Filters








29 Hits in 4.4 sec

Mini Review: Deep Learning for Atrial Segmentation From Late Gadolinium-Enhanced MRIs

Kevin Jamart, Zhaohan Xiong, Gonzalo D. Maso Talou, Martin K. Stiles, Jichao Zhao
2020 Frontiers in Cardiovascular Medicine  
In this paper, we conduct an in-depth review of the current state-of-the-art of deep learning approaches for atrial segmentation from late gadolinium-enhanced MRIs, and provide critical insights for overcoming  ...  This has been illustrated during the recent 2018 Atrial Segmentation Challenge for which most of the challengers developed deep learning approaches for atrial segmentation, reaching high accuracy (>90%  ...  We would also like to thank Vincent Guichot who provided great assistance for the creation of the figures.  ... 
doi:10.3389/fcvm.2020.00086 pmid:32528977 pmcid:PMC7266934 fatcat:cpik7i6tdrgodi2qivwnt5ywmu

Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review [article]

Lei Li and Veronika A. Zimmer and Julia A. Schnabel and Xiahai Zhuang
2022 arXiv   pre-print
This paper aims to provide a systematic review on computing methods for LA cavity, wall, scar and ablation gap segmentation and quantification from LGE MRI, and the related literature for AF studies.  ...  Hence, LA scar segmentation and quantification from LGE MRI can be useful in computer-assisted diagnosis and treatment stratification of AF patients.  ...  JA Schnabel and VA Zimmer would like to acknowledge funding from a Wellcome Trust IEH Award (WT 102431), an EPSRC programme grant (EP/P001009/1), and the Wellcome/EPSRC Center for Medical Engineering (  ... 
arXiv:2106.09862v3 fatcat:y7gk5bjqirgotbx3bwfq62rnqy

Deep Learning for Cardiac Image Segmentation: A Review

Chen Chen, Chen Qin, Huaqi Qiu, Giacomo Tarroni, Jinming Duan, Wenjia Bai, Daniel Rueckert
2020 Frontiers in Cardiovascular Medicine  
Deep learning has become the most widely used approach for cardiac image segmentation in recent years.  ...  In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography  ...  colleagues: Karl Hahn, Qingjie Meng, James Batten, and Jonathan Passerat-Palmbach who provided the insight and expertise that greatly assisted the work, and also constructive and thoughtful comments from  ... 
doi:10.3389/fcvm.2020.00025 pmid:32195270 pmcid:PMC7066212 fatcat:iw7xpnltn5cgbn5ullq2ldy3nq

Deep learning for cardiac image segmentation: A review [article]

Chen Chen, Chen Qin, Huaqi Qiu, Giacomo Tarroni, Jinming Duan, Wenjia Bai, Daniel Rueckert
2019 arXiv   pre-print
Deep learning has become the most widely used approach for cardiac image segmentation in recent years.  ...  In this paper, we provide a review of over 100 cardiac image segmentation papers using deep learning, which covers common imaging modalities including magnetic resonance imaging (MRI), computed tomography  ...  ) Fully automated; Multi-view Two-Task Recursive Attention Model LGE MRI LA; atrial scars Zabihollahy et al. (2018) Semi-automated; 2D CNN for scar tissue classification LGE MRI Myocardial scars  ... 
arXiv:1911.03723v1 fatcat:cwsq5hiaebgkza5ktmtyw553je

V-FCNN: Volumetric Fully Convolution Neural Network For Automatic Atrial Segmentation [article]

Nicoló Savioli, Giovanni Montana, Pablo Lamata
2018 arXiv   pre-print
A better characterization of these changes is desirable for the definition of clinical biomarkers, furthermore, thus there is a need for its fully automatic segmentation from clinical images.  ...  Atrial Fibrillation (AF) is a common electro-physiological cardiac disorder that causes changes in the anatomy of the atria.  ...  There is thus a need for a fully automatic segmentation of the atria from clinical images, especially in LGE studies.  ... 
arXiv:1808.01944v2 fatcat:vqhzrkc2ird2hdq67xcu7wz62m

