Physica Medica, Год журнала: 2024, Номер 125, С. 104510 - 104510
Опубликована: Авг. 30, 2024
Язык: Английский
Clinical Cardiology, Год журнала: 2025, Номер 48(1)
Опубликована: Янв. 1, 2025
ABSTRACT Background Technological advancements in artificial intelligence (AI) are redefining cardiac imaging by providing advanced tools for analyzing complex health data. AI is increasingly applied across various modalities, including echocardiography, magnetic resonance (MRI), computed tomography (CT), and nuclear imaging, to enhance diagnostic workflows improve patient outcomes. Hypothesis Integrating into enhances image quality, accelerates processing times, improves accuracy, enabling timely personalized interventions that lead better Methods A comprehensive literature review was conducted examine the impact of machine learning deep algorithms on detection subtle patterns anomalies, key challenges such as data safety, regulatory barriers. Results Findings indicate integration reduces precision, contributing clinical decision‐making. Emerging techniques demonstrate ability identify abnormalities traditional methods may overlook. However, significant persist, standardization, compliance, safety concerns. Conclusions holds transformative potential significantly advancing diagnosis Overcoming barriers implementation will require ongoing collaboration among clinicians, researchers, bodies. Further research essential ensure safe, ethical, effective cardiology, supporting its broader application cardiovascular health.
Язык: Английский
Процитировано
3
Annals of Medicine and Surgery, Год журнала: 2025, Номер 87(4), С. 1947 - 1968
Опубликована: Фев. 27, 2025
Background: The application of artificial intelligence (AI) in cardiac imaging has rapidly evolved, offering enhanced accuracy and efficiency the diagnosis management cardiovascular diseases. This bibliometric study aimed to evaluate research trends, impact, scholarly output this expanding field. Methods: A systematic search was conducted on 14 August 2024 using Web Science Core Collection database. VOSviewer, CiteSpace, Biblioshiny were utilized for data analysis. Results: findings revealed a significant increase publications AI imaging, particularly from 2018 2023, with United States leading output. England have emerged as central hubs global network, highlighting their role generating high-quality impactful publications. University London identified top contributing institution, while Frontiers Cardiovascular Medicine most prolific journal. Keyword analysis highlighted machine learning, echocardiography, frequently occurring terms. time trend showed shift focus toward applications computed tomography (CT) magnetic resonance (MRI), recent keywords like ejection fraction, risk, heart failure reflecting emerging areas interest. Conclusion: Healthcare providers should consider integrating tools into practice, demonstrated potential enhance diagnostic improve patient outcomes. highlights rising importance personalized predictive care, urging healthcare stay informed about these advancements clinical decision-making management.
Язык: Английский
Процитировано
1
Seminars in Nuclear Medicine, Год журнала: 2025, Номер unknown
Опубликована: Апрель 1, 2025
Язык: Английский
Процитировано
1
Circulation Cardiovascular Imaging, Год журнала: 2025, Номер unknown
Опубликована: Май 13, 2025
BACKGROUND: Computed tomography (CT) attenuation correction scans are an intrinsic part of positron emission (PET) myocardial perfusion imaging using PET/CT, but anatomic information is rarely derived from these ultralow-dose CT scans. We aimed to assess the association between deep learning-derived cardiac chamber volumes (right atrial, right ventricular, left and atrial) mass (left ventricular) with flow reserve heart failure hospitalization. METHODS: included 18 079 patients consecutive PET/CT 6 sites. A learning model estimated ventricular computed imaging. Associations hospitalization reduced were assessed in a multivariable analysis. RESULTS: During median follow-up 4.3 years, 1721 (9.5%) experienced Patients 3 or 4 abnormal 7× more likely be hospitalized for compared normal volumes. In adjusted analyses, atrial volume (hazard ratio [HR], 1.25 [95% CI, 1.19–1.30]), (HR, 1.29 1.23–1.35]), 1.20–1.31]), 1.27 1.18–1.32]) independently associated (odds ratio, 1.14 1.0–1.19]) 1.12 1.6–1.17]) independent predictors reserve. CONCLUSIONS: Deep learning–derived predictive undergoing PET This data can routinely reported along other parameters improve risk prediction.
Язык: Английский
Процитировано
1
Journal of Personalized Medicine, Год журнала: 2025, Номер 15(3), С. 100 - 100
Опубликована: Март 3, 2025
Coronary artery disease remains the leading cause of morbidity and mortality worldwide. With changing clinical manifestation novel therapeutical options, precise phenotyping becomes increasingly important at point care. In management coronary disease, myocardial perfusion imaging (MPI) cornerstone practice. Although traditionally MPI has been primarily performed with single photon emission computed tomography (SPECT), nowadays, given spectrum greater precision additional assessment blood flow are desired. Due to fundamental advantages PET over SPECT, i.e., higher spatial resolution, accurate attenuation correction for each scan, count rates, sensitivity specificity than those SPECT estimated be approximately 90–92% vs. 83–88% 81–87% 70–76%, respectively, according meta-analysis data. Consequently, past decade, we have witnessed an increased uptake positron (PET) MPI. improved ability quantify flow, potential depict burden atherosclerosis low-dose tomography, PET/CT is uniquely positioned facilitate a comprehensive non-invasive providing opportunity medicine. The wealth data obtained during session can challenging integrate time image analysis. There therefore increasing interest in developing predefined thresholds or variables (scores) which combine multidimensional acquired Beyond MPI, also serve activity atherosclerotic plaque level, further refining our understanding biology hope enhanced prediction infarctions. this narrative review, present current applications focus specifically on two areas that recently garnered considerable interest—the integration multiparametric imaging.
Язык: Английский
Процитировано
0
Journal of Nuclear Cardiology, Год журнала: 2025, Номер unknown, С. 102170 - 102170
Опубликована: Март 1, 2025
Язык: Английский
Процитировано
0
Seminars in Nuclear Medicine, Год журнала: 2025, Номер 55(3), С. 291 - 293
Опубликована: Апрель 15, 2025
Язык: Английский
Процитировано
0
Future Cardiology, Год журнала: 2024, Номер 20(4), С. 197 - 207
Опубликована: Март 11, 2024
Evaluation of the performance ChatGPT-4.0 in providing prediagnosis and treatment plans for cardiac clinical cases by expert cardiologists.
Язык: Английский
Процитировано
1
Seminars in Nuclear Medicine, Год журнала: 2024, Номер 54(5), С. 635 - 637
Опубликована: Авг. 16, 2024
Язык: Английский
Процитировано
0
Physica Medica, Год журнала: 2024, Номер 125, С. 104510 - 104510
Опубликована: Авг. 30, 2024
Язык: Английский
Процитировано
0