Radiology. Cardiothoracic imaging最新文献

{"title":"Enabling Reliable Visual Detection of Chronic Myocardial Infarction with Native T1 Cardiac MRI Using Data-Driven Native Contrast Mapping.","authors":"Khalid Youssef, Xinheng Zhang, Ghazal Yoosefian, Yinyin Chen, Shing Fai Chan, Hsin-Jung Yang, Keyur Vora, Andrew Howarth, Andreas Kumar, Behzad Sharif, Rohan Dharmakumar","doi":"10.1148/ryct.230338","DOIUrl":"10.1148/ryct.230338","url":null,"abstract":"<p><p>Purpose To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and <i>t</i>-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as <i>data-driven native mapping</i> (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; <i>P</i> < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; <i>P</i> = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (<i>R</i>² = 0.71 for native T1 maps vs LGE; <i>R</i>² = 0.85 for DNM vs LGE; <i>P</i> < .001). Conclusion Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories. <b>Keywords:</b> Chronic Myocardial Infarction, Cardiac MRI, Data-Driven Native Contrast Mapping <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 4","pages":"e230338"},"PeriodicalIF":3.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11369652/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141634376","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":"Coronary Plaque Characterization with T1-weighted MRI and Near-Infrared Spectroscopy to Predict Periprocedural Myocardial Injury.","authors":"Koji Isodono, Hidenari Matsumoto, Debiao Li, Piotr J Slomka, Damini Dey, Sebastien Cadet, Daisuke Irie, Satoshi Higuchi, Hiroki Tanisawa, Motoki Nakazawa, Yoshiaki Komori, Hidefumi Ohya, Ryoji Kitamura, Tetsuichi Hondera, Ikumi Sato, Hsu-Lei Lee, Anthony G Christodoulou, Yibin Xie, Toshiro Shinke","doi":"10.1148/ryct.230339","DOIUrl":"10.1148/ryct.230339","url":null,"abstract":"<p><p>Purpose To clarify the predominant causative plaque constituent for periprocedural myocardial injury (PMI) following percutaneous coronary intervention: <i>(a)</i> erythrocyte-derived materials, indicated by a high plaque-to-myocardium signal intensity ratio (PMR) at coronary atherosclerosis T1-weighted characterization (CATCH) MRI, or <i>(b)</i> lipids, represented by a high maximum 4-mm lipid core burden index (maxLCBI_{4 mm}) at near-infrared spectroscopy intravascular US (NIRS-IVUS). Materials and Methods This retrospective study included consecutive patients who underwent CATCH MRI before elective NIRS-IVUS-guided percutaneous coronary intervention at two facilities. PMI was defined as post-percutaneous coronary intervention troponin T values greater than five times the upper reference limit. Multivariable analysis was performed to identify predictors of PMI. Finally, the predictive capabilities of MRI, NIRS-IVUS, and their combination were compared. Results A total of 103 lesions from 103 patients (median age, 72 years [IQR, 64-78]; 78 male patients) were included. PMI occurred in 36 lesions. In multivariable analysis, PMR emerged as the strongest predictor (<i>P</i> = .001), whereas maxLCBI_{4 mm} was not a significant predictor (<i>P</i> = .07). When PMR was excluded from the analysis, maxLCBI_{4 mm} emerged as the sole independent predictor (<i>P</i> = .02). The combination of MRI and NIRS-IVUS yielded the largest area under the receiver operating curve (0.86 [95% CI: 0.64, 0.83]), surpassing that of NIRS-IVUS alone (0.75 [95% CI: 0.64, 0.83]; <i>P</i> = .02) or MRI alone (0.80 [95% CI: 0.68, 0.88]; <i>P</i> = .30). Conclusion Erythrocyte-derived materials in plaques, represented by a high PMR at CATCH MRI, were strongly associated with PMI independent of lipids. MRI may play a crucial role in predicting PMI by offering unique pathologic insights into plaques, distinct from those provided by NIRS. <b>Keywords:</b> Coronary Plaque, Periprocedural Myocardial Injury, MRI, Near-Infrared Spectroscopy Intravascular US <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 4","pages":"e230339"},"PeriodicalIF":3.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11375432/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141983155","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":"Safety Net Reconstruction to Catch Low-Density and Low-Volume Calcifications at Photon-Counting Detector CT Using Virtual Noncontrast Imaging.","authors":"Prabhakar Shantha Rajiah, Kishore Rajendran","doi":"10.1148/ryct.240266","DOIUrl":"10.1148/ryct.240266","url":null,"abstract":"","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 4","pages":"e240266"},"PeriodicalIF":3.