Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand.
State Key Lab of Virtual Reality Technology and Systems, Beihang University, Beijing, China.
Med Image Anal. 2021 Jan;67:101832. doi: 10.1016/j.media.2020.101832. Epub 2020 Oct 16.
Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging community.
医学图像分割，特别是用于可视化病变心房结构的钆延迟增强磁共振成像（LGE-MRI），是房颤消融治疗的关键第一步。然而，由于对比剂引起的强度变化，直接对 LGE-MRI 进行分割具有挑战性。由于大多数临床研究都依赖于手动、劳动密集型方法，因此自动方法非常受欢迎，特别是经过优化的机器学习方法。为了解决这个问题，我们使用 154 个 3D LGE-MRI 组织了 2018 年左心房分割挑战赛，这是目前全球最大的心房 LGE-MRI 数据集，以及由三位医学专家分割的左心房的相关标签，最终吸引了 27 个国际团队的参与。在本文中，通过进行子组分析和进行超参数分析，对提交的算法使用技术和生物学指标进行了广泛分析，提供了卷积神经网络（CNN）的主要设计选择和实现最先进的左心房分割的实际考虑因素的总体情况。结果表明，顶级方法的 Dice 得分为 93.2%，平均表面到表面距离为 0.7 mm，明显优于之前的最先进方法。特别是，我们的分析表明，双顺序使用 CNN 的方法，其中第一个 CNN 用于自动感兴趣区域定位，随后的 CNN 用于精细的区域分割，比传统方法和包含单个 CNN 的机器学习方法取得了更好的结果。这项大规模的基准研究朝着改进心房 LGE-MRI 的分割方法迈出了重要的一步，将成为评估和比较该领域未来工作的重要基准。此外，这项研究的结果可能会扩展到其他成像数据集和模式，对更广泛的医学成像社区产生影响。
