Calf circumference as a surrogate indicator for detecting low muscle mass in hospitalized geriatric patients.

BACKGROUND: Sarcopenia is characterized by low muscle strength, decreased muscle mass, and decline in physical performance. While the measurements of muscle strength and physical performance are easy to perform, an accurate evaluation of muscle mass is technically more demanding. We therefore evaluated the suitability of calf circumference (CC) as a clinical indicator for muscle mass. METHODS: In a cross-sectional single-centre study, geriatric inpatients were assessed for sarcopenia according to the European Working Group on Sarcopenia in Older People 2 (EWGSOP2) consensus. Calf circumference was tested for correlation with appendicular skeletal muscle mass index (ASMI). Receiver operating characteristic curves (ROC) were used to calculate the discriminatory value of the CC cut-off values to differentiate patients above and below ASMI cut-offs for sarcopenia. RESULTS: In this study population (n = 305, age 83.5 ± 7.0 years, BMI 25.7 kg/m2, 65.6% female), the prevalence of sarcopenia was 22.6%. In subjects with low ASMI, mean CC was 29.5 ± 3.4 cm for females and 32.0 ± 3.4 cm for males. A positive relationship between CC and ASMI was found. The optimized cut-off value for CC to identify patients with low ASMI was <31.5 cm for females (sensitivity 78%, specificity 79%), and <33.5 cm for males (sensitivity 71%, specificity 62%). CONCLUSION: In clinical settings where imaging technology for muscle mass quantification is not available, simple calf circumference measurement may be used as a dependable indicator for low muscle mass in older adults.

[The Impact of Nutrition on Muscle Health in Older Individuals]. / Die Rolle der Ernährung für die Muskelgesundheit im Alter.

The Impact of Nutrition on Muscle Health in Older Individuals Abstract: The age-related change in the importance of nutrition for muscle health starts at the age of 50. Considering its effects on the mobility and physical independence of older people, the aging of the musculoskeletal system represents one of the greatest public health challenges and tasks for a demographically aging Switzerland. In particular sarcopenia, a pathological decrease in muscle strength, muscle mass and muscle function beyond the physiological age-related changes, correlates with a significantly increased risk of falls as well as increasing morbidity and mortality. Common chronic diseases related to old age not only promote additional muscle loss but also frailty, leading to an additional decline of the quality of life. General practitioners play a crucial role in the initial assessment of changing life circumstances and activity profiles of older people. Thanks to their medical care over many years they are able to identify functional impairments of their aging patients at an early stage and address them in time. This is important because the combination of a high-protein diet and exercise may be extremely effective for improving muscle health and function. Eating more proteins (taking into account the newly revised and increased daily protein requirement for healthy seniors of 1,0-1,2g/kg body weight (bw)) can significantly slow down age-related muscle loss. Depending on age and comorbidities, the daily protein requirement might be even higher (1,5 to 2,0g/kg bw). According to current studies, a minimal protein amount of 25-35g per main dish is recommended for optimal muscle growth stimulation among older individiuals. Thanks to their highly potent boosting power on myofibrillar protein synthesis rates the amino acid L-leucine and L-leucine-rich foods play an important role in elderly people's diet.

CNN-based evaluation of bone density improves diagnostic performance to detect osteopenia and osteoporosis in patients with non-contrast chest CT examinations.

PURPOSE: As osteoporosis is still underdiagnosed by clinicians and radiologists, the aim of the present study was to assess the performance of an Artificial intelligence (AI)-based Convolutional Neuronal Network (CNN)-Algorithm for the detection of low bone density on routine non-contrast chest CT in comparison to clinical reports using DEXA scans as reference. METHOD: This retrospective cross-sectional study included patients who underwent non-contrast chest CT and DEXA between April 2018 and June 2018 (n = 109, 19 men, mean age: 67.7 years). CT studies were evaluated for thoracic vertebral bone pathologies using a CNN-Algorithm, which calculates the attenuation profile of the spine. The content of the radiological reports was evaluated for the description of osteoporosis or osteopenia. DEXA was used as the reference standard. To estimate correlation the Spearman test was used and the comparison of the different groups was performed using the Wilcoxon rank sum test. Diagnostic was evaluated by performing a receiver operating characteristic curve analysis. RESULTS: The DEXA examination revealed normal bone density in 42 patients, while 49 patients had osteopenia and 7 osteoporosis. There was a statistically significant correlation between the mean CNN-based attenuation of the thoracic spine and the bone density measured on the DEXA in the hip (r = 0.51, p < 0.001) and lumbar spine (r = 0.34, p = 0.01). The mean attenuation was significantly higher in patients with normal bone density (172 ± 44.5 HU) compared to those with osteopenia or osteoporosis (125.2 ± 33.8 HU), (p < 0.0001). Diagnostic performance in distinguishing normal from abnormal bone density was higher using the CNN-based vertebral attenuation (accuracy 0.75, sensitivity: 0.93, specificity: 0.61) compared to clinical reports (accuracy 0.51, sensitivity: 0.14, specificity: 0.53). CONCLUSION: CNN-based evaluation of bone density may provide additional value over standard clinical reports for the detection of osteopenia and osteoporosis in patients undergoing routine non-contrast chest CT scans. This additional value could improve identification of fracture risk and subsequent treatment.