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11369647/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142018490","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":"Erratum for: MRI in Patients with Cardiovascular Implantable Electronic Devices and Fractured or Abandoned Leads.","authors":"Mark J Greenhill, Pooja Rangan, Wilber Su, J Peter Weiss, Michael Zawaneh, Samuel Unzek, Balaji Tamarappoo, Julia Indik, Roderick Tung, Michael F Morris","doi":"10.1148/ryct.249004","DOIUrl":"10.1148/ryct.249004","url":null,"abstract":"","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 4","pages":"e249004"},"PeriodicalIF":3.8,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11375431/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141580736","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":"Leveraging Serial Low-Dose CT Scans in Radiomics-based Reinforcement Learning to Improve Early Diagnosis of Lung Cancer at Baseline Screening.","authors":"Yifan Wang, Chuan Zhou, Lei Ying, Elizabeth Lee, Heang-Ping Chan, Aamer Chughtai, Lubomir M Hadjiiski, Ella A Kazerooni","doi":"10.1148/ryct.230196","DOIUrl":"10.1148/ryct.230196","url":null,"abstract":"<p><p>Purpose To evaluate the feasibility of leveraging serial low-dose CT (LDCT) scans to develop a radiomics-based reinforcement learning (RRL) model for improving early diagnosis of lung cancer at baseline screening. Materials and Methods In this retrospective study, 1951 participants (female patients, 822; median age, 61 years [range, 55-74 years]) (male patients, 1129; median age, 62 years [range, 55-74 years]) were randomly selected from the National Lung Screening Trial between August 2002 and April 2004. An RRL model using serial LDCT scans (S-RRL) was trained and validated using data from 1404 participants (372 with lung cancer) containing 2525 available serial LDCT scans up to 3 years. A baseline RRL (B-RRL) model was trained with only LDCT scans acquired at baseline screening for comparison. The 547 held-out individuals (150 with lung cancer) were used as an independent test set for performance evaluation. The area under the receiver operating characteristic curve (AUC) and the net reclassification index (NRI) were used to assess the performances of the models in the classification of screen-detected nodules. Results Deployment to the held-out baseline scans showed that the S-RRL model achieved a significantly higher test AUC (0.88 [95% CI: 0.85, 0.91]) than both the Brock model (AUC, 0.84 [95% CI: 0.81, 0.88]; <i>P</i> = .02) and the B-RRL model (AUC, 0.86 [95% CI: 0.83, 0.90]; <i>P</i> = .02). Lung cancer risk stratification was significantly improved by the S-RRL model as compared with Lung CT Screening Reporting and Data System (NRI, 0.29; <i>P</i> < .001) and the Brock model (NRI, 0.12; <i>P</i> = .008). Conclusion The S-RRL model demonstrated the potential to improve early diagnosis and risk stratification for lung cancer at baseline screening as compared with the B-RRL model and clinical models. <b>Keywords:</b> Radiomics-based Reinforcement Learning, Lung Cancer Screening, Low-Dose CT, Machine Learning © RSNA, 2024 <i>Supplemental material is available for this article.</i></p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 3","pages":"e230196"},"PeriodicalIF":3.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211947/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140945860","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":"Sex Differences in Aging-related Myocardial Stiffening Quantitatively Measured with MR Elastography.","authors":"Arvin Arani, Matthew C Murphy, Huzefa Bhopalwala, Shivaram P Arunachalam, Phillip J Rossman, Joshua D Trzasko, Kevin Glaser, Yi Sui, Tina Gunderson, Adelaide M Arruda-Olson, Armando Manduca, Kejal Kantarci, Richard L Ehman, Philip A Araoz","doi":"10.1148/ryct.230140","DOIUrl":"10.1148/ryct.230140","url":null,"abstract":"<p><p>Purpose To investigate the feasibility of using quantitative MR elastography (MRE) to characterize the influence of aging and sex on left ventricular (LV) shear stiffness. Materials and Methods In this prospective study, LV myocardial shear stiffness was measured in 109 healthy volunteers (age range: 18-84 years; mean age, 40 years ± 18 [SD]; 57 women, 52 men) enrolled between November 2018 and September 2019, using a 5-minute MRE