Machine learning detects symptomatic patients with carotid plaques based on 6-type calcium configuration classification on CT angiography.

OBJECTIVES: While the link between carotid plaque composition and cerebrovascular vascular (CVE) events is recognized, the role of calcium configuration remains unclear. This study aimed to develop and validate a CT angiography (CTA)-based machine learning (ML) model that uses carotid plaques 6-type calcium grading, and clinical parameters to identify CVE patients with bilateral plaques. MATERIAL AND METHODS: We conducted a multicenter, retrospective diagnostic study (March 2013-May 2020) approved by the institutional review board. We included adults (18 +) with bilateral carotid artery plaques, symptomatic patients having recently experienced a carotid territory ischemic event, and asymptomatic patients either after 3 months from symptom onset or with no such event. Four ML models (clinical factors, calcium configurations, and both with and without plaque grading [ML-All-G and ML-All-NG]) and logistic regression on all variables identified symptomatic patients. Internal validation assessed discrimination and calibration. External validation was also performed, and identified important variables and causes of misclassifications. RESULTS: We included 790 patients (median age 72, IQR [61-80], 42% male, 64% symptomatic) for training and internal validation, and 159 patients (age 68 [63-76], 36% male, 39% symptomatic) for external testing. The ML-All-G model achieved an area-under-ROC curve of 0.71 (95% CI 0.58-0.78; p < .001) and sensitivity 80% (79-81). Performance was comparable on external testing. Calcified plaque, especially the positive rim sign on the right artery in older and hyperlipidemic patients, had a major impact on identifying symptomatic patients. CONCLUSION: The developed model can identify symptomatic patients using plaques calcium configuration data and clinical information with reasonable diagnostic accuracy. CLINICAL RELEVANCE: The analysis of the type of calcium configuration in carotid plaques into 6 classes, combined with clinical variables, allows for an effective identification of symptomatic patients. KEY POINTS: • While the association between carotid plaques composition and cerebrovascular events is recognized, the role of calcium configuration remains unclear. • Machine learning of 6-type plaque grading can identify symptomatic patients. Calcified plaques on the right artery, advanced age, and hyperlipidemia were the most important predictors. • Fast acquisition of CTA enables rapid grading of plaques upon the patient's arrival at the hospital, which streamlines the diagnosis of symptoms using ML.

Validation of a Length-Adjusted Abdominal Arterial Calcium Score Method for Contrast-Enhanced CT Scans.

BACKGROUND: The Agatston score on noncontrast computed tomography (CT) scans is the gold standard for calcium load determination. However, contrast-enhanced CT is commonly used for patients with atherosclerotic cardiovascular diseases (ASCVDs), such as peripheral arterial occlusive disease (PAOD) and abdominal aortic aneurysm (AAA). Currently, there is no validated method to determine calcium load in the aorta and peripheral arteries with a contrast-enhanced CT. This study validated a length-adjusted calcium score (LACS) method for contrast-enhanced CT scans. METHOD: The LACS (calcium volume in mm3/arterial length in cm) in the abdominal aorta was calculated using four-phase liver CT scans of 30 patients treated between 2017 and 2021 at the University Medical Center Groningen (UMCG) with no aortic disease. Noncontrast CT scans were segmented with a 130 Hounsfield units (HU) threshold, and a patient-specific threshold was used for contrast-enhanced CTs. The LACS was calculated and compared from both segmentations. Secondly, the interobserver variability and the influence of slice thickness (0.75 mm vs. 2.0 mm) was determined. RESULTS: There was a high correlation between the LACS from contrast-enhanced CT scans and the LACS of noncontrast CTs (R2 = 0.98). A correction factor of 1.9 was established to convert the LACS derived from contrast-enhanced CT to noncontrast CT scans. LACS interobserver agreement on contrast-enhanced CT was excellent (1.0, 95% confidence interval = 1.0-1.0). The 0.75 mm CT threshold was 541 (459-625) HU compared with 500 (419-568) HU on 2 mm CTs (p = 0.15). LACS calculated with both thresholds was not significantly different (p = 0.63). CONCLUSION: The LACS seems to be a robust method for scoring calcium load on contrast-enhanced CT scans in arterial segments with various lengths.