Enhanced proteostasis, lipid remodeling, and nitrogen remobilization define barley flag leaf senescence.

Leaf senescence is a developmental process allowing nutrient remobilization to sink organs. We characterized flag leaf senescence at 7, 14, and 21 d past anthesis in two near-isogenic barley lines varying in the allelic state of the HvNAM1 transcription factor gene, which influences senescence timing. Metabolomics and microscopy indicated that, as senescence progressed, thylakoid lipids were transiently converted to neutral lipids accumulating in lipid droplets. Senescing leaves also exhibited an accumulation of sugars including glucose, while nitrogen compounds (nucleobases, nucleotides, and amino acids) decreased. RNA-Seq analysis suggested lipid catabolism via ß-oxidation and the glyoxylate cycle, producing carbon skeletons and feeding respiration as a replacement of the diminished carbon supply from photosynthesis. Comparison of the two barley lines highlighted a more prominent up-regulation of heat stress transcription factor- and chaperone-encoding genes in the late-senescing line, suggesting a role for these genes in the control of leaf longevity. While numerous genes with putative roles in nitrogen remobilization were up-regulated in both lines, several peptidases, nucleases, and nitrogen transporters were more highly induced in the early-senescing line; this finding identifies processes and specific candidates which may affect nitrogen remobilization from senescing barley leaves, downstream of the HvNAM1 transcription factor.

Optimization of contrast material administration for coronary CT angiography using a software-based test-bolus evaluation algorithm.

OBJECTIVES: To evaluate the benefit of a prototype circulation time-based test bolus evaluation algorithm for the individualized optimal timing of contrast media (CM) delivery in patients undergoing coronary CT angiography (CCTA). METHODS: Thirty-two patients (62 ± 16 years) underwent CCTA using a prototype bolus evaluation tool to determine the optimal time-delay for CM administration. Contrast attenuation, signal-to-noise ratio (SNR), objective, and subjective image quality were evaluated by two independent radiologists. Results were compared to a control cohort (matched for age, sex, body mass index, and tube voltage) of patients who underwent CCTA using the generic test bolus peak attenuation +4 s protocol as scan delay. RESULTS: In the study group, the mean time delay to CCTA acquisition was significantly longer (26.0 ± 2.9 s) compared to the control group (23.1 ± 3.5 s; p < 0.01). In the study group, SNR improvement was seen in the right coronary artery (17.5 vs 13; p = 0.028), the left main (15.3 vs 12.3; p = 0.027), and the left anterior descending artery (18.5 vs 14.1; p = 0.048). Subjective image quality was rated higher in the study group (4.75 ± 0.7 vs 3.64 ± 0.5; p < 0.001). CONCLUSIONS: The prototype test bolus evaluation algorithm provided a reliable patient-specific scan delay for CCTA that ensured homogenous vascular attenuation, improvement in objective and subjective image quality, and avoidance of beam hardening artifacts. ADVANCES IN KNOWLEDGE: The prototype contrast bolus evaluation and optimization tool estimated circulation time-based time-delay improves the overall quality of CCTA.

Quiescent-Interval Slice-Selective MRA Accurately Estimates Intravascular Stent Dimensions Prior to Intervention in Patients With Peripheral Artery Disease.