acquisition added to a clinical MRI protocol. Linear regression models were used to estimate the association of cardiac MRI and MRE characteristics with age and sex; models were also fit to assess potential age-sex interaction. Results Myocardial shear stiffness significantly increased with age in female (age slope = 0.03 kPa/year ± 0.01, <i>P</i> = .009) but not male (age slope = 0.008 kPa/year ± 0.009, <i>P</i> = .38) volunteers. LV ejection fraction (LVEF) increased significantly with age in female volunteers (0.23% ± 0.08 per year, <i>P</i> = .005). LV end-systolic volume (LVESV) decreased with age in female volunteers (-0.20 mL/m² ± 0.07, <i>P</i> = .003). MRI parameters, including T1, strain, and LV mass, did not demonstrate this interaction (<i>P</i> > .05). Myocardial shear stiffness was not significantly correlated with LVEF, LV stroke volume, body mass index, or any MRI strain metrics (<i>P</i> > .05) but showed significant correlations with LV end-diastolic volume/body surface area (BSA) (slope = -3 kPa/mL/m² ± 1, <i>P</i> = .004, <i>r</i>² = 0.08) and LVESV/BSA (-1.6 kPa/mL/m² ± 0.5, <i>P</i> = .003, <i>r</i>² = 0.08). Conclusion This study demonstrates that female, but not male, individuals experience disproportionate LV stiffening with natural aging, and these changes can be noninvasively measured with MRE. <b>Keywords:</b> Cardiac, Elastography, Biological Effects, Experimental Investigations, Sexual Dimorphisms, MR Elastography, Myocardial Shear Stiffness, Quantitative Stiffness Imaging, Aging Heart, Myocardial Biomechanics, Cardiac MRE <i>Supplemental material is available for this article</i>. Published under a CC BY 4.0 license.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 3","pages":"e230140"},"PeriodicalIF":3.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211939/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141080841","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":"Seeing between Time: Higher Frame Rate Cardiac Cine MRI using Deep Learning.","authors":"Ioannis Koktzoglou","doi":"10.1148/ryct.240140","DOIUrl":"10.1148/ryct.240140","url":null,"abstract":"","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 3","pages":"e240140"},"PeriodicalIF":3.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211936/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141262643","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":"Intraindividual Comparison of Dose Reduction and Coronary Calcium Scoring Accuracy Using Kilovolt-independent and Tin Filtration CT Protocols.","authors":"Salma Zook, Bhupendar Tayal, Kristian Kragholm, Ola Abdelkarim, Diana Tran, Myra Cocker, Juan Carlos Ramirez-Giraldo, Kristina Hallam, Colleen Sexton, Stephanie Johnson, Su Min Chang","doi":"10.1148/ryct.230246","DOIUrl":"10.1148/ryct.230246","url":null,"abstract":"<p><p>Purpose To investigate the ability of kilovolt-independent (hereafter, kV-independent) and tin filter spectral shaping to accurately quantify the coronary artery calcium score (CACS) and radiation dose reductions compared with the standard 120-kV CT protocol. Materials and Methods This prospective, blinded reader study included 201 participants (mean age, 60 years ± 9.8 [SD]; 119 female, 82 male) who underwent standard 120-kV CT and additional kV-independent and tin filter research CT scans from October 2020 to July 2021. Scans were reconstructed using a Qr36f kernel for standard scans and an Sa36f kernel for research scans simulating artificial 120-kV images. CACS, risk categorization, and radiation doses were compared by analyzing data with analysis of variance, Kruskal-Wallis test, Mann-Whitney test, Bland-Altman analysis, Pearson correlations, and κ analysis for agreement. Results There was no evidence of differences in CACS across standard 120-kV, kV-independent, and tin filter scans, with median CACS values of 1 (IQR, 0-48), 0.6 (IQR, 0-58), and 0 (IQR, 0-51), respectively (<i>P</i> = .85). Compared with standard 120-kV scans, kV-independent and tin filter scans showed excellent correlation in CACS values (<i>r</i> = 0.993 and <i>r</i> = 0.999, respectively), with high agreement in CACS risk categorization (κ = 0.95 and κ = 0.93, respectively). Standard 120-kV scans had a mean radiation dose of 2.09 mSv ± 0.84, while kV-independent and tin filter scans reduced it to 1.21 mSv ± 0.85 and 0.26 mSv ± 0.11, cutting doses by 42% and 87%, respectively (<i>P</i> < .001). Conclusion The kV-independent and tin filter research CT acquisition techniques showed excellent agreement and high accuracy in CACS estimation compared with standard 120-kV scans, with large reductions in radiation dose. <b>Keywords:</b> CT, Cardiac, Coronary Arteries, Radiation Safety, Coronary Artery Calcium Score, Radiation Dose Reduction, Low-Dose CT Scan, Tin Filter, kV-Independent <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 3","pages":"e230246"},"PeriodicalIF":3.