Recent Advances in Fibrosis and Scar Segmentation from Cardiac MRI: A State-of-the-Art Review and Future Perspectives [article]

Yinzhe Wu, Zeyu Tang, Binghuan Li, David Firmin, Guang Yang
2021 arXiv   pre-print
For LGE CMR, many methods have demonstrated success in accurately segmenting scarring regions.  ...  Segmentation of cardiac fibrosis and scar are essential for clinical diagnosis and can provide invaluable guidance for the treatment of cardiac diseases.  ...  performances of the models based on 2D CNNs and models based on 3D CNNs.  ... 
arXiv:2106.15707v1 fatcat:tk4bz7nux5bhhb3s7bv5z64squ

Multi-Modality Cardiac Image Analysis with Deep Learning [article]

Lei Li, Fuping Wu, Sihang Wang, Xiahai Zhuang
2021 arXiv   pre-print
Secondly, two novel frameworks for left atrial scar segmentation and quantification from LGE MRI were presented.  ...  Moreover, compared with the other sequences LGE MRIs with gold standard labels are particularly limited, which represents another obstacle for developing novel algorithms for automatic segmentation and  ...  Section 3 presents two novel frameworks, namely LearnGC and AtrialJSQnet, for left atrial scar segmentation and quantification from LGE MRI (with the assist of an additional non-enhanced MRI).  ... 
arXiv:2111.04736v1 fatcat:pdxoa7p23jhknc7rvtdydurqma

Multiview Sequential Learning and Dilated Residual Learning for a Fully Automatic Delineation of the Left Atrium and Pulmonary Veins from Late Gadolinium-Enhanced Cardiac MRI Images

Guang Yang, Jun Chen, Zhifan Gao, Heye Zhang, Hao Ni, Elsa Angelini, Raad Mohiaddin, Tom Wong, Jennifer Keegan, David Firmin
2018 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  
The proposed framework leads to an automatic generation of a patient-specific model that can potentially enable an objective atrial scarring assessment for the atrial fibrillation patients.  ...  Late Gadolinium-Enhanced Cardiac MRI (LGE-CMRI) is an emerging imaging technology for myocardial infarction or scar detection based on the differences in the volume of residual gadolinium distribution  ...  DISCUSSIONS AND CONCLUSION In this work, we present a fully automatic deep learning framework to segment the LA and PV from LGE-CMRI images directly.  ... 
doi:10.1109/embc.2018.8512550 pmid:30440587 fatcat:hihm4h4otfbznaa7kxge54is3i

Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge [article]

Xiahai Zhuang, Jiahang Xu, Xinzhe Luo, Chen Chen, Cheng Ouyang, Daniel Rueckert, Victor M. Campello, Karim Lekadir, Sulaiman Vesal, Nishant RaviKumar, Yashu Liu, Gongning Luo (+11 others)
2021 arXiv   pre-print
Furthermore, compared with the other sequences LGE CMR images with gold standard labels are particularly limited, which represents another obstacle for developing novel algorithms for automatic segmentation  ...  In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR.  ...  two domains: bSSFP and LGE, respectively; (b) the two-stage cascaded segmentation network.  ... 
arXiv:2006.12434v2 fatcat:s4f3cchzhvhb3kyogwo3j5mmci

Fully Automated 3D Cardiac MRI Localisation and Segmentation Using Deep Neural Networks

Sulaiman Vesal, Andreas Maier, Nishant Ravikumar
2020 Journal of Imaging  
We evaluate the two proposed segmentation strategies on two cardiac MRI datasets, namely, the Automatic Cardiac Segmentation Challenge (ACDC) STACOM 2017, and Left Atrium Segmentation Challenge (LASC)  ...  For the latter, the same two-stage architecture is trained end-to-end.  ...  Conclusions In this paper, we introduced two strategies for training a segmentation network, namely, multi-stage and end-to-end, for automatic cardiac MRI localization and segmentation.  ... 
doi:10.3390/jimaging6070065 pmid:34460658 pmcid:PMC8321054 fatcat:aaqtmncrgbhcpdcekmzoulfr5q

Fully automated deep learning based segmentation of normal, infarcted and edema regions from multiple cardiac MRI sequences [article]

