Difference between revisions of "Publications/xiong.20.media"

From LRDE

Line 6: Line 6:
 
| volume = 67
 
| volume = 67
 
| pages = 101832
 
| pages = 101832
| authors = Zhaohan Xiong, Qing Xia, Zhiqiang Hu, Ning Huang, Cheng Bian, Yefeng Zheng, Sulaiman Vesal, Nishant Ravikumar, Andreas Maier, Xin Yang, Pheng-Ann Heng, Dong Ni, Caizi Li, Qianqian Tong, Weixin Si, Elodie Puybareau, Younes Khoudli, Thierry Géraud, Chen Chen, Wenjia Bai, Daniel Rueckert, Lingchao Xu, Xiahai Zhuang, Xinzhe Luo, Shuman Jia, Maxime Sermesant, Yashu Liu, Kuanquan Wang, Davide Borra, Alessandro Masci, Cristiana Corsi, Coen de Vente, Mitko Veta, Rashed Karim, Chandrakanth Jayachandran Preetha, Sandy Engelhardt, Menyun Qiao, Yuanyuan Wang, Qian Tao, Marta Nunez-Garcia, Oscar Camara, Nicolo Savioli, Pablo Lamata, Jichao Zhao
+
| authors = Zhaohan Xiong, Qing Xia, Zhiqiang Hu, Ning Huang, Cheng Bian, Yefeng Zheng, Sulaiman Vesal, Nishant Ravikumar, Andreas Maier, Xin Yang, Pheng-Ann Heng, Dong Ni, Caizi Li, Qianqian Tong, Weixin Si, Élodie Puybareau, Younes Khoudli, Thierry Géraud, Chen Chen, Wenjia Bai, Daniel Rueckert, Lingchao Xu, Xiahai Zhuang, Xinzhe Luo, Shuman Jia, Maxime Sermesant, Yashu Liu, Kuanquan Wang, Davide Borra, Alessandro Masci, Cristiana Corsi, Coen de Vente, Mitko Veta, Rashed Karim, Chandrakanth Jayachandran Preetha, Sandy Engelhardt, Menyun Qiao, Yuanyuan Wang, Qian Tao, Marta Nunez-Garcia, Oscar Camara, Nicolo Savioli, Pablo Lamata, Jichao Zhao
 
| None = Left atrium, Convolutional neural networks, Late gadolinium-enhanced magnetic resonance imaging, Image segmentation
 
| None = Left atrium, Convolutional neural networks, Late gadolinium-enhanced magnetic resonance imaging, Image segmentation
 
| abstract = 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-MRIscurrently 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 CNNsin 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.
 
| abstract = 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-MRIscurrently 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 CNNsin 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.
Line 28: Line 28:
 
Nishant Ravikumar and Andreas Maier and Xin Yang and
 
Nishant Ravikumar and Andreas Maier and Xin Yang and
 
Pheng-Ann Heng and Dong Ni and Caizi Li and Qianqian Tong
 
Pheng-Ann Heng and Dong Ni and Caizi Li and Qianqian Tong
and Weixin Si and Elodie Puybareau and Younes Khoudli and
+
and Weixin Si and \'Elodie Puybareau and Younes Khoudli and
 
Thierry G\'<nowiki>{</nowiki>e<nowiki>}</nowiki>raud and Chen Chen and Wenjia Bai and Daniel
 
Thierry G\'<nowiki>{</nowiki>e<nowiki>}</nowiki>raud and Chen Chen and Wenjia Bai and Daniel
 
Rueckert and Lingchao Xu and Xiahai Zhuang and Xinzhe Luo
 
Rueckert and Lingchao Xu and Xiahai Zhuang and Xinzhe Luo

Revision as of 18:20, 21 May 2021

Abstract

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-MRIscurrently 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 CNNsin 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.


Bibtex (lrde.bib)

@Article{	  xiong.20.media,
  title		= {A global benchmark of algorithms for segmenting the left
		  atrium from late gadolinium-enhanced cardiac magnetic
		  resonance imaging},
  journal	= {Medical Image Analysis},
  volume	= {67},
  pages		= {101832},
  year		= {2021},
  issn		= {1361-8415},
  doi		= {10.1016/j.media.2020.101832},
  author	= {Zhaohan Xiong and Qing Xia and Zhiqiang Hu and Ning Huang
		  and Cheng Bian and Yefeng Zheng and Sulaiman Vesal and
		  Nishant Ravikumar and Andreas Maier and Xin Yang and
		  Pheng-Ann Heng and Dong Ni and Caizi Li and Qianqian Tong
		  and Weixin Si and \'Elodie Puybareau and Younes Khoudli and
		  Thierry G\'{e}raud and Chen Chen and Wenjia Bai and Daniel
		  Rueckert and Lingchao Xu and Xiahai Zhuang and Xinzhe Luo
		  and Shuman Jia and Maxime Sermesant and Yashu Liu and
		  Kuanquan Wang and Davide Borra and Alessandro Masci and
		  Cristiana Corsi and Coen {de Vente} and Mitko Veta and
		  Rashed Karim and Chandrakanth Jayachandran Preetha and
		  Sandy Engelhardt and Menyun Qiao and Yuanyuan Wang and Qian
		  Tao and Marta Nunez-Garcia and Oscar Camara and Nicolo
		  Savioli and Pablo Lamata and Jichao Zhao},
  keywords	= {Left atrium, Convolutional neural networks, Late
		  gadolinium-enhanced magnetic resonance imaging, Image
		  segmentation},
  abstract	= {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.}
}