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211948/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141459042","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":"Infracardiac Total Anomalous Pulmonary Venous Connection.","authors":"Lucas de Pádua Gomes de Farias, Luciana de Pádua Silva Baptista, Márcio Campos Sampaio","doi":"10.1148/ryct.240018","DOIUrl":"10.1148/ryct.240018","url":null,"abstract":"","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 3","pages":"e240018"},"PeriodicalIF":3.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211932/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140945909","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":"Arrhythmic Mitral Valve Prolapse Phenotype: An Unsupervised Machine Learning Analysis Using a Multicenter Cardiac MRI Registry.","authors":"Ralph Kwame Akyea, Stefano Figliozzi, Pedro M Lopes, Klemens B Bauer, Sara Moura-Ferreira, Lara Tondi, Saima Mushtaq, Stefano Censi, Anna Giulia Pavon, Ilaria Bassi, Laura Galian-Gay, Arco J Teske, Federico Biondi, Domenico Filomena, Vasileios Stylianidis, Camilla Torlasco, Denisa Muraru, Pierre Monney, Giuseppina Quattrocchi, Viviana Maestrini, Luciano Agati, Lorenzo Monti, Patrizia Pedrotti, Bert Vandenberk, Angelo Squeri, Massimo Lombardi, António M Ferreira, Juerg Schwitter, Giovanni Donato Aquaro, Gianluca Pontone, Amedeo Chiribiri, José F Rodríguez Palomares, Ali Yilmaz, Daniele Andreini, Anca-Rezeda Florian, Marco Francone, Tim Leiner, João Abecasis, Luigi Paolo Badano, Jan Bogaert, Georgios Georgiopoulos, Pier-Giorgio Masci","doi":"10.1148/ryct.230247","DOIUrl":"10.1148/ryct.230247","url":null,"abstract":"<p><p>Purpose To use unsupervised machine learning to identify phenotypic clusters with increased risk of arrhythmic mitral valve prolapse (MVP). Materials and Methods This retrospective study included patients with MVP without hemodynamically significant mitral regurgitation or left ventricular (LV) dysfunction undergoing late gadolinium enhancement (LGE) cardiac MRI between October 2007 and June 2020 in 15 European tertiary centers. The study end point was a composite of sustained ventricular tachycardia, (aborted) sudden cardiac death, or unexplained syncope. Unsupervised data-driven hierarchical <i>k</i>-mean algorithm was utilized to identify phenotypic clusters. The association between clusters and the study end point was assessed by Cox proportional hazards model. Results A total of 474 patients (mean age, 47 years ± 16 [SD]; 244 female, 230 male) with two phenotypic clusters were identified. Patients in cluster 2 (199 of 474, 42%) had more severe mitral valve degeneration (ie, bileaflet MVP and leaflet displacement), left and right heart chamber remodeling, and myocardial fibrosis as assessed with LGE cardiac MRI than those in cluster 1. Demographic and clinical features (ie, symptoms, arrhythmias at Holter monitoring) had negligible contribution in differentiating the two clusters. Compared with cluster 1, the risk of developing the study end point over a median follow-up of 39 months was significantly higher in cluster 2 patients (hazard ratio: 3.79 [95% CI: 1.19, 12.12], <i>P</i> = .02) after adjustment for LGE extent. Conclusion Among patients with MVP without significant mitral regurgitation or LV dysfunction, unsupervised machine learning enabled the identification of two phenotypic clusters with distinct arrhythmic outcomes based primarily on cardiac MRI features. These results encourage the use of in-depth imaging-based phenotyping for implementing arrhythmic risk prediction in MVP. <b>Keywords:</b> MR Imaging, Cardiac, Cardiac MRI, Mitral Valve Prolapse, Cluster Analysis, Ventricular Arrhythmia, Sudden Cardiac Death, Unsupervised Machine Learning <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 3","pages":"e230247"},"PeriodicalIF":3.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211946/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141427481","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}