A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging

By Zhaohan Xiong, Qing Xia, Ning Huang, C. Bian, Yefeng Zheng, Sulaiman Vesal, N. Ravikumar, Andreas K. Maier, Xin Yang, P. Heng and 30 more. Medical Image Anal., 2020

478 citations recorded by the source corpus.

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.

Subfields: Cardiology and Cardiovascular Medicine, Surgery

View Paper: https://www.semanticscholar.org/paper/df1a11f220b4c638bd91fb9458535c19c84e087f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Semi-supervised Left Atrium Segmentation with Mutual Consistency Training (2021, methodology): “We evaluate our proposed MC-Net against six recent state-of-the-art (SOTA) methods on the popular LA database [16].”
Continual Self-Supervised Learning: Towards Universal Multi-Modal Medical Data Representation Learning (2023, background): “…classification (RICORD [43]) and liver and liver tumor segmentation (LiTS [3]); (4) MRI: vestibular schwannoma segmentation (VS [37]) and left atrium segmentation (LA [47]); (5) Pathological imaging: colorectal cancer and healthy tissue classification (NCH [24]) and gland segmentation (GlaS [38]).”
Mutual consistency learning for semi-supervised medical image segmentation (2021, methodology): “In We also appreciate the eﬀorts to collect and share the datasets (Xiong et al., 2021; Clark et al., 2013; Bernard et al., 2018) and several public benchmarks (Yu et al., 2019; Li et al., 2020b; Luo et al., 2021a,b; Luo, 2020).”