagnosis varies substantially. The validity and generalizability of these findings is complicated by poor adherence to reporting guidelines and high risk of bias, which are most likely due to the need for urgent publication of findings in the first months of the COVID-19 pandemic.Supplemental material is available for this article.© RSNA, 2020.

Deep Learning Analysis of Coronary Arteries in Cardiac CT Angiography for Detection of Patients Requiring Invasive Coronary Angiography.

In patients with obstructive coronary artery disease, the functional significance of a coronary artery stenosis needs to be determined to guide treatment. This is typically established through fractional flow reserve (FFR) measurement, performed during invasive coronary angiography (ICA). We present a method for automatic and non-invasive detection of patients requiring ICA, employing deep unsupervised analysis of complete coronary arteries in cardiac CT angiography (CCTA) images. We retrospectively collected CCTA scans of 187 patients, 137 of them underwent invasive FFR measurement in 192 different coronary arteries. These FFR measurements served as a reference standard for the functional significance of the coronary stenosis. The centerlines of the coronary arteries were extracted and used to reconstruct straightened multi-planar reformatted (MPR) volumes. To automatically identify arteries with functionally significant stenosis that require ICA, each MPR volume was encoded into a fixed number of encodings using two disjoint 3D and 1D convolutional autoencoders performing spatial and sequential encodings, respectively. Thereafter, these encodings were employed to classify arteries using a support vector machine classifier. The detection of coronary arteries requiring invasive evaluation, evaluated using repeated cross-validation experiments, resulted in an area under the receiver operating characteristic curve of 0.81 ± 0.02 on the artery-level, and 0.87 ± 0.02 on the patient-level. The results demonstrate the feasibility of automatic non-invasive detection of patients that require ICA and possibly subsequent coronary artery intervention. This could potentially reduce the number of patients that unnecessarily undergo ICA.

Deep learning from dual-energy information for whole-heart segmentation in dual-energy and single-energy non-contrast-enhanced cardiac CT.

PURPOSE: Deep learning-based whole-heart segmentation in coronary computed tomography angiography (CCTA) allows the extraction of quantitative imaging measures for cardiovascular risk prediction. Automatic extraction of these measures in patients undergoing only non-contrast-enhanced CT (NCCT) scanning would be valuable, but defining a manual reference standard that would allow training a deep learning-based method for whole-heart segmentation in NCCT is challenging, if not impossible. In this work, we leverage dual-energy information provided by a dual-layer detector CT scanner to obtain a reference standard in virtual non-contrast (VNC) CT images mimicking NCCT images, and train a three-dimensional (3D) convolutional neural network (CNN) for the segmentation of VNC as well as NCCT images. METHODS: Eighteen patients were scanned with and without contrast enhancement on a dual-layer detector CT scanner. Contrast-enhanced acquisitions were reconstructed into a CCTA and a perfectly aligned VNC image. In each CCTA image, manual reference segmentations of the left ventricular (LV) myocardium, LV cavity, right ventricle, left atrium, right atrium, ascending aorta, and pulmonary artery trunk were obtained and propagated to the corresponding VNC image. These VNC images and reference segmentations were used to train 3D CNNs in a sixfold cross-validation for automatic segmentation in either VNC images or NCCT images reconstructed from the non-contrast-enhanced acquisition. Automatic segmentation in VNC images was evaluated using the Dice similarity coefficient (DSC) and average symmetric surface distance (ASSD). Automatically determined volumes of the cardiac chambers and LV myocardium in NCCT were compared to reference volumes of the same patient in CCTA by Bland-Altman analysis. An additional independent multivendor multicenter set of single-energy NCCT images from 290 patients was used for qualitative analysis, in which two observers graded segmentations on a five-point scale. RESULTS: Automatic segmentations in VNC images showed good agreement with reference segmentations, with an average DSC of 0.897 ± 0.034 and an average ASSD of 1.42 ± 0.45 mm. Volume differences [95% confidence interval] between automatic NCCT and reference CCTA segmentations were -19 [-67; 30] mL for LV myocardium, -25 [-78; 29] mL for LV cavity, -29 [-73; 14] mL for right ventricle, -20 [-62; 21] mL for left atrium, and -19 [-73; 34] mL for right atrium, respectively. In 214 (74%) NCCT images from the independent multivendor multicenter set, both observers agreed that the automatic segmentation was mostly accurate (grade 3) or better. CONCLUSION: Our automatic method produced accurate whole-heart segmentations in NCCT images using a CNN trained with VNC images from a dual-layer detector CT scanner. This method might enable quantification of additional cardiac measures from NCCT images for improved cardiovascular risk prediction.

