Deep learning-based intravascular ultrasound segmentation for the assessment of coronary artery disease.

BACKGROUND: Accurate segmentation of the coronary arteries with intravascular ultrasound (IVUS) is important to optimize coronary stent implantation. Recently, deep learning (DL) methods have been proposed to develop automatic IVUS segmentation. However, most of those have been limited to segmenting the lumen and vessel (i.e. lumen-intima and media-adventitia borders), not applied to segmenting stent dimension. Hence, this study aimed to develop a DL method for automatic IVUS segmentation of stent area in addition to lumen and vessel area. METHODS: This study included a total of 45,449 images from 1576 IVUS pullback runs. The datasets were randomly split into training, validation, and test datasets (0.7:0.15:0.15). After developing the DL-based system to segment IVUS images using the training and validation datasets, we evaluated the performance through the independent test dataset. RESULTS: The DL-based segmentation correlated well with the expert-analyzed segmentation with a mean intersection over union (± standard deviation) of 0.80 ± 0.20, correlation coefficient of 0.98 (95% confidence intervals: 0.98 to 0.98), 0.96 (0.95 to 0.96), and 0.96 (0.96 to 0.96) for lumen, vessel, and stent area, and the mean difference (± standard deviation) of 0.02 ± 0.57, -0.44 ± 1.56 and - 0.17 ± 0.74 mm2 for lumen, vessel and stent area, respectively. CONCLUSION: This automated DL-based IVUS segmentation of lumen, vessel and stent area showed an excellent agreement with manual segmentation by experts, supporting the feasibility of artificial intelligence-assisted IVUS assessment in patients undergoing coronary stent implantation.

Incremental Value of Aortomitral Continuity Calcification for Risk Assessment after Transcatheter Aortic Valve Replacement.

PURPOSE: To investigate the association of aortomitral continuity calcification (AMCC) with all-cause mortality, postprocedural paravalvular leak (PVL), and prolonged hospital stay in patients undergoing transcatheter aortic valve replacement (TAVR). MATERIALS AND METHODS: The authors retrospectively evaluated 329 patients who underwent TAVR between March 2013 and March 2016. AMCC, aortic valve calcification (AVC), and coronary artery calcification (CAC) were quantified by using preprocedural CT. Pre-procedural Society of Thoracic Surgeons (STS) score was recorded. Associations between baseline AMCC, AVC, and CAC and 1-year mortality, PVL, and hospital stay longer than 7 days were analyzed. RESULTS: The median follow-up was 415 days (interquartiles, 344-727 days). After 1 year, 46 of the 329 patients (14%) died and 52 (16%) were hospitalized for more than 7 days. Of the 326 patients who underwent postprocedural echocardiography, 147 (45%) had postprocedural PVL. The CAC score (hazard ratio: 1.11 per 500 points) and AMCC mass (hazard ratio: 1.13 per 500 mg) were associated with 1-year mortality. AVC mass (odds ratio: 1.93 per 100 mg) was associated with postprocedural PVL. Only the STS score was associated with prolonged hospital stay (odds ratio: 1.19 per point). CONCLUSION: AMCC is associated with mortality within 1 year after TAVR and substantially improves individual risk classification when added to a model consisting of STS score and AVC mass only.Supplemental material is available for this article.© RSNA, 2019See also the commentary by Brown and Leipsic in this issue.

Invasive assessment of microvascular function in patients with valvular heart disease.

BACKGROUND: The aim of this study was to investigate microvascular function in patients with valvular heart disease (VHD), which causes chronic left ventricular volume and/or pressure overload, therefore change in coronary microvascular hemodynamics. PATIENTS AND METHODS: We prospectively enrolled 30 patients with VHD considered for surgery (10 aortic stenosis, 12 aortic regurgitation, and eight mitral regurgitation) and 30 controls. Intracoronary physiological assessments were performed in the unobstructed left anterior descending artery using a pressure-temperature sensor guidewire at rest and hyperemia. RESULTS: The index of microcirculatory resistance (IMR) was similar between the two groups (16.2±6.5 vs. 16.2±8.5, P=0.997), whereas coronary flow reserve (CFR) was lower in the VHD group compared with the controls (3.2±1.4 vs. 4.3±1.7, P=0.005). Resting and hyperemic coronary distal pressure, and hyperemic mean transit time were similar between VHD and controls, whereas resting mean transit time was significantly shorter (0.70±0.29 vs. 0.89±0.39, P=0.035) and baseline resting microvascular resistance was significantly lower in the VHD group compared with the controls (58.1±25.4 vs. 78.1±36.7, P=0.011). Patients with aortic stenosis showed numerically higher IMR values than aortic regurgitation, mitral regurgitation, and controls, although this was not statistically significant (20.4±6.9, P=0.14). CFR was significantly correlated with log high-sensitivity cardiac troponin T levels in patients with VHD (r=-0.523, P=0.004). CONCLUSION: CFR was reduced in patients with VHD compared with controls, despite similar microvascular function as assessed by IMR. This appeared to be mainly because of an increased resting coronary flow accompanied by a decreased resting coronary microvascular resistance rather than microvascular disease.

