Radiology. Cardiothoracic imaging最新文献

{"title":"Prognostic Value of Myocardial Parametric Mapping in Patients with Acute Myocarditis: A Retrospective Study.","authors":"Yining Wang, Xuejing Duan, Leyi Zhu, Jing Xu, Di Zhou, Wenjing Yang, Mengdi Jiang, Huaying Zhang, Arlene Sirajuddin, Andrew E Arai, Shihua Zhao, Hongyue Wang, Minjie Lu","doi":"10.1148/ryct.240125","DOIUrl":"10.1148/ryct.240125","url":null,"abstract":"<p><p>Purpose To investigate the prognostic value of T1 mapping, extracellular volume fraction (ECV), and T2 mapping in a large cohort of patients with acute myocarditis. Materials and Methods This retrospective study included patients with acute myocarditis who underwent cardiac MRI (3.0 T) between March 2016 and October 2022. Diagnosis was confirmed by diagnostic cardiac MRI criteria or endomyocardial biopsy. The primary end point was major adverse cardiovascular events (MACEs), defined as the composite of cardiac death, heart failure hospitalization, heart transplantation, sustained ventricular arrhythmia, and recurrent myocarditis. Univariable and multivariable Cox regression analyses were performed to assess the association of clinical and cardiac MRI variables with the primary end point. The prognostic value of each model was assessed using the Harrell C index. Results A total of 235 patients (mean age, 32 years ± 13 [SD]; 150 [63.8%] men) were included. During a mean follow-up of 1637 days (IQR: 1441-1833 days), MACEs occurred in 45 (19%) patients. Patients with MACEs had higher global native T1, ECV, and T2 values (1342 msec ± 64 vs 1263 msec ± 48; <i>P</i> < .001; 39.1% ± 8.7 vs 32.7% ± 5.7; <i>P</i> < .001; 61.1 msec ± 10.0 vs 55.3 msec ± 9.4; <i>P</i> = .03, respectively). In a series of multivariable Cox regression models, native T1 (per 10-msec increase: hazard ratio, 1.61; 95% CI: 1.31, 1.98; <i>P</i> < .001) and ECV (per 5% increase: hazard ratio, 1.70; 95% CI: 1.38, 2.08; <i>P</i> < .001) independently predicted MACE occurrence, and the addition of native T1 (Harrell C index = 0.76) or ECV (Harrell C index = 0.79) to the model including only clinical variables, left ventricular ejection fraction, and septal late gadolinium enhancement (Harrell C index = 0.72) improved discrimination for the primary end point. Conclusion Cardiac MRI-derived native T1 and ECV were independent predictors of MACEs in patients with acute myocarditis and provided incremental prognostic value when combined with conventional parameters. <b>Keywords:</b> MRI, Cardiac, Heart, Inflammation <i>Supplemental material is available for this article.</i> © RSNA, 2025.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"7 1","pages":"e240125"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880863/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modified CT Technique Improves Image Quality for Assessment of Cardiac Conduction Device Lead Perforation.","authors":"Ryan S Huang, Gauri Rani Karur, Felipe Soares Torres, Farah Cadour, Jacques Du Plessis, Kate Hanneman, Behruz Karasfi, Elsie T Nguyen","doi":"10.1148/ryct.240342","DOIUrl":"https://doi.org/10.1148/ryct.240342","url":null,"abstract":"","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"7 1","pages":"e240342"},"PeriodicalIF":3.8,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143067460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerated Cardiac MRI with Deep Learning-based Image Reconstruction for Cine Imaging.","authors":"Ann-Christin Klemenz, Linda Reichardt, Margarita Gorodezky, Mathias Manzke, Xucheng Zhu, Antonia Dalmer, Roberto Lorbeer, Cajetan I Lang, Marc-André Weber, Felix G Meinel","doi":"10.1148/ryct.230419","DOIUrl":"10.1148/ryct.230419","url":null,"abstract":"<p><p>Purpose To assess the influence of deep learning (DL)-based image reconstruction on acquisition time, volumetric results, and image quality of cine sequences in cardiac MRI. Materials and Methods This prospective study (performed from January 2023 to March 2023) included 55 healthy volunteers who underwent a noncontrast cardiac MRI examination at 1.5 T. Short-axis stack DL cine sequences of the left