Feasibility of fresh frozen human cadavers as a research and training model for endovascular image guided interventions.

OBJECTIVE: To describe the feasibility of a fresh frozen human cadaver model for research and training of endovascular image guided procedures in the aorta and lower extremity. METHODS: The cadaver model was constructed in fresh frozen human cadaver torsos and lower extremities. Endovascular access was acquired by inserting a sheath in the femoral artery. The arterial segment of the specimen was restricted by ligation of collateral arteries and, in the torsos, clamping of the contralateral femoral artery and balloon occlusion of the supratruncal aorta. Tap water was administered through the sheath to create sufficient intraluminal pressure to manipulate devices and acquire digital subtraction angiography (DSA). Endovascular cannulation tasks of the visceral arteries (torso) or the peripheral arteries (lower extremities) were performed to assess the vascular patency of the model. Feasibility of this model is based on our institute's experiences throughout the use of six fresh frozen human cadaver torsos and 22 lower extremities. RESULTS: Endovascular simulation in the aortic and peripheral vasculature was achieved using this human cadaver model. Acquisition of DSA images was feasible in both the torsos and the lower extremities. Approximately 84 of the 90 target vessels (93.3%) were patent, the remaining six vessels showed signs of calcified steno-occlusive disease. CONCLUSIONS: Fresh frozen human cadavers provide a feasible simulation model for aortic and peripheral endovascular interventions, and can potentially reduce the need for animal experimentation. This model is suitable for the evaluation of new endovascular devices and techniques or to master endovascular skills.

Coronary artery centerline extraction in cardiac CT angiography using a CNN-based orientation classifier.

Coronary artery centerline extraction in cardiac CT angiography (CCTA) images is a prerequisite for evaluation of stenoses and atherosclerotic plaque. In this work, we propose an algorithm that extracts coronary artery centerlines in CCTA using a convolutional neural network (CNN). In the proposed method, a 3D dilated CNN is trained to predict the most likely direction and radius of an artery at any given point in a CCTA image based on a local image patch. Starting from a single seed point placed manually or automatically anywhere in a coronary artery, a tracker follows the vessel centerline in two directions using the predictions of the CNN. Tracking is terminated when no direction can be identified with high certainty. The CNN is trained using manually annotated centerlines in training images. No image preprocessing is required, so that the process is guided solely by the local image values around the tracker's location. The CNN was trained using a training set consisting of 8 CCTA images with a total of 32 manually annotated centerlines provided in the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08). Evaluation was performed within the CAT08 challenge using a test set consisting of 24 CCTA test images in which 96 centerlines were extracted. The extracted centerlines had an average overlap of 93.7% with manually annotated reference centerlines. Extracted centerline points were highly accurate, with an average distance of 0.21 mm to reference centerline points. Based on these results the method ranks third among 25 publicly evaluated methods in CAT08. In a second test set consisting of 50 CCTA scans acquired at our institution (UMCU), an expert placed 5448 markers in the coronary arteries, along with radius measurements. Each marker was used as a seed point to extract a single centerline, which was compared to the other markers placed by the expert. This showed strong correspondence between extracted centerlines and manually placed markers. In a third test set containing 36 CCTA scans from the MICCAI 2014 Challenge on Automatic Coronary Calcium Scoring (orCaScore), fully automatic seeding and centerline extraction was evaluated using a segment-wise analysis. This showed that the algorithm is able to fully-automatically extract on average 92% of clinically relevant coronary artery segments. Finally, the limits of agreement between reference and automatic artery radius measurements were found to be below the size of one voxel in both the CAT08 dataset and the UMCU dataset. Extraction of a centerline based on a single seed point required on average 0.4 ±â€¯0.1 s and fully automatic coronary tree extraction required around 20 s. The proposed method is able to accurately and efficiently determine the direction and radius of coronary arteries based on information derived directly from the image data. The method can be trained with limited training data, and once trained allows fast automatic or interactive extraction of coronary artery trees from CCTA images.