Effects of plaque characteristics and artery hemodynamics on the residual stenosis after carotid artery stenting.

OBJECTIVE: Carotid artery stenting (CAS) has become an alternative strategy to carotid endarterectomy for carotid artery stenosis. Residual stenosis was an independent risk factor for restenosis, with the latter affecting the long-term outcomes of CAS. This multicenter study aimed to evaluate the echogenicity of plaques and hemodynamic alteration by color duplex ultrasound (CDU) examination and investigate their effects on the residual stenosis after CAS. METHODS: From June 2018 to June 2020, 454 patients (386 males and 68 females) with a mean age of 67.2 ± 7.9 years, who underwent CAS from 11 advanced stroke centers in China were enrolled. One week before recanalization, CDU was used to evaluate the responsible plaques, including the morphology (regular or irregular), echogenicity of the plaques (iso-, hypo-, or hyperechoic) and calcification characteristics (without calcification, superficial calcification, inner calcification, and basal calcification). One week after CAS, the alteration of diameter and hemodynamic parameters were evaluated by CDU, and the occurrence and degree of residual stenosis were determined. In addition, magnetic resonance imaging was performed before and during the 30-day postprocedural period to identify new ischemic cerebral lesions. RESULTS: The rate of composite complications, including cerebral hemorrhage, symptomatic new ischemic cerebral lesions, and death after CAS, was 1.54% (7/454 cases). The rate of residual stenosis after CAS was 16.3% (74/454 cases). After CAS, both the diameter and peak systolic velocity (PSV) improved in the preprocedural 50% to 69% and 70% to 99% stenosis groups (P < .05). Compared with the groups without residual stenosis and with <50% residual stenosis, the PSV of all three segments of stent in the 50% to 69% residual stenosis group were the highest, and the difference in the midsegment of stent PSV was the largest (P < .05). Logistic regression analysis showed that preprocedural severe (70% to 99%) stenosis (odds ratio [OR], 9.421; P = .032), hyperechoic plaques (OR, 3.060; P = .006) and plaques with basal calcification (OR, 1.885; P = .049) were independent risk factors for residual stenosis after CAS. CONCLUSIONS: Patients with hyperechoic and calcified plaques of the carotid stenosis are at a high risk of residual stenosis after CAS. CDU is an optimal, simple and noninvasive imaging method to evaluate plaque echogenicity and hemodynamic alterations during the perioperative period of CAS, which can help surgeons to select the optimal strategies and prevent the occurrence of residual stenosis.

Computed tomography independent quantitative determinants of CAD-RADS 4 versus CAD-RADS 3 for calcified coronary lesions.

Purpose: An investigation of coronary computed tomography angiography (CCTA)-derived quantitative parameters to determine CAD-RADS 4 versus CAD-RADS 3 of coronary lesions with moderate to severe calcification. Material and methods: The study included 150 coronary lesions proven to have moderate or severe stenosis by invasive coronary angiography and showing moderate to severe calcification in CCTA. Various CCTA-quantitative parameters were correlated to the degree of stenosis (moderately versus severely stenosed lesions). Their sensitivity and specificity to detect severe stenosis (supposed to be corresponding to CAD-RADS 4) were examined at multiple cut-off points. Results: The calcification remodelling index (CRI) was the only statistically significant independent computed tomo-graphy angiography-derived predictor of severe stenosis versus moderate stenosis on multivariate regression analysis. The best cut-off value was ≤ 0.84, with 77.78% sensitivity and 86.46% specificity. Conclusions: From all quantitative-derived CCTA parameters, CRI ≤ 0.84 was the predictor with the highest diagnostic performance for severe versus moderate stenosis in moderately to severely calcified coronary lesions. Accordingly, CRI can help to determine CAD-RADS 4 versus CAD-RADS 3.

Superficial Femoral Artery Rupture "Bailed Out" Using Novel Design of Supera Stent.