Clinical Outcomes and Cost-Effectiveness of Fractional Flow Reserve-Guided Percutaneous Coronary Intervention in Patients With Stable Coronary Artery Disease: Three-Year Follow-Up of the FAME 2 Trial (Fractional Flow Reserve Versus Angiography for Multivessel Evaluation).

BACKGROUND: Previous studies found that percutaneous coronary intervention (PCI) does not improve outcome compared with medical therapy (MT) in patients with stable coronary artery disease, but PCI was guided by angiography alone. FAME 2 trial (Fractional Flow Reserve Versus Angiography for Multivessel Evaluation) compared PCI guided by fractional flow reserve with best MT in patients with stable coronary artery disease to assess clinical outcomes and cost-effectiveness. METHODS: A total of 888 patients with stable single-vessel or multivessel coronary artery disease with reduced fractional flow reserve were randomly assigned to PCI plus MT (n=447) or MT alone (n=441). Major adverse cardiac events included death, myocardial infarction, and urgent revascularization. Costs were calculated on the basis of resource use and Medicare reimbursement rates. Changes in quality-adjusted life-years were assessed with utilities determined by the European Quality of Life-5 Dimensions health survey at baseline and over follow-up. RESULTS: Major adverse cardiac events at 3 years were significantly lower in the PCI group compared with the MT group (10.1% versus 22.0%; P<0.001), primarily as a result of a lower rate of urgent revascularization (4.3% versus 17.2%; P<0.001). Death and myocardial infarction were numerically lower in the PCI group (8.3% versus 10.4%; P=0.28). Angina was significantly less severe in the PCI group at all follow-up points to 3 years. Mean initial costs were higher in the PCI group ($9944 versus $4440; P<0.001) but by 3 years were similar between the 2 groups ($16 792 versus $16 737; P=0.94). The incremental cost-effectiveness ratio for PCI compared with MT was $17 300 per quality-adjusted life-year at 2 years and $1600 per quality-adjusted life-year at 3 years. The above findings were robust in sensitivity analyses. CONCLUSIONS: PCI of lesions with reduced fractional flow reserve improves long-term outcome and is economically attractive compared with MT alone in patients with stable coronary artery disease. CLINICAL TRIAL REGISTRATION: URL: https://www.clinicaltrials.gov. Unique identifier: NCT01132495.

Three-Vessel Assessment of Coronary Microvascular Dysfunction in Patients With Clinical Suspicion of Ischemia: Prospective Observational Study With the Index of Microcirculatory Resistance.

BACKGROUND: Difficulty directly visualizing the coronary microvasculature as opposed to the epicardial coronary artery makes its assessment challenging. The goal of this study is to measure the index of microcirculatory resistance (IMR) in all 3 major coronary vessels to identify the clinical and angiographic predictors of an abnormal IMR. METHODS AND RESULTS: Ninety-three patients who underwent coronary physiological assessment in all 3 major coronary vessels were prospectively enrolled (59.8±9.4 years with 77.4% men). IMR was corrected using Yong's formula and coronary microvascular dysfunction (CMD) was defined using vessel-specific cutoffs. A global IMR was calculated as the sum of the IMR in all 3 major epicardial vessels. Angiographic epicardial disease severity was assessed with vessel-specific and overall SYNTAX score. Median IMR and fractional flow reserve was 17.2 (Q1-Q3: 13.3-22.9) and 0.92 (0.85-0.97). The majority of patients (59.1%) had no CMD, 23.7% had 1-vessel CMD, 14.0% had 2-vessel CMD, and 3.2% had 3-vessel CMD. CMD was observed at a similar rate in the territories supplied by all 3 major coronary vessels (left anterior descending coronary artery 28.0%, left circumflex artery 19.4%, and right coronary artery 23.7%; P=0.39). Fractional flow reserve had a weak, positive correlation with IMR (ρ=0.16; P<0.01). The SYNTAX score had no significant correlation with IMR, both at a patient level (ρ=-0.002; P=0.99) and a vessel-specific level (ρ=-0.06; P=0.36). By multivariable ordinal logistic regression analysis, no variable was left as an independent predictor of an abnormal IMR. CONCLUSIONS: Clinical factors and epicardial coronary disease severity are not predictors of the extent of CMD. CLINICAL TRIAL REGISTRATION: URL: https://www.clinicaltrials.gov. Unique identifier: NCT01621438.

Comparison of 3-dimensional and 2-dimensional quantitative coronary angiography and intravascular ultrasound for functional assessment of coronary lesions.