BACKGROUND: Quiescent-interval slice-selective (QISS) magnetic resonance angiography (MRA) is a non-contrast alternative for the pre-procedural assessment of patients with peripheral artery disease (PAD). However, the feasibility of pre-procedural stent size estimation using QISS MRA would merit investigation. PURPOSE: To evaluate the feasibility of QISS MRA for pre-procedural stent size estimation in PAD patients compared to computed tomography angiography (CTA). STUDY TYPE: Retrospective. SUBJECTS: Thirty-three PAD patients (68 ± 9 years, 18 men, 15 women). FIELD STRENGTH/SEQUENCE: Two-dimensional balanced steady-state free precession QISS MRA at 1.5 T and 3 T. ASSESSMENT: All patients received QISS MRA and CTA of the lower extremity run-off followed by interventional digital subtraction angiography (DSA). Stenotic lesion length and diameter were quantified (AMF and AVS with 3 and 13 years of experience in cardiovascular imaging, respectively) to estimate the dimensions of the stent necessary to restore blood flow in the treated arteries. Measured dimensions were adjusted to the closest stent size available. STATISTICAL TESTS: The Friedman test with subsequent pairwise Wilcoxon signed-rank test was used to compare the estimated stent dimensions between QISS MRA, CTA, and the physical stent size used for intervention. Intra-class correlation (ICC) analysis was performed to assess inter-reader agreement. Significant differences were considered at P < 0.05. RESULTS: No significant difference was observed between estimated stent diameter by QISS MRA or CTA compared to physical stent diameter (8.9 ± 2.9 mm, 8.8 ± 3.0 mm, and 8.8 ± 3.8 mm, respectively; χ2  = 1.45, P = 0.483). There was a significant underestimation of stent length for both QISS MRA and CTA, compared to physical stent length (45.8 ± 27.8 mm, 46.4 ± 29.3 mm, and 50.4 ± 34.0 mm, respectively; χ2  = 11.96) which could be corrected when measurements were adjusted to the next available stent length (χ2  = 2.38, P = 0.303). Inter-reader assessment showed good to excellent agreement between the readers (all ICC ≥0.81). DATA CONCLUSION: QISS MRA represents a reliable method for pre-procedural lesion assessment and stent diameter and length estimation in PAD patients. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Performance of an Artificial Intelligence-Based Platform Against Clinical Radiology Reports for the Evaluation of Noncontrast Chest CT.

RATIONALE AND OBJECTIVES: Research on implementation of artificial intelligence (AI) in radiology workflows and its impact on reports remains scarce. In this study, we aim to assess if an AI platform would perform better than clinical radiology reports in evaluating noncontrast chest computed tomography (CT) scans. MATERIALS AND METHODS: Consecutive patients who had undergone noncontrast chest CT were retrospectively identified. The radiology reports were reviewed in a binary fashion for reporting of pulmonary lesions, pulmonary emphysema, aortic dilatation, coronary artery calcifications (CAC), and vertebral compression fractures (VCF). CT scans were then processed using an AI platform. The reports' findings and the AI results were subsequently compared to a consensus read by two board-certificated radiologists as reference. RESULTS: A total of 100 patients (mean age: 64.2 ± 14.8 years; 57% males) were included in this study. Aortic segmentation and calcium quantification failed to be processed by AI in 2 and 3 cases, respectively. AI showed superior diagnostic performance in identifying aortic dilatation (AI: sensitivity: 96.3%, specificity: 81.4%, AUC: 0.89) vs (Reports: sensitivity: 25.9%, specificity: 100%, AUC: 0.63), p <0.001; and CAC (AI: sensitivity: 89.8%, specificity: 100, AUC: 0.95) vs (Reports: sensitivity: 75.4%, specificity: 94.9%, AUC: 0.85), p = 0.005. Reports had better performance than AI in identifying pulmonary lesions (Reports: sensitivity: 97.6%, specificity: 100%, AUC: 0.99) vs (AI: sensitivity: 92.8%, specificity: 82.4%, AUC: 0.88), p = 0.024; and VCF (Reports: sensitivity:100%, specificity: 100%, AUC: 1.0) vs (AI: sensitivity: 100%, specificity: 63.7%, AUC: 0.82), p <0.001. A comparable diagnostic performance was noted in identifying pulmonary emphysema on AI (sensitivity: 80.6%, specificity: 66.7%. AUC: 0.74) and reports (sensitivity: 74.2%, specificity: 97.1%, AUC: 0.86), p = 0.064. CONCLUSION: Our results demonstrate that incorporating AI support platforms into radiology workflows can provide significant added value to clinical radiology reporting.