ventricle (LV) were performed over one (1RR), three (3RR), and six cardiac (6RR) cycles and compared with a standard cine sequence (without DL, performed over 10-12 cardiac cycles) in regard to acquisition time, subjective image quality, edge sharpness, and volumetric results. Results Total acquisition time (median) for a short-axis stack was 47 seconds for the 1RR cine, 108 seconds for 3RR cine, 184 seconds for 6RR cine, and 227 seconds for the standard sequence. Volumetric results showed no difference for the conventional cine (median LV ejection fraction [EF] 63%), 6RR cine (median LVEF, 62%), and 3RR cine (median LVEF, 61%). The 1RR cine sequence significantly underestimated EF (57%) because of a different segmentation of the papillary muscles. Subjective image quality (<i>P</i> = .37) and edge sharpness (<i>P</i> = .06) of the three-heartbeat DL cine did not differ from the reference standard, while both metrics were lower for single-heartbeat DL cine and higher for six-heartbeat DL cine. Conclusion For DL-based cine sequences, acquisition over three cardiac cycles appears to be the optimal compromise, with no evidence of differences in image quality, edge sharpness, and volumetric results, but with a greater than 50% reduced acquisition time compared with the reference sequence. <b>Keywords:</b> MR Imaging, Cardiac, Heart, Technical Aspects, Cardiac MRI, Deep Learning, Clinical Imaging, Accelerated Imaging <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e230419"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683685/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142627164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cardiac MRI Pectoralis Muscle Thickness as a Measure of Sarcopenia: Prognostic Significance, Interreader Agreement, and Physiologic Correlation.","authors":"Moran Drucker Iarovich, João Francisco Matos, William Holden Lowes, Nilushi de Silva, Yasbanoo Moayedi, Paaladinesh Thavendiranathan, Rachel M Wald, Michael McInnis, Rachel Hong, Kate Hanneman","doi":"10.1148/ryct.240147","DOIUrl":"10.1148/ryct.240147","url":null,"abstract":"<p><p>Purpose To evaluate pectoralis muscle thickness at routine cardiac MRI as a marker of sarcopenia, including prognostic significance for major adverse cardiac events (MACE), interobserver agreement, and correlation with physiologic parameters. Materials and Methods This retrospective cohort study included adult patients undergoing cardiac MRI for assessment of suspected cardiomyopathy between October 2018 and February 2020. Measurements of maximum pectoralis major thickness were performed by two experienced radiologists using axial images at the level of the carina. A random subset of 50 patients were re-evaluated to assess intra- and interobserver agreement. The primary end point was MACE, defined as a composite of cardiac death, resuscitated sudden cardiac death, appropriate implantable cardioverter defibrillator discharge, or hospitalization for heart failure. Prognostic significance of pectoralis major thickness measurements for MACE was assessed using Cox proportional hazard models, and correlation between muscle thickness measurements and cardiopulmonary exercise testing (CPET), performed within 1 year of MRI, was assessed using Spearman correlation. Results The study included 1045 patients (mean age, 50 years ± 17 [SD]; 642 male, 403 female). After median follow-up of 3.3 years (IQR: 2.3-3.9 years), MACE occurred in 66 patients. In multivariable models adjusted for patient age, left ventricular ejection fraction, late gadolinium enhancement, and cardiomyopathy cause, pectoralis major muscle thickness was predictive of MACE in both male (hazard ratio [HR], 0.89 [95% CI: 0.85, 0.94]; <i>P</i> < .001) and female patients (HR, 0.85 [95% CI: 0.76, 0.96]; <i>P</i> = .008), with improved model fit in nested models. Pectoralis muscle thickness measurements had excellent intra- and interobserver agreement (intraclass correlation coefficient, 0.99 and 0.95, respectively) and correlated with absolute peak oxygen uptake (<i>r</i> = 0.65, <i>P</i> < .0001) and oxygen uptake efficiency slope (<i>r</i> = 0.61, <i>P</i> < .001) in the subset who underwent CPET within 1 year of MRI (<i>n</i> = 258). Conclusion Pectoralis major muscle thickness at routine cardiac MRI is a simple, reproducible measure of sarcopenia that was associated with MACE occurrence in male and female patients and correlated with CPET parameters. <b>Keywords:</b> Cardiac, Cardiomyopathies, MR Imaging <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e240147"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683207/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142682622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Top 2024 Images in Cardiothoracic Imaging.","authors":"Domenico Mastrodicasa, Suvai Gunasekaran, Samer Alabed, Kate Hanneman, Gaurav S Gulsin","doi":"10.1148/ryct.240415","DOIUrl":"10.1148/ryct.240415","url":null,"abstract":"","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e240415"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683202/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142751380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Late Gadolinium Enhancement of Nonischemic Cardiomyopathy at 5.0 T versus 3.0 T: A Crossover Design Study.","authors":"Xianling Qian, Shiyu Wang, Yali Wu, Xiyin Miao, Yinyin Chen, Hongfei Lu, Rui Wang, Dong Wang, Fang Wang, Shiyu Zhang, Jiaxin Hao, Hang Jin, Mengsu Zeng","doi":"10.1148/ryct.240035","DOIUrl":"10.1148/ryct.240035","url":null,"abstract":"<p><p>Purpose To compare the acquisition time, image quality, and late gadolinium enhancement (LGE) visualization and quantification on phase-sensitive inversion recovery (PSIR) images using 5.0-T versus 3.0-T cardiac MRI. Materials and Methods In this prospective crossover study, 49 participants (mean ± SD age, 43.7 years ± 13.1; 39 men) suspected or diagnosed with nonischemic cardiomyopathy were enrolled from April 2023 to March 2024 and randomly assigned to group 1 (5.0-T followed by 3.0-T LGE cardiac MRI) or group 2 (3.0-T followed by 5.0-T LGE cardiac MRI). PSIR images were acquired at spatial resolutions of 1.2, 0.9, and 1.6 mm. Image quality and LGE were qualitatively evaluated using a five-point Likert scale by two readers, and signal-to-noise ratio, contrast-to-noise ratio, and LGE mass were quantitatively assessed. Bland-Altman plots were used to evaluate interreader agreement. Results There was no evidence of a difference in the acquisition time for obtaining a single-layer PSIR image at 5.0 T compared with 3.0 T (<i>P</i> > .05 for all), irrespective of resolutions at 1.2, 0.9, and 1.6 mm. The 5.0-T PSIR images demonstrated better image quality and LGE visualization compared with 3.0-T images, particularly at 1.2 mm (image quality: median 5 [IQR, 5-5] vs median 5 [IQR, 4-5]; <i>P</i> = .004; LGE score: median 5 [IQR, 5-5] vs median 4.25 [IQR, 4-5]; <i>P</i> < .001). No evidence of differences in image quality or LGE scores was found between 5.0-T and 3.0-T cardiac MRI at 1.6-mm resolution. Signal-to-noise ratio and contrast-to-noise ratio were higher on 5.0-T PSIR images across all resolutions compared with 3.0-T images (<i>P</i> < .001 for all), but no evidence of a difference was found in LGE mass measurements. Conclusion The study demonstrates that 5.0-T PSIR imaging offers better image quality and LGE visualization than 3.0-T PSIR, particularly at a 1.2-mm resolution, in individuals with nonischemic cardiomyopathy. <b>Keywords:</b> MRI, Cardiac, Heart, Comparative Studies, Nonischemic Cardiomyopathy, Late Gadolinium Enhancement, Phase-Sensitive Inversion Recovery <i>Supplemental material is available for this article.