Xiaoran Zhang and Michelle Noga and Kumaradevan Punithakumar
2020 arXiv   pre-print
The training set for the CNN model consists of images acquired from 25 cases, and the gold standard labels are provided by trained raters and validated by radiologists.  ...  In this study, we propose a fully automated approach using deep convolutional neural networks (CNN) for cardiac pathology segmentation, including left ventricular (LV) blood pool, right ventricular blood  ...  [11] proposed a semiautomatic tool for LV scar segmentation using CNNs. Li et al. [6] proposed a fully automatic tool for left atrial scar segmentation.  ... 
arXiv:2008.07770v1 fatcat:u4tjs6ykzjg5tetvcpps4tmdui

Automatic 3D Surface Reconstruction of the Left Atrium From Clinically Mapped Point Clouds Using Convolutional Neural Networks

Zhaohan Xiong, Martin K. Stiles, Yan Yao, Rui Shi, Aaqel Nalar, Josh Hawson, Geoffrey Lee, Jichao Zhao
2022 Frontiers in Physiology  
In this study, for the first time, we proposed a novel deep learning framework for the automatic 3D surface reconstruction of the LA directly from point clouds acquired via widely used clinical mapping  ...  Many clinics rely on additional imaging such as MRIs/CTs to improve the accuracy of LA mapping.  ...  We would like to acknowledge the NIH/ NIGMS Center for Integrative Biomedical Computing (CIBC) at the University of Utah, United States for providing the MRI data.  ... 
doi:10.3389/fphys.2022.880260 pmid:35574484 pmcid:PMC9092219 fatcat:clydd47gure6pjo3md326vurm4

Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge

Xiahai Zhuang, Lei Li, Christian Payer, Darko Štern, Martin Urschler, Mattias P. Heinrich, Julien Oster, Chunliang Wang, Örjan Smedby, Cheng Bian, Xin Yang, Pheng-Ann Heng (+22 others)
2019 Medical Image Analysis  
Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated.  ...  This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction  ...  Transfer learning or domain adaptation was particularly emphasized to achieve the segmentation of LGE MRI with the knowledge from other MRI sequences.  ... 
doi:10.1016/j.media.2019.101537 pmid:31446280 pmcid:PMC6839613 fatcat:4a5fbpvz5jgi3hyafow2pcpfw4

Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge [article]

Xiahai Zhuang, Lei Li, Christian Payer, Darko Stern, Martin Urschler, Mattias P. Heinrich, Julien Oster, Chunliang Wang, Orjan Smedby, Cheng Bian, Xin Yang, Pheng-Ann Heng, Aliasghar Mortazi, Ulas Bagci (+18 others)
2019 arXiv   pre-print
Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated.  ...  This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction  ...  and Xiong (2018) 2018 150 LGE-MRI LA atrial fibrillation Table 3 : 3 Summary of submitted methods.  ... 
arXiv:1902.07880v1 fatcat:7w3sp334ejdotc3p7h2uwjpewe

The Role of AI in Characterizing the DCM Phenotype

Clint Asher, Esther Puyol-Antón, Maleeha Rizvi, Bram Ruijsink, Amedeo Chiribiri, Reza Razavi, Gerry Carr-White
2021 Frontiers in Cardiovascular Medicine  
Cardiac MRI (CMR) is well-placed in this respect, not only for its diagnostic utility, but the wealth of information captured in global and regional function assessment with the addition of unique tissue  ...  The final section of this paper is dedicated to the allied clinical applications to imaging, that incorporate artificial intelligence and have harnessed the comprehensive abundance of data from genetics  ...  Deformable model for segmentation, SAX images Avendi et al. (91) 2D CNN for RV Training 16 Mean 0.83 (SD Unspecified; localizing RV, Testing 16 0.14) mix of cardiac stacked conditions from autoencoder  ... 
doi:10.3389/fcvm.2021.787614 pmid:34993240 pmcid:PMC8724536 fatcat:v63dlo5mkzatfcy3bhsf3zkucq
« Previous Showing results 1 — 15 out of 29 results