Non-invasive fractional flow reserve (FFRCT) in the evaluation of acute chest pain - Concepts and first experiences.

OBJECTIVE: To evaluate 30 day rate of major adverse cardiac events (MACE) utilizing cCTA and FFRCT for evaluation of patients presenting to the Emergency Department (ED) with acute chest pain. MATERIALS AND METHODS: Patients between the ages of 18-95 years who underwent clinically indicated cCTA and FFRCT in the evaluation of acute chest pain in the emergency department were retrospectively evaluated for 30 day MACE, repeat presentation/admission for chest pain, revascularization, and additional testing. RESULTS: A total of 59 patients underwent CCTA and subsequent FFRCT for the evaluation of acute chest pain in the ED over the enrollment period. 32 out of 59 patients (54 %) had negative FFRCT (>0.80) out of whom 18 patients (55 %) were discharged from the ED. Out of the 32 patients without functionally significant CAD by FFRCT, 32 patients (100 %) underwent no revascularization and 32 patients (100 %) had no MACE at the 30-day follow-up period. CONCLUSION: In this limited retrospective study, patients presenting to the ED with acute chest pain and with CCTA with subsequent FFRCT of >0.8 had no MACE at 30 days; however, for many of these patients results were not available at time of clinical decision making by the ED physician.

Evaluating a New Contrast Media Injection System in Coronary CT Angiography.

PURPOSE: To evaluate a new contrast media (CM) injection system in patients undergoing coronary computed tomography angiography (CCTA). METHODS: Seventy-one consecutive patients (33 men and 38 women, mean age 59.0 ± 14.5 years) who underwent CCTA between February and April 2019 using the CT injection system MEDRAD Stellant FLEX (Bayer) were included retrospectively in this single-center study. Quantitative and qualitative image quality parameters were assessed, and the injection system's usability and operational efficiency were evaluated. Results were compared with a matched control group. RESULTS: All examinations were rated as diagnostic. Usability and operational efficiency of the new injector were rated higher than that of the standard injector system, and no significant differences were found for quantitative and qualitative image quality parameters compared with the control group (P ≥ .05). DISCUSSION: Software-based injection facilitates individualized CM application while maintaining high image quality standards in CCTA. Diagnostic accuracy analysis was not performed, but as image quality analysis showed no significant differences, no discrepancies regarding this issue are expected. CONCLUSION: This study demonstrates that the MEDRAD Stellant FLEX CT injection system allows for consistent high-quality CCTA scanning with increased usability and operational efficiency.

Evaluation of a Tube Voltage-Tailored Contrast Medium Injection Protocol for Coronary CT Angiography: Results From the Prospective VOLCANIC Study.

OBJECTIVE. The purpose of this study was to prospectively evaluate, using software support, the feasibility and the quantitative and qualitative image quality parameters of a tube voltage-tailored contrast medium (CM) application protocol for patient-specific injection during coronary CT angiography (CCTA). SUBJECTS AND METHODS. In the Voltage-Based Contrast Media Adaptation in Coronary Computed Tomography Angiography (VOLCANIC-CTA) study, a single-center trial, 120 patients referred for CCTA were prospectively assigned to a tube voltage-tailored CM injection protocol. Automated tube voltage levels were selected in 10-kV intervals and ranged from 70 to 130 kV, and the iodine delivery rate (IDR) was adapted to the tube voltage level using dedicated software. The administered CM volume (370 mg I/mL) ranged from 33 mL at 70 kV (IDR, 0.7 g I/s) to 65 mL at 130 kV (IDR, 1.7 g I/s). Attenuation was measured in the aorta and coronary arteries to calculate quantitative signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and 5-point scales were used to evaluate overall image quality. Radiation metrics were also assessed and compared among the protocols. RESULTS. The mean age of the study patients was 62.5 ± 11.9 (SD) years. Image quality was rated as diagnostic in all patients. Contrast attenuation peaked at 70 kV (p < 0.001), whereas SNR and CNR parameters showed no significant differences between tube voltage levels (p ≥ 0.085). Additionally, no significant differences in subjective image quality parameters were found among the different protocols (p ≥ 0.139). The lowest radiation dose values were observed in the group assigned to the 70-kV protocol, which had a median radiation effective dose of 2.0 mSv (p < 0.001). CONCLUSION. The proposed tube voltage-tailored injection protocol allows individualized scanning of patients undergoing CCTA and significantly reduces CM and radiation dose while maintaining a high diagnostic image quality.