</i> ©RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e240035"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683737/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142855297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Need for Clarification Regarding Current State-of-the-Art Techniques for Characterizing Lung Parenchymal Aeration?","authors":"Filip Klimeš, Andreas Voskrebenzev, Jens Vogel-Claussen","doi":"10.1148/ryct.240350","DOIUrl":"10.1148/ryct.240350","url":null,"abstract":"","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e240350"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683206/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142813793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability of 4D Flow MRI for Investigation of Fetal Cardiovascular Hemodynamics in the Third Trimester.","authors":"Erin K Englund, Takashi Fujiwara, Sarah A Smith, Mariana L Meyers, Richard M Friesen, Lorna P Browne, Alex J Barker","doi":"10.1148/ryct.240119","DOIUrl":"10.1148/ryct.240119","url":null,"abstract":"<p><p>Purpose To provide reference values for four-dimensional (4D) flow MRI in healthy fetuses and evaluate reliability of fetal 4D flow MRI hemodynamics in third trimester fetuses with normal cardiovascular development or suspected coarctation of the aorta (CoA). Materials and Methods Pregnant patients with healthy fetuses or fetuses with echocardiographic concern for CoA were prospectively recruited between May 2021 and October 2023. Doppler US-gated fetal 4D flow MRI was performed at 3 T. Repeated 4D flow (time permitting) and two-dimensional (2D) phase contrast (PC) MRI data were acquired. Net flow was quantified, and the reliability of 4D flow measurement was evaluated by using precision across adjacent measurement planes, internal consistency based on conservation of mass, comparison of net flow from 4D flow MRI versus 2D PC MRI, and repeatability of 4D flow from separate acquisitions. Results Data were obtained in 34 pregnant participants (mean maternal age, 33 years ± 5 [SD]; mean gestational age, 35 weeks ± 2; <i>n</i> = 22 healthy fetuses and 12 fetuses with suspected CoA). Precision was high across all vascular segments (mean within-subject coefficient of variation = 7%). For mass conservation, there was an average difference of 19% ± 12 between ductus arteriosus plus isthmus flow versus descending aorta flow (<i>r</i> = 0.76). Net flow measured with 4D flow MRI correlated with that measured with 2D PC MRI (<i>r</i> = 0.51) but was underestimated relative to 2D PC MRI by approximately 34%. Hemodynamic parameters quantified from repeated 4D flow acquisitions had good agreement, with an intraclass correlation coefficient of 0.94 between test and retest data. Conclusion Hemodynamic measurements derived from fetal 4D flow MRI were reliable, showing good internal consistency, precision, and repeatability; however, as expected, 4D flow MRI underestimated absolute blood flow relative to 2D PC MRI. <b>Keywords:</b> Fetal MRI, Cardiac, Aorta, Hemodynamics/Flow Dynamics, Pulmonary Arteries <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e240119"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683204/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142785701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Cumulative Benefit of Inspiratory CT, Expiratory CT, and Clinical Data for COPD Diagnosis and Staging through Deep Learning.","authors":"Amanda N Lee, Albert Hsiao, Kyle A Hasenstab","doi":"10.1148/ryct.240005","DOIUrl":"10.1148/ryct.240005","url":null,"abstract":"<p><p>Purpose To measure the benefit of single-phase CT, inspiratory-expiratory CT, and clinical data for convolutional neural network (CNN)-based chronic obstructive pulmonary disease (COPD) staging. Materials and Methods This retrospective study included inspiratory and expiratory lung CT images and spirometry measurements acquired between November 2007 and April 2011 from 8893 participants (mean age, 59.6 years ± 9.0 [SD]; 53.3% [4738 of 8893] male) in the COPDGene phase I cohort (ClinicalTrials.gov: NCT00608764). CNNs were trained to predict spirometry measurements (forced expiratory volume in 1 second [FEV₁], FEV₁ percent predicted, and ratio of FEV₁ to forced vital capacity [FEV₁/FVC]) using clinical data and either single-phase or multiphase CT. Spirometry predictions were then used to predict Global Initiative for Chronic Obstructive Lung Disease (GOLD) stage. Agreement between CNN-predicted and reference standard spirometry measurements and GOLD stage was assessed using intraclass correlation coefficient (ICC) and compared using