Scholarlink

Coronary artery disease (CAD) remains a leading global cause of mortality, highlighting the need for innovative diagnostic and prognostic tools. Cardiac magnetic resonance (CMR), utilizing techniques such as stress perfusion imaging, late gadolinium enhancement (LGE), and T1/T2 mapping, provides unparalleled precision in assessing myocardial perfusion, viability, and structural abnormalities. On the other hand, Artificial Intelligence (AI) has revolutionized CAD diagnostics by employing machine learning (ML) and deep learning (DL) algorithms to automate and enhance interpretations of imaging modalities, including CMR, single-photon emission computed tomography (SPECT), positron emission tomography (PET), and coronary computed tomographic angiography (CCTA). These algorithms improve myocardial perfusion quantification, coronary artery calcification (CAC) scoring, and stenosis detection, addressing challenges such as clinician workload and inter-reader variability. Previous studies highlighted AI’s ability to surpass traditional diagnostic methods, with tools like convolutional neural networks (CNNs), with acceptable sensitivity, specificity, and accuracy. The integration of CMR and AI represents a major advancement in non-invasive CAD management, enabling early detection, personalized treatment planning, and robust long-term prognostic evaluation. By combining the detailed imaging capabilities of CMR with AI’s analytical precision, this approach simplifies clinical workflows and reduces diagnostic uncertainty. These advancements highlight the potential of AI-enhanced imaging in transforming cardiovascular medicine. This chapter focuses on the integration of AI with Imaging modalities, particularly advanced CMR techniques, to improve the detection, characterization, and management of CAD.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Coronary Artery Disease: Integration of Artificial Intelligence with Advanced Imaging Techniques for Detection and Management

  • 章节

  • 发表日期：

    2025年

查看全文
  • Amir Ghaffari Jolfayi,
  • Reza Elahi,
  • Amir Azimi,
  • Hosein Tanha,
  • Saba Mehrtabar,
  • Samin Sadraei,
  • Shahrzad Shahrokhi Nejad,
  • Sanaz Asadian

摘要

Coronary artery disease (CAD) remains a leading global cause of mortality, highlighting the need for innovative diagnostic and prognostic tools. Cardiac magnetic resonance (CMR), utilizing techniques such as stress perfusion imaging, late gadolinium enhancement (LGE), and T1/T2 mapping, provides unparalleled precision in assessing myocardial perfusion, viability, and structural abnormalities. On the other hand, Artificial Intelligence (AI) has revolutionized CAD diagnostics by employing machine learning (ML) and deep learning (DL) algorithms to automate and enhance interpretations of imaging modalities, including CMR, single-photon emission computed tomography (SPECT), positron emission tomography (PET), and coronary computed tomographic angiography (CCTA). These algorithms improve myocardial perfusion quantification, coronary artery calcification (CAC) scoring, and stenosis detection, addressing challenges such as clinician workload and inter-reader variability. Previous studies highlighted AI’s ability to surpass traditional diagnostic methods, with tools like convolutional neural networks (CNNs), with acceptable sensitivity, specificity, and accuracy. The integration of CMR and AI represents a major advancement in non-invasive CAD management, enabling early detection, personalized treatment planning, and robust long-term prognostic evaluation. By combining the detailed imaging capabilities of CMR with AI’s analytical precision, this approach simplifies clinical workflows and reduces diagnostic uncertainty. These advancements highlight the potential of AI-enhanced imaging in transforming cardiovascular medicine. This chapter focuses on the integration of AI with Imaging modalities, particularly advanced CMR techniques, to improve the detection, characterization, and management of CAD.