Diagnostic Performance of On-Site Coronary CT Angiography-derived Fractional Flow Reserve Based on Patient-specific Lumped Parameter Models.

PURPOSE: To evaluate the diagnostic performance of a prototype on-site coronary CT angiography-derived fractional flow reserve (CT FFR) algorithm, based on patient-specific lumped parameter models, for the detection of functionally significant stenosis defined by invasive FFR, and to compare the performance to anatomic evaluation of stenosis degree. MATERIALS AND METHODS: In this retrospective feasibility study, 77 vessels in 57 patients (42 of 57 [74%]) men; mean age, 58.5 years ± 9.2 [standard deviation]) who underwent clinically indicated coronary CT angiography within 60 days prior to an invasive FFR measurement were analyzed. Invasive FFR less than or equal to 0.80 was used to indicate a functionally significant stenosis. Diagnostic performance of CT FFR was evaluated and compared with evaluation of stenosis degree. Analysis was performed on a per-vessel basis. RESULTS: Invasive FFR revealed functionally significant stenoses in 37 vessels (48%). CT FFR showed a significantly increased ability to indicate functionally significant stenosis (area under the receiver operating characteristic curve [AUC], 0.87) compared with degree of stenosis at coronary CT angiography (AUC, 0.70; ΔAUC 0.17; P < .01). Using a cutoff of less than or equal to 0.80 for CT FFR and greater than or equal to 50% degree of stenosis at coronary CT angiography to indicate a significant stenosis, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 33 of 37 (89.2%), 31 of 40 (77.5%), 33 of 42 (78.6%), 31 of 35 (88.6%), and 64 of 77 (83.1%), respectively, for CT FFR, and 33 of 37 (89.2%), 17 of 40 (42.5%), 33 of 56 (58.9%), 17 of 21 (81.0%), and 50 of 77 (64.9%), respectively, for degree of stenosis at coronary CT angiography. CONCLUSION: Diagnostic performance of on-site CT FFR was superior to stenosis evaluation at coronary CT angiography for identification of functionally significant coronary artery stenosis in patients suspected of having or known to have coronary artery disease.© RSNA, 2019See also commentary by Schoepf et al.

A Recurrent CNN for Automatic Detection and Classification of Coronary Artery Plaque and Stenosis in Coronary CT Angiography.

Various types of atherosclerotic plaque and varying grades of stenosis could lead to different management of patients with a coronary artery disease. Therefore, it is crucial to detect and classify the type of coronary artery plaque, as well as to detect and determine the degree of coronary artery stenosis. This paper includes retrospectively collected clinically obtained coronary CT angiography (CCTA) scans of 163 patients. In these, the centerlines of the coronary arteries were extracted and used to reconstruct multi-planar reformatted (MPR) images for the coronary arteries. To define the reference standard, the presence and the type of plaque in the coronary arteries (no plaque, non-calcified, mixed, calcified), as well as the presence and the anatomical significance of coronary stenosis (no stenosis, non-significant, i.e., <50% luminal narrowing, and significant, i.e., ≥50% luminal narrowing) were manually annotated in the MPR images by identifying the start- and end-points of the segment of the artery affected by the plaque. To perform an automatic analysis, a multi-task recurrent convolutional neural network is applied on coronary artery MPR images. First, a 3D convolutional neural network is utilized to extract features along the coronary artery. Subsequently, the extracted features are aggregated by a recurrent neural network that performs two simultaneous multi-class classification tasks. In the first task, the network detects and characterizes the type of the coronary artery plaque. In the second task, the network detects and determines the anatomical significance of the coronary artery stenosis. The network was trained and tested using the CCTA images of 98 and 65 patients, respectively. For detection and characterization of coronary plaque, the method was achieved an accuracy of 0.77. For detection of stenosis and determination of its anatomical significance, the method was achieved an accuracy of 0.80. The results demonstrate that automatic detection and classification of coronary artery plaque and stenosis are feasible. This may enable automated triage of patients to those without coronary plaque and those with coronary plaque and stenosis in need for further cardiovascular workup.