bootstrapping. Accuracy for predicting GOLD stage, within-one GOLD stage, and GOLD 0 versus 1-4 was calculated. Results CNN-predicted and reference standard spirometry measurements showed moderate to good agreement (ICC, 0.66-0.79), which improved by inclusion of clinical data (ICC, 0.70-0.85; <i>P</i> ≤ .04), except for FEV₁/FVC in the inspiratory-phase CNN model with clinical data (<i>P</i> = .35) and FEV₁ in the expiratory-phase CNN model with clinical data (<i>P</i> = .33). Single-phase CNN accuracies for GOLD stage, within-one stage, and diagnosis ranged from 59.8% to 84.1% (682-959 of 1140), with moderate to good agreement (ICC, 0.68-0.70). Accuracies of CNN models using inspiratory and expiratory images ranged from 60.0% to 86.3% (684-984 of 1140), with moderate to good agreement (ICC, 0.72). Inclusion of clinical data improved agreement and accuracy for both the single-phase CNNs (ICC, 0.72; <i>P</i> ≤ .001; accuracy, 65.2%-85.8% [743-978 of 1140]) and inspiratory-expiratory CNNs (ICC, 0.77-0.78; <i>P</i> ≤ .001; accuracy, 67.6%-88.0% [771-1003 of 1140]), except expiratory CNN with clinical data (no change in GOLD stage ICC; <i>P</i> = .08). Conclusion CNN-based COPD diagnosis and staging using single-phase CT provides comparable accuracy with inspiratory-expiratory CT when provided clinical data relevant to staging. <b>Keywords:</b> Convolutional Neural Network, Chronic Obstructive Pulmonary Disease, CT, Severity Staging, Attention Map <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e240005"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683208/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142813733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic Performance of AI-enabled Plaque Quantification from Coronary CT Angiography Compared with Intravascular Ultrasound.","authors":"Abdul Rahman Ihdayhid, Georgios Tzimas, Kersten Peterson, Nicholas Ng, Saba Mirza, Akiko Maehara, Robert D Safian","doi":"10.1148/ryct.230312","DOIUrl":"10.1148/ryct.230312","url":null,"abstract":"<p><p>Purpose To assess the diagnostic performance of a coronary CT angiography (CCTA) artificial intelligence (AI)-enabled tool (AI-QCPA; HeartFlow) to quantify plaque volume, as compared with intravascular US (IVUS). Materials and Methods A retrospective subanalysis of a single-center prospective registry study was conducted in participants with ST-elevation myocardial infarction treated with primary percutaneous coronary intervention of the culprit vessel. Participants with greater than 50% stenosis in nonculprit vessels underwent CCTA, invasive coronary angiography, and IVUS of nonculprit lesion(s) between 2 and 40 days after primary percutaneous coronary intervention. Comparisons of plaque volumes obtained using AI-QCPA (HeartFlow) and IVUS were assessed using Spearman rank correlation (ρ) and Bland-Altman analysis. Results Thirty-three participants (mean age, 59.1 years ± 8.8 [SD]; 27 [82%] male and six [18%] female participants) and 67 vessels were included for analysis. There was strong agreement between AI-QCPA and IVUS in vessel (ρ = 0.94) and lumen volumes (ρ = 0.97). High agreement between AI-QCPA and IVUS was also found for total plaque volume (ρ = 0.92), noncalcified plaque (ρ = 0.91), and calcified plaque (ρ = 0.87). Bland-Altman analysis demonstrated AI-QCPA underestimated total plaque volume (-9.4 mm³) and calcified plaque (-11.4 mm³) and overestimated for noncalcified plaque (2.0 mm³) when compared with IVUS. Conclusion An AI-enabled automated plaque quantification tool for CCTA had high agreement with IVUS for quantifying plaque volume and characterizing plaque. <b>Keywords:</b> Coronary Plaque, Intravascular US, Coronary CT Angiography, Artificial Intelligence <i>Supplemental material is available for this article.</i> ClinicalTrials.gov registration no. NCT02926755 © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 6","pages":"e230312"},"PeriodicalIF":3.8,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11683154/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142627166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}