BACKGROUND: Three-dimensional quantitative coronary angiography (3D-QCA) reportedly allows more accurate delineation of true vessel geometry when compared with standard two-dimensional (2D) QCA and has been validated by intravascular ultrasound (IVUS). This study sought to compare diagnostic efficiency of 2D- and 3D-QCA, and IVUS in identifying hemodynamically significant coronary stenoses as determined by fractional flow reserve (FFR). METHODS: Forty-two lesions in 40 patients were assessed by FFR, IVUS, and 2D- and 3D-QCA. Correlations between FFR values and anatomical parameters obtained by 2D- and 3D-QCA and IVUS were analyzed. The receiver operating characteristic (ROC) curves were used to compare the diagnostic accuracy of the parameters for predicting FFR≤0.80. RESULTS: Mean FFR value was 0.75±0.13. FFR≤0.80 was observed in 28 lesions (67%). Of IVUS measurements, minimum lumen area (MLA) well correlated with FFR values (r=0.71, p<0.001). Of 3D- and 2D-QCA measurements, minimum lumen diameter (MLD) correlated best with FFR values (r=0.79, p<0.01; r=0.68, p<0.01, respectively), followed by MLA (r=0.76, p<0.01; r=0.67, p<0.01, respectively). The area under the ROC curve for 3D-QCA MLD was greater than those for 2D-QCA MLD (p=0.03) and 2D-QCA MLA (p=0.03). On the other hand, the AUC for 3D-QCA MLD, 3D-QCA MLA, and IVUS MLA were not significantly different. CONCLUSIONS: 3D-QCA is more useful than 2D-QCA and possibly comparable to IVUS in the assessment of functional stenosis severity. When FFR is not available, 3D-QCA MLA and MLD may assist in the assessment of functional severity of intermediate lesions.

Efficacy of intravenous nicorandil for fractional flow reserve assessment: study protocol for a crossover randomised trial.

INTRODUCTION: Nicorandil has vasodilatory effects on both the epicardial coronary arteries and the coronary microvasculature, thereby increasing coronary blood flow. Intravenous administration of nicorandil can be applicable for fractional flow reserve (FFR) measurement as a hyperaemic agent and a possible alternative to adenosine. However, the effectiveness of intravenous nicorandil infusion for FFR measurement is largely unclear. METHODS AND ANALYSIS: This crossover randomised study is being performed to investigate the efficacy of intravenous administration of nicorandil for FFR measurement. Patients with an intermediate coronary artery stenosis who satisfy the eligibility criteria undergo FFR measurement with a consecutive randomised order of patient-blind infusions of continuous intravenous administration of adenosine and a single bolus intravenous administration of nicorandil. The primary end point of the study is the agreement between the FFR values obtained by the intravenous nicorandil and those obtained by the intravenous adenosine. Recruitment of this trial started in November 2015 and will end in March 2017, or until a total of 50 participants have been recruited. ETHICS AND DISSEMINATION: The protocol was approved by the Institutional Review Board at Chiba University Hospital. Study findings will be published in peer-reviewed journals. TRIAL REGISTRATION NUMBER: UMIN000019309; Pre-results.

Efficacy of combined administration of intracoronary papaverine plus intravenous adenosine 5'-triphosphate in assessment of fractional flow reserve.

BACKGROUND: Inducing maximal coronary hyperemia is important to measure fractional flow reserve (FFR) accurately. Intravenous adenosine and adenosine 5'-triphosphate (ATP) have been used to achieve maximal hyperemia. However, they may not induce maximal hyperemia in all patients. The present study evaluated the combined effect of intracoronary papaverine and intravenous ATP on FFR measurements. METHODS: FFR measurements with administration of intracoronary papaverine (12mg in the left coronary artery and 8mg in the right coronary artery), intravenous ATP (140µg/kg/min), and combined administration of intracoronary papaverine and intravenous ATP were performed in 51 patients with 57 intermediate lesions. RESULTS: The mean FFR after intravenous ATP was higher compared to intracoronary papaverine and intravenous ATP plus intracoronary papaverine (0.76±0.13 vs. 0.75±0.13 vs. 0.75±0.13, p=0.01). FFR-positive lesions (FFR ≤0.80) were observed more frequently with intravenous ATP plus intracoronary papaverine compared to intravenous ATP (64.9% vs. 47.4%, p=0.02). Of 32 and 25 FFR-negative lesions with intravenous ATP and intracoronary papaverine, 11 (34%) and 7 (28%) had positive FFR after administration of intravenous ATP plus intracoronary papaverine. No ventricular tachycardia or ventricular fibrillation was observed after administration of intracoronary papaverine. CONCLUSIONS: Maximal hyperemia may not be induced with intravenous ATP in all lesions. When sufficient hyperemia is doubtful during intravenous infusion of ATP, additional intracoronary administration of papaverine may be a possible option.