A fully automated software platform for structural mitral valve analysis.

OBJECTIVE: To evaluate a novel fully automated mitral valve analysis software platform for cardiac computer tomography angiography (CCTA)-based structural heart therapy procedure planning. METHODS: The study included 52 patients (25 women; mean age, 66.9 ± 12.4 years) who had undergone CCTA prior to transcatheter mitral valve replacement (TMVR) or surgical mitral valve intervention (replacement or repair). Therapeutically relevant mitral valve annulus parameters (projected area, circumference, trigone-to-trigone (T-T) distance, anterior-posterior (AP) diameter, and anterolateral-posteromedial (AL-PM) diameter) were measured. Results of the fully automated mitral valve analysis software platform with and without manual adjustments were compared with the reference standard of a user-driven measurement program (3mensio, Pie Medical Imaging). Measurements were compared between the fully automated software, both with and without manual adjustment, and the user-driven program using intraclass correlation coefficients (ICC). A secondary analysis included the time to obtain all measurements. RESULTS: Fully automated measurements showed a good to excellent agreement (circumference, ICC = 0.70; projected area, ICC = 0.81; T-T distance, ICC = 0.64; AP, ICC = 0.62; and AL-PM diameter, ICC = 0.78) compared with the user-driven analysis. There was an excellent agreement between fully automated measurement with manual adjustments and user-driven analysis regarding circumference (ICC = 0.91), projected area (ICC = 0.93), T-T distance (ICC = 0.80), AP (ICC = 0.78), and AL-PM diameter (ICC = 0.79). The time required for mitral valve analysis was significantly lower using the fully automated software with manual adjustments compared with the standard assessment (134.4 ± 36.4 s vs. 304.3 ± 77.7 s) (p < 0.01). CONCLUSION: The fully automated mitral valve analysis software, when combined with manual adjustments, demonstrated a strong correlation compared with the user-driven software while reducing the total time required for measurement. KEY POINTS: • The novel software platform allows for a fully automated analysis of mitral valve structures. • An excellent agreement was found between the fully automated measurement with manual adjustments and the user-driven analysis. • The software showed quicker measurement time compared with the standard analysis of the mitral valve.

Individualized coronary calcium scoring at any tube voltage using a kV-independent reconstruction algorithm.

PURPOSE: We prospectively investigate the feasibility of a patient specific automated tube voltage selection (ATVS)-based coronary artery calcium scoring (CACS) protocol, using a kV-independent reconstruction algorithm, to achieve significant dose reductions while maintaining the overall cardiac risk classification. METHODS: Forty-three patients (mean age, 61.8 ± 9.0 years; 40% male) underwent a clinically indicated CACS scan at 120kVp, as well as an additional CACS acquisition using an individualized tube voltage between 70 and 130kVp based on the ATVS selection (CARE-kV). Datasets of the additional CACS scans were reconstructed using a kV-independent algorithm that allows for calcium scoring without changing the weighting threshold of 130HU, regardless of the tube voltage chosen for image acquisition. Agatston scores and radiation dose derived from the different ATVS-based CACS studies were compared to the standard acquisition at 120kVp. RESULTS: Thirteen patients displayed a score of 0 and were correctly identified with the ATVS protocol. Agatston scores derived from the standard 120kVp (median, 33.4; IQR, 0-289.7) and the patient-tailored kV-independent protocol (median, 47.5; IQR, 0-287.5) showed no significant differences (p = 0.094). The intra-class correlation for Agatston scores derived from the two different protocols was excellent (ICC = 0.99). The mean dose-length-product was 29.8 ± 11.9 mGy × cm using the ATVS protocol and 31.7 ± 11.4 mGy × cm using the standard 120kVp protocol (p < 0.001). Additionally, 95% of patients were classified into the same risk category (0, 1-10, 11-100, 101-400, or > 400) using the patient-tailored protocol. CONCLUSIONS: ATVS-based CACS, using a kV-independent algorithm, allows for high accuracy compared to the standard 120kVp scanning, while significantly reducing radiation dose parameters. KEY POINTS: • ATVS allows for CT scanning with reduced radiation dose values. • KV-independent CACS is feasible at any tube voltage between 70 and 130 kVp. • ATVS applied to kV-independent CACS can significantly reduce the radiation dose.

