arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.27003physics.med-ph
收藏

基于人工智能的常规磁共振成像心脏形状重建

AI-enabled cardiac shape reconstruction from routine magnetic resonance imaging

Texas A&M University(德克萨斯农工大学);Brown University(布朗大学);Cincinnati Children’s Hospital Medical Center(辛辛那提儿童医院医学中心);Univ Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint-Étienne, CNRS, Inserm, CREATIS UMR 5220, U1294(里昂大学,里昂国立应用科学学院,克洛德·贝尔纳里昂大学1,圣艾蒂安大学,法国国家科学研究中心,法国国家健康与医学研究院,CREATIS);University of Arizona(亚利桑那大学);Savoie Mont-Blanc University(萨瓦勃朗峰大学);Texas A&M University School of Engineering Medicine(德克萨斯农工大学工程医学院)
Tanmay Mukherjee, Neil Gautam, Nikhil Kadivar, Elizabeth M. Fugate, Kyle J. Myers, Diana Lindquist, Pierre Croisille, Sakthivel Sadayappan, Patrick Clarysse, Ja… 展开作者

Tanmay Mukherjee, Neil Gautam, Nikhil Kadivar, Elizabeth M. Fugate, Kyle J. Myers, Diana Lindquist, Pierre Croisille, Sakthivel Sadayappan, Patrick Clarysse, Jacques Ohayon, Roderic Pettigrew, George Karniadakis, Reza Avazmohammadi

AI总结:

本文提出一种基于神经场的重建框架,通过学习连续形状表示,从稀疏平面轮廓数据中恢复3D心脏几何,提高了在复杂解剖区域的几何保真度。

摘要:

计算模型的 cardiac structure and function 正日益成为开发 subject-specific cardiac digital twins 的核心,有助于改进 contractile dysfunction, pathological remodeling 和 electrical abnormalities 的表征。这些模型的关键前提条件是准确地从医学影像中重建三维(3D)心脏解剖结构。多平面磁共振成像,特别是结合人工智能,提供了传统重建技术的一种临床可行替代方案。在本研究中,我们提出了一种神经场基于的重建框架,通过学习连续形状表示,从稀疏平面轮廓数据中恢复3D心脏几何。重建性能通过互补的 in-silico 和 in vivo 数据集评估,涵盖了采样密度和几何复杂性的变化。在两个数据集中,重建的网格与参考几何体高度吻合,证明了神经场方法能够忠实捕捉心脏平面轮廓。与传统局部插值方法相比,所提出的框架在解剖挑战区域,如左心室尖端和基底段,特别是在稀疏采样条件下,表现出改进的几何保真度。这些发现表明,基于神经场的重建提供了一种稳健且高效的多平面心脏形状恢复途径,特别适用于AI驱动的建模流程和数据有限的环境,如小动物和时间分辨心脏成像。

英文摘要:

Computational models of cardiac structure and function are increasingly central to the development of subject-specific cardiac digital twins, enabling improved characterization of contractile dysfunction, pathological remodeling, and electrical abnormalities. A critical prerequisite for these models is the accurate reconstruction of three-dimensional (3D) cardiac anatomy from medical imaging. Multi-planar magnetic resonance imaging, particularly when combined with artificial intelligence, offers a clinically feasible alternative to conventional reconstruction techniques. In this study, we present a neural field-based reconstruction framework that recovers 3D cardiac geometries from sparse planar contour data by learning continuous shape representations. Reconstruction performance was evaluated using complementary in-silico and in vivo datasets spanning variations in sampling density and geometric complexity. Across both datasets, reconstructed meshes closely matched reference geometries, demonstrating that the neural field approach faithfully captures cardiac planar contours. Compared with traditional local interpolation methods, the proposed framework exhibited improved geometric fidelity in anatomically challenging regions, including the left ventricular apex and basal segments, particularly under sparse sampling conditions. Collectively, these findings demonstrate that neural field-based reconstruction provides a robust and efficient pathway for multi-planar cardiac shape recovery, with particular relevance for AI-driven modeling pipelines and data-limited settings such as small-animal and time-resolved cardiac imaging.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