• Corpus ID: 216553758

A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging

  title={A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging},
  author={Zhaohan Xiong and Qing Xia and Zhiqiang Hu and Ning Huang and Sulaiman Vesal and Nishant Ravikumar and Andreas K. Maier and Caizi Li and Qianqian Tong and Weixin Si and {\'E}lodie 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 Davide Borra and Alessandro Masci and Cristiana Corsi and Rashed Karim and Coen de Vente and Mitko Veta and Chandrakanth Jayachandran Preetha and Sandy Engelhardt and Menyun Qiao and Yuanyuan Wang and Qian Tao and Marta Nu{\~n}ez-Garcia and Oscar Camara and Yashu Liu and Kuanquan Wang and Nicol{\'o} Savioli and Pablo Lamata and Jichao Zhao},
Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) widely used for visualizing diseased cardiac structures, is a crucial first step for clinical diagnosis and treatment. However, direct segmentation of LGE-MRIs is challenging due to its attenuated contrast. Since most clinical studies have relied on manual and labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address… 

Figures from this paper

Anatomically-Informed Deep Learning on Contrast-Enhanced Cardiac MRI for Scar Segmentation and Clinical Feature Extraction

An anatomically-informed deep learning approach to myocardium and scar segmentation and clinical feature extraction from LGE-CMR images has the potential of a broad applicability in computer vision beyond cardiology, and even outside of medicine.

Performance Comparison of Deep Learning Approaches for Left Atrium Segmentation From LGE-MRI Data

U-Net was the best-performing algorithm overall, outperforming significantly AttnU- net with a Dice Coefficient of 0.9015±0.0308 (mean ± standard deviation), and no significant differences were found between U-Net and Attn U- net DS/DS+MI.

Attention V-Net: A Modified V-Net Architecture for Left Atrial Segmentation

The Attention V-Net architecture, which uses the 3D attention gate module, and applied it to the left atrium segmentation framework based on semi-supervised learning can effectively improve the accuracy of left atrial segmentation.

MRI Kardiyak MR Görüntülerinde Sol Kulakçık Bölütlenmesi İçin Derin Öğrenme Tabanlı Hibrit Model

  • İlkay Öksüz
  • Computer Science
    Turkish Studies-Information Technologies and Applied Sciences
  • 2020
This study shows that combining information from neural networks with random fields can improve the segmentation of left atrium volumetric cardiac MRI data.

Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation

This work introduces Maximum Entropy on Erroneous Predictions (MEEP), a training strategy for segmentation networks which selectively penalizes overconfident predictions, focusing only on misclassified pixels, increasing the network uncertainty in complex scenarios.

Semi-supervised Medical Image Segmentation through Dual-task Consistency

This work proposes a novel dual-task-consistency semi-supervised framework that can largely improve the performance by incorporating the unlabeled data and outperforms the state-of-the-art semi- supervised learning methods.

Parameter Decoupling Strategy for Semi-supervised 3D Left Atrium Segmentation

A novel semi-supervised segmentation model based on parameter decoupling strategy to encourage consistent predictions from diverse views is presented and has achieved a competitive result over the state-of-the-art semi- supervised methods on the Atrial Segmentation Challenge dataset, demonstrating the effectiveness of the framework.

MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations with Limited Labels

MisMatch is proposed, a semi-supervised segmentation frame- work based on the consistency between paired predictions which are derived from two differently learnt morphological feature perturbations which statistically outperforms state-of-the-art semi- supervised methods when only 6% of the total labels are used.

Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data

This study proposes an Adaptive Hierarchical Dual Consistency (AHDC) for the semi-supervised LA segmentation on cross-domain data and demonstrates the performance of the proposed AHDC on four 3D late gadolinium enhancement cardiac MR datasets from different centres and a 3D CT dataset.



Segmentation of the Left Atrium from 3D Gadolinium-Enhanced MR Images with Convolutional Neural Networks

This work presents a deep learning approach which is able to segment the left atrium from 3D GE-MRI, and trains the network on 100 data sets, predicted novel segmentations on the official test set and, according to the leaderboard, achieved a final score of 0.888.

Dilated Convolutions in Neural Networks for Left Atrial Segmentation in 3D Gadolinium Enhanced-MRI

A 3D CNN for volumetric segmentation of the left atrial chamber in LGE-MRI, based on the well known U-Net architecture is proposed, which shows that including global context through the use of dilated convolutions, helps in domain adaptation, and the overall segmentation accuracy is improved in comparison to a 3D U- net.

A Semantic-Wise Convolutional Neural Network Approach for 3-D Left Atrium Segmentation from Late Gadolinium Enhanced Magnetic Resonance Imaging

This work focuses on the design and development of a semantic-wise convolutional neural network based on the successful architecture U-Net (U-SWCNN), which was trained end-to-end with the 3-D data available from the 2018 Atrial Segmentation Challenge.

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

How far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies is measured, to open the door to highly accurate and fully automatic analysis of cardiac CMRI.

Deep Learning Based Method for Left Atrial Segmentation in GE-MRI

Two convolutional neural networks structures, fully Convolutional network (FCN) and U-Net, are explored to improve the accuracy and efficiency of LA segmentation in GE-MRI.

Fully Automatic Left Atrium Segmentation From Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network

This work has developed AtriaNet, a 16-layer convolutional neural network (CNN) that was tested on the largest known data set for LA segmentation, and to the best of the knowledge, it is the most robust approach that has ever been developed for segmenting LGE-MRIs.

A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging

The goal of this review paper is to discuss the structural and functional CMR indices that have been proposed thus far for clinical assessment of the cardiac chambers, including indices definitions, the requirements for the calculations, exemplar applications in cardiovascular diseases, and the corresponding normal ranges.

Automatic 3D Atrial Segmentation from GE-MRIs Using Volumetric Fully Convolutional Networks

This paper proposes an approach for automatic 3D atrial segmentation from Gadolinium-enhanced MRIs based on volumetric fully convolutional networks, which achieves satisfactory segmentation accuracy.

Convolutional Neural Networks for Segmentation of the Left Atrium from Gadolinium-Enhancement MRI Images

A left atrial segmentation pipeline that utilises a deep neural network for learning segmentations of the LA from Gadolinium enhancement magnetic resonance images (GE-MRI) is introduced.

Benchmark for Algorithms Segmenting the Left Atrium From 3D CT and MRI Datasets

A standardisation framework can be used to label and further analyse anatomical regions of the LA by performing the standardisation directly on the left atrial surface, including meshes exported from different electroanatomical mapping systems.