Machine Learning/Deep Neuronal Network: Routine Application in Chest Computed Tomography and Workflow Considerations.

The constantly increasing number of computed tomography (CT) examinations poses major challenges for radiologists. In this article, the additional benefits and potential of an artificial intelligence (AI) analysis platform for chest CT examinations in routine clinical practice will be examined. Specific application examples include AI-based, fully automatic lung segmentation with emphysema quantification, aortic measurements, detection of pulmonary nodules, and bone mineral density measurement. This contribution aims to appraise this AI-based application for value-added diagnosis during routine chest CT examinations and explore future development perspectives.

Artificial Intelligence-based Fully Automated Per Lobe Segmentation and Emphysema-quantification Based on Chest Computed Tomography Compared With Global Initiative for Chronic Obstructive Lung Disease Severity of Smokers.

OBJECTIVES: The objective of this study was to evaluate an artificial intelligence (AI)-based prototype algorithm for the fully automated per lobe segmentation and emphysema quantification (EQ) on chest-computed tomography as it compares to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) severity classification of chronic obstructive pulmonary disease (COPD) patients. METHODS: Patients (n=137) who underwent chest-computed tomography acquisition and spirometry within 6 months were retrospectively included in this Institutional Review Board-approved and Health Insurance Portability and Accountability Act-compliant study. Patient-specific spirometry data, which included forced expiratory volume in 1 second, forced vital capacity, and the forced expiratory volume in 1 second/forced vital capacity ratio (Tiffeneau-Index), were used to assign patients to their respective GOLD stage I to IV. Lung lobe segmentation was carried out using AI-RAD Companion software prototype (Siemens Healthineers), a deep convolution image-to-image network and emphysema was quantified in each lung lobe to detect the low attenuation volume. RESULTS: A strong correlation between the whole-lung-EQ and the GOLD stages was found (ρ=0.88, P<0.0001). The most significant correlation was noted in the left upper lobe (ρ=0.85, P<0.0001), and the weakest in the left lower lobe (ρ=0.72, P<0.0001) and right middle lobe (ρ=0.72, P<0.0001). CONCLUSIONS: AI-based per lobe segmentation and its EQ demonstrate a very strong correlation with the GOLD severity stages of COPD patients. Furthermore, the low attenuation volume of the left upper lobe not only showed the strongest correlation to GOLD severity but was also able to most clearly distinguish mild and moderate forms of COPD. This is particularly relevant due to the fact that early disease processes often elude conventional pulmonary function diagnostics. Earlier detection of COPD is a crucial element for positively altering the course of disease progression through various therapeutic options.

Accuracy of an Artificial Intelligence Deep Learning Algorithm Implementing a Recurrent Neural Network With Long Short-term Memory for the Automated Detection of Calcified Plaques From Coronary Computed Tomography Angiography.

PURPOSE: The purpose of this study was to evaluate the accuracy of a novel fully automated deep learning (DL) algorithm implementing a recurrent neural network (RNN) with long short-term memory (LSTM) for the detection of coronary artery calcium (CAC) from coronary computed tomography angiography (CCTA) data. MATERIALS AND METHODS: Under an IRB waiver and in HIPAA compliance, a total of 194 patients who had undergone CCTA were retrospectively included. Two observers independently evaluated the image quality and recorded the presence of CAC in the right (RCA), the combination of left main and left anterior descending (LM-LAD), and left circumflex (LCx) coronary arteries. Noncontrast CACS scans were allowed to be used in cases of uncertainty. Heart and coronary artery centerline detection and labeling were automatically performed. Presence of CAC was assessed by a RNN-LSTM. The algorithm's overall and per-vessel sensitivity, specificity, and diagnostic accuracy were calculated. RESULTS: CAC was absent in 84 and present in 110 patients. As regards CCTA, the median subjective image quality, signal-to-noise ratio, and contrast-to-noise ratio were 3.0, 13.0, and 11.4. A total of 565 vessels were evaluated. On a per-vessel basis, the algorithm achieved a sensitivity, specificity, and diagnostic accuracy of 93.1% (confidence interval [CI], 84.3%-96.7%), 82.76% (CI, 74.6%-89.4%), and 86.7% (CI, 76.8%-87.9%), respectively, for the RCA, 93.1% (CI, 86.4%-97.7%), 95.5% (CI, 88.77%-98.75%), and 94.2% (CI. 90.2%-94.6%), respectively, for the LM-LAD, and 89.9% (CI, 80.2%-95.8%), 90.0% (CI, 83.2%-94.7%), and 89.9% (CI, 85.0%-94.1%), respectively, for the LCx. The overall sensitivity, specificity, and diagnostic accuracy were 92.1% (CI, 92.1%-95.2%), 88.9% (CI. 84.9%-92.1%), and 90.3% (CI, 88.0%-90.0%), respectively. When accounting for image quality, the algorithm achieved a sensitivity, specificity, and diagnostic accuracy of 76.2%, 87.5%, and 82.2%, respectively, for poor-quality data sets and 93.3%, 89.2% and 90.9%, respectively, when data sets rated adequate or higher were combined. CONCLUSION: The proposed RNN-LSTM demonstrated high diagnostic accuracy for the detection of CAC from CCTA.

