发表机构
Technical University Munich; TUM University Hospital; Aix-Marseille Université; Imperial College London（慕尼黑工业大学; 慕尼黑工业大学附属医院; 艾克斯-马赛大学; 伦敦帝国学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出NISF++架构，从2D短轴和长轴MR视图构建心脏3D+时间隐式表示，实现时空一致性与运动校正，在UK-Biobank120人队列中获良好分割与运动校正效果。
AI 中文摘要
心脏磁共振（CMR）成像的临床采集涉及沿径向和纵向获取心脏的横截面。尽管这些平面是心脏的2D横截面图像，但放射科医生能够理解被成像器官的3D空间和连续时间特性。然而，用于处理CMR图像的传统深度学习架构并非如此，它们依赖于平面内和基于网格的操作，因此无法有机整合来自所有成像平面的信息。本文在先前神经隐式分割函数（NISF）工作的基础上，克服了CMR领域心脏功能建模中未解决的挑战。对于给定受试者，我们的架构会从所有可用的采集平面构建共享的3D+时间表示，无论其方向如何。根据设计，任意成像平面方向上的预测都是同一3D表示的横截面，从而在所有切片间实现时空一致性。此外，我们的架构使成像平面的旋转和平移参数可学习，允许在刚性假设下校正切片采集间常见的呼吸和患者运动。还可在任意所需分辨率下对4D的强度和分割进行插值。我们对英国生物银行（UK-Biobank）CMR成像数据的120名受试者子队列开展研究，结果显示我们的平面内分割性能与现有CMR分割方法相当，并探讨了多数失败案例源于真实分割的局限性，我们的表示所做预测比其原始训练数据具有更好的解剖准确性。我们还评估了运动校正能力，在切片对齐方面展现出定量和定性的改进。
英文摘要
Clinical acquisition in cardiac magnetic resonance (CMR) imaging involves obtaining cross-sectional planes of the heart along the radial and longitudinal directions. Despite these planes being 2D cross-sectional images of the heart, radiologists understand the 3D spatial and continuous temporal nature of the organ being imaged. The same can not be said about the conventional deep learning architectures used to process CMR images, which rely on in-plane and grid-based operations, and are hence unable to organically integrate information from all imaging planes. This paper builds upon previous work on neural implicit segmentation functions (NISF) to overcome unaddressed challenges in cardiac function modeling in the CMR domain. For a given subject, our architecture builds a shared 3D+time representations from all available acquisition planes regardless of orientation. By design, predictions along any imaging plane orientation are cross-sections of the same 3D representation, leading to spatio-temporal consistency across all slices. Moreover, our architecture makes the rotation and translation parameters of imaging planes learnable, allowing us to correct for the commonplace respiratory and patient motion between slice acquisitions under a rigid assumption. Furthermore, interpolation of intensities and segmentation can be performed in 4D at any desired resolution. We perform our study on a 120 subject sub-cohort of CMR imaging data from the UK-Biobank. Our in-plane segmentation performance is on-par with existing CMR segmentation methods and explore how the majority of failure cases arise from limitations in the ground-truth segmentation, for which our representations make predictions with better anatomical accuracy than its original training data. We also evaluate our motion-correction capabilities, displaying quantitative and qualitative improvements in slice alignment.