Peripheral artery disease is a condition that occurs due to narrowing or occlusion of arterial lumen usually secondary to atherosclerosis. Endovascular treatments are minimally invasive procedures that have become popular for recanalization of such calcified/sclerosed arteries. However, heavily calcified arteries make these procedures challenging and are more prone to complications like balloon rupture and bleeding. Herein, we report a novel case of rupture of superficial femoral artery and its management using self-expanding Supera stent.

Divergent Occurrence of Carotid Intima-Media Thickness and Carotid Arteries Plaques in Stable Kidney Transplant Recipients.

Background: Carotid atherosclerosis is one of the main cerebrovascular complications in kidney transplant recipients (KTRs). We analyzed the relationships between carotid intima-media thickness (IMT) and the occurrence and characteristics of carotid plaques in a cohort of KTRs. Methods: In 500 KTRs (aged 49.9 ± 12.0 years), IMT was measured and carotid plaques were semi-qualitatively assessed. Concomitantly, biochemical and hormonal inflammatory, vascular and calcium-phosphate metabolism parameters were also assessed. Results: In 10.2% of patients, a side-to-side IMT difference > 0.1 mm was observed, whereas 26.8% of patients with no plaques in one carotid artery had at least one contralateral calcified plaque. Multivariate logistic regression analysis revealed that age ( r partial = 0.409; p < 0.001), male sex ( r partial = 0.199; p < 0.001), and coronary artery disease ( r partial = 0.139; p < 0.01) independently increased IMT ( R 2 = 0.25). For the occurrence of calcified carotid plaques, age ( r partial = 0.544; p < 0.001), male gender ( r partial = 0.127; p < 0.05), and the duration of renal insufficiency prior to transplantation ( r partial = 0.235; p < 0.001) were confirmed as independent variables. Conclusions: Substantial side-to-side differences in IMT values and carotid plaques distribution are present in a large percentage of stable KTRs. In addition, there are different clinical risk factors profiles associated with IMT and the presence of calcified plaques. Vascular and calcium-phosphate metabolism biomarkers were not associated with any carotid atherosclerosis characteristics.

Influence of contrast material density and kV setting on detectability of calcified plaques on coronary CT angiography.

PURPOSE: To analyze the impact of tube potential and iodine concentration on the visibility of calcified plaques in coronary computed tomography angiography (cCTA). METHODS & MATERIALS: 164 consecutive patients (65.9 % men and a mean age of 57.1 ±â€¯11.3 years) with suspected coronary artery disease underwent calcium scoring (CaSc) scan followed by cCTA with topogram-based automated tube voltage selection (70 kV, 80 kV, 90 kV, 100 kV or 120 kV). In 127 Patients (HC), we injected 50 mL of contrast material (CM) with a concentration of 400 mg iodine per ml and in 37 patients (LC) 50 mL iodine concentration of 280 mg/mL. Sensitivity of cCTA for detecting calcified plaques was calculated with CaSc serving as gold standard. Density of CM enhanced coronary vessels and calcified plaques were quantified by region-of-interest (ROI) measurements in unenhanced and cCTA image series. RESULTS: Overall sensitivity of cCTA to detect calcified plaques was significantly higher using LC compared to HC (79 % vs. 73 %; p = 0.0035). The impact of LC was impressive at 70 kV with an improved sensitivity of 70 % vs. 57.1 % in HC (p = 0.0082). Furthermore, density values of HC enhanced coronary vessels exceeded those of calcified plaques, especially at low kV levels. In LC, except for the 70 kV setting, higher density values were shown for calculi than enhanced vessels. CONCLUSION: Low kV cCTA in routine using highly concentrated CM leads to reduced calcified plaque perceptibility and hence potentially underestimation of stenosis. Thus, low kV cCTA using CM with lower iodine concentration is necessary. In addition, a dose reduction up to 77.7 % can also be benefited.

Broken arrow: Successful retrieval of a dislodged coronary orbital atherectomy microtip.