Comparison of Artificial Intelligence-Based Fully Automatic Chest CT Emphysema Quantification to Pulmonary Function Testing.

OBJECTIVE. The purpose of this study was to evaluate an artificial intelligence (AI)-based prototype algorithm for fully automated quantification of emphysema on chest CT compared with pulmonary function testing (spirometry). MATERIALS AND METHODS. A total of 141 patients (72 women, mean age ± SD of 66.46 ± 9.7 years [range, 23-86 years]; 69 men, mean age of 66.72 ± 11.4 years [range, 27-91 years]) who underwent both chest CT acquisition and spirometry within 6 months were retrospectively included. The spirometry-based Tiffeneau index (TI; calculated as the ratio of forced expiratory volume in the first second to forced vital capacity) was used to measure emphysema severity; a value less than 0.7 was considered to indicate airway obstruction. Segmentation of the lung based on two different reconstruction methods was carried out by using a deep convolution image-to-image network. This multilayer convolutional neural network was combined with multilevel feature chaining and depth monitoring. To discriminate the output of the network from ground truth, an adversarial network was used during training. Emphysema was quantified using spatial filtering and attenuation-based thresholds. Emphysema quantification and TI were compared using the Spearman correlation coefficient. RESULTS. The mean TI for all patients was 0.57 ± 0.13. The mean percentages of emphysema using reconstruction methods 1 and 2 were 9.96% ± 11.87% and 8.04% ± 10.32%, respectively. AI-based emphysema quantification showed very strong correlation with TI (reconstruction method 1, ρ = -0.86; reconstruction method 2, ρ = -0.85; both p < 0.0001), indicating that AI-based emphysema quantification meaningfully reflects clinical pulmonary physiology. CONCLUSION. AI-based, fully automated emphysema quantification shows good correlation with TI, potentially contributing to an image-based diagnosis and quantification of emphysema severity.

Value of Machine Learning-based Coronary CT Fractional Flow Reserve Applied to Triple-Rule-Out CT Angiography in Acute Chest Pain.

PURPOSE: To evaluate the additional value of noninvasive artificial intelligence (AI)-based CT-derived fractional flow reserve (CT FFR), derived from triple-rule-out coronary CT angiography for acute chest pain (ACP) in the emergency department (ED) setting. MATERIALS AND METHODS: AI-based CT FFR from triple-rule-out CT angiography data sets was retrospectively obtained in 159 of 271 eligible patients (102 men; mean age, 57.0 years ± 9.7 [standard deviation]) presenting to the ED with ACP. The agreement between CT FFR (≤ 0.80) and stenosis at triple-rule-out CT angiography (≥ 50%), as well as downstream cardiac diagnostic testing, was investigated. Furthermore, the predictive value of CT FFR for coronary revascularization and major adverse cardiac events (MACE) was assessed over a 1-year follow-up period. RESULTS: CT FFR and triple-rule-out CT angiography demonstrated agreement in severity of coronary artery disease (CAD) in 52% (82 of 159) of all cases. CT FFR of 0.80 and less served as a better predictor for coronary revascularization and MACE than stenosis of 50% and greater at triple-rule-out CT angiography (odds ratio, 3.4; 95% confidence interval: 1.4, 8.2 vs odds ratio, 2.2; 95% confidence interval: 0.9, 5.3) (P < .01). In the subgroup of patients with additional noninvasive cardiac testing (94 of 159), there was higher agreement as to the presence or absence of significant disease with CT FFR (55%) than with coronary triple-rule-out CT angiography (47%) (P = .23). CONCLUSION: CT FFR derived from triple-rule-out CT angiography was a better predictor for coronary revascularization and MACE and showed better agreement with additional diagnostic testing than triple-rule-out CT angiography. Therefore, CT FFR may improve the specificity in identifying patients with ACP with significant CAD in the ED setting and reduce unnecessary downstream testing.© RSNA, 2020See also the commentary by Ihdayhid and Ben Zekry in this issue.

Low-kV coronary artery calcium scoring with tin filtration using a kV-independent reconstruction algorithm.

PURPOSE: To investigate the accuracy of Agatston scoring and potential for radiation dose reduction of a coronary artery calcium scoring (CACS) CT protocol at 100 kV with tin filtration (Sn100kV) and kV-independent iterative reconstruction, compared to standard 120 kV acquisitions. MATERIALS AND METHODS: With IRB approval and in HIPAA compliance, 114 patients (61.8 ± 9.6 years; 66 men) underwent CACS using a standard 120 kV protocol and an additional Sn100kV CACS scan. The two datasets were reconstructed using a medium sharp convolution algorithm and in addition the Sn100kV scans were reconstructed iteratively based on a kV-independent algorithm. Agatston scores and radiation dose values were compared between the Sn100kV and the standard 120 kV protocol. RESULTS: Median Agatston scores derived from the Sn100kV protocol with the kV-independent algorithm and the standard 120 kV were 21.4 (IQR, 0-173.8) and 24.7 (IQR, 0-171.1) respectively, with no significant differences (p=0.18). Agatston scores derived from the two different protocols had an excellent correlation (r = 0.99). The dose-length-product was 11.5 ± 4.1 mGy × cm using Sn100kV and 50.4 ± 24.9 mGy × cm using the standard 120 kV protocol (p < 0.01), resulting in a significantly lower (77%) effective dose at Sn100kV (0.16 ± 0.06 mSv vs. 0.71 ± 0.35 mSv, p < 0.01). Additionally, 99% of the patients were classified into the same risk category (0, 1-10, 11-100, 101-400, or >400) using the Sn100kV protocol. CONCLUSION: CACS at Sn100kV using the kV-independent iterative algorithm is feasible and provides high accuracy when compared to standard 120 kV scanning. Furthermore, radiation dose can be significantly reduced for this screening application in a priori healthy individuals.

Correcting versus resolving respiratory motion in free-breathing whole-heart MRA: a comparison in patients with thoracic aortic disease.

BACKGROUND: Whole-heart magnetic resonance angiography (MRA) requires sophisticated methods accounting for respiratory motion. Our purpose was to evaluate the image quality of compressed sensing-based respiratory motion-resolved three-dimensional (3D) whole-heart MRA compared with self-navigated motion-corrected whole-heart MRA in patients with known thoracic aorta dilation. METHODS: Twenty-five patients were prospectively enrolled in this ethically approved study. Whole-heart 1.5-T MRA was acquired using a prototype 3D radial steady-state free-precession free-breathing sequence. The same data were reconstructed with a one-dimensional motion-correction algorithm (1D-MCA) and an extradimensional golden-angle radial sparse parallel reconstruction (XD-GRASP). Subjective image quality was scored and objective image quality was quantified (signal intensity ratio, SIR; vessel sharpness). Wilcoxon, McNemar, and paired t tests were used. RESULTS: Subjective image quality was significantly higher using XD-GRASP compared to 1D-MCA (median 4.5, interquartile range 4.5-5.0 versus 4.0 [2.25-4.75]; p < 0.001), as well as signal homogeneity (3.0 [3.0-3.0] versus 2.0 [2.0-3.0]; p = 0.003), and image sharpness (3.0 [2.0-3.0] vs 2.0 [1.25-3.0]; p < 0.001). SIR with the 1D-MCA and XD-GRASP was 6.1 ± 3.9 versus 7.4 ± 2.5, respectively (p < 0.001); while signal homogeneity was 274.2 ± 265.0 versus 199.8 ± 67.2 (p = 0.129). XD-GRASP provided a higher vessel sharpness (45.3 ± 10.7 versus 40.6 ± 101, p = 0.025). CONCLUSIONS: XD-GRASP-based motion-resolved reconstruction of free-breathing 3D whole-heart MRA datasets provides improved image contrast, sharpness, and signal homogeneity and seems to be a promising technique that overcomes some of the limitations of motion correction or respiratory navigator gating.