A 68-year-old female with a history of coronary artery disease and prior bypass surgery presented for staged percutaneous coronary intervention (PCI) to a calcified and angulated ostial left circumflex (LCX) artery lesion after PCI of the anastomosis of the left internal mammary artery - to left anterior descending artery. Orbital atherectomy of the LCX was performed at a speed of 80,000 RPM with multiple passes, and was complicated by device microtip dislodgement and entrapment within the vessel. After advancing a "buddy" wire beyond the microtip, a tapered microcatheter was advanced over the ViperWire and into the edge of the broken microtip and torqued into the microtip with forward pressure using the 0.014 in ViperWire tip as a "backstop." The guidewire, microcatheter, and microtip were then successfully removed as a unit and the intervention with stent placement was completed over the "buddy" wire. Scanning electron microscopy of the shaft revealed evidence of cyclic fatigue, indicating that the fracture occurred while spinning. The fracture when performing atherectomy in a model coronary artery with a radius of approximately 6 mm. This represents a first case of microtip dislodgement and entrapment during the use of a coronary orbital atherctomy device.short.

Framework for detection and localization of coronary non-calcified plaques in cardiac CTA using mean radial profiles.

BACKGROUND AND OBJECTIVE: The high mortality rate associated with coronary heart disease (CHD) has driven intensive research in cardiac imaging and image analysis. The advent of computed tomography angiography (CTA) has turned non-invasive diagnosis of cardiovascular anomalies into reality as calcified coronary plaques can be easily identified due to their high intensity values. However, the detection of non-calcified plaques in CTA is still a challenging problem because of lower intensity values, which are often similar to the nearby blood and muscle tissues. In this work, we propose the use of mean radial profiles for the detection of non-calcified plaques in CTA imagery. METHODS: Accordingly, we computed radial profiles by averaging the image intensity in concentric rings around the vessel centreline in a first stage. In the subsequent stage, an SVM classifier is applied to identify the abnormal coronary segments. For occluded segments, we further propose a derivative-based method to localize the position and length of the plaque inside the segment. RESULTS: A total of 32 CTA volumes were analysed and a detection accuracy of 88.4% with respect to the manual expert was achieved. The plaque localization accuracy was computed using the Dice similarity coefficient and a mean of 83.2% was achieved. CONCLUSION: The consistent performance for multi-vendor, multi-institution data demonstrates the reproducibility of our method across different CTA datasets with a good agreement with manual expert annotations.

Coronary CT angiography in calcified coronary plaques: Comparison of diagnostic accuracy between bifurcation angle measurement and coronary lumen assessment for diagnosing significant coronary stenosis.

BACKGROUND: To investigate the diagnostic value of coronary CT angiography (CCTA) by bifurcation angle measurement in the assessment of calcified plaques compared to conventional coronary lumen analysis. METHODS: Fifty-three patients with calcified plaques identified on CCTA in the left coronary artery were included in the study. Minimal lumen diameter (MLD) and bifurcation angle between the left anterior descending (LAD) and left circumflex (LCx) arteries were measured and compared between CCTA and invasive coronary angiography (ICA), while the areas under the curves (AUCs) by receiver-operating characteristic curve analysis (ROC) were compared between CCTA and ICA with regard to the diagnostic value of using bifurcation angle as a criterion. RESULTS: On a per-vessel assessment, the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) and 95% confidence interval (CI) with the use of bifurcation angle for determining coronary stenosis were 100% (86%, 100%), 79% (59%, 92%), 81% (62%, 92%), and 100% (85%, 100%) for CCTA, and 100% (86%, 100%), 82% (63%, 94%), 83% (65%, 94%), and 100% (85%, 100%) for ICA, respectively. While the sensitivity and NPV remained unchanged, the specificity and PPV of CCTA by MLD were 33% (21%, 47%) and 43% (31%, 56%). The AUCs by ROC curve analysis for CCTA and ICA bifurcation angle measurements demonstrated no significant difference (p>0.05, 0.79 vs 0.86, and 0.70 vs 0.68 at the LAD and LCx assessment, respectively). CONCLUSION: Coronary CT angiography by bifurcation angle measurement shows significant improvement in the diagnosis of calcified plaques with diagnostic value comparable to invasive coronary angiography.