Filters








519 Hits in 8.3 sec

Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge

Victor M. Campello, Polyxeni Gkontra, Cristian Izquierdo, Carlos Martin-Isla, Alireza Sojoudi, Peter M. Full, Klaus Maier-Hein, Yao Zhang, Zhiqiang He, Jun Ma, Mario Parreno, Alberto Albiol (+35 others)
2021 IEEE Transactions on Medical Imaging  
Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference.  ...  To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease  ...  ACKNOWLEDGMENT The authors would like to thank NVIDIA and the Barcelona Super Computing (BSC) centre for providing the necessary computational resources for this work.  ... 
doi:10.1109/tmi.2021.3090082 pmid:34138702 fatcat:v55qqrms6rcbrewi2foiuvembq

Domain-Adversarial Learning for Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac MR Image Segmentation [article]

Cian M. Scannell and Amedeo Chiribiri and Mitko Veta
2020 arXiv   pre-print
This approach is evaluated on both seen and unseen domains from the M\&Ms challenge dataset and the domain-adversarial approach shows improved performance as compared to standard training.  ...  Deep learning has shown the potential to automate the requisite cardiac structure segmentation.  ...  Acknowledgements The authors of this paper declare that the segmentation method they implemented for participation in the M&Ms challenge has not used any pre-trained models nor additional MRI datasets  ... 
arXiv:2008.11776v1 fatcat:77bk33wkm5ck7lprkx57h6lzqu

Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge

Victor M Campello, Polyxeni Gkontra, Cristian Izquierdo, Carlos Martin-Isla, Et Al, Bjoern Menze
2021
To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease  ...  Cardiac Segmentation (MMs) Challenge, which was recently organized as part of the MICCAI 2020 Conference.  ...  ACKNOWLEDGMENT The authors would like to thank NVIDIA and the Barcelona Super Computing (BSC) Centre for providing the necessary computational resources for this work.  ... 
doi:10.5167/uzh-214495 fatcat:po3ijktc5jbmhacvy2jatwaguu

Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge [article]

Víctor M. Campello, José F. Rodríguez Palomares, Andrea Guala, Mahir Marakas, Matthias Friedrich, Karim Lekadir
2020 Zenodo  
The M&MS challenge is the first international competition to date on cardiac image segmentation combining data from different centres, vendors, diseases and countries at the same time.  ...  This is the challenge design document for the "Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge", accepted for MICCAI 2020.  ...  Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge Page 3 of 12 b) Report the platform (e.g. grand-challenge.org) used to run the challenge.  ... 
doi:10.5281/zenodo.3886268 fatcat:kj6vzgvqtjcu3l7dhcdjuiij4m

Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge [article]

Víctor M. Campello, José F. Rodríguez Palomares, Andrea Guala, Mahir Marakas, Matthias Friedrich, Karim Lekadir
2020 Zenodo  
The M&MS challenge is the first international competition to date on cardiac image segmentation combining data from different centres, vendors, diseases and countries at the same time.  ...  This is the challenge design document for the "Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge", accepted for MICCAI 2020.  ...  Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge Page 3 of 12 b) Report the platform (e.g. grand-challenge.org) used to run the challenge.  ... 
doi:10.5281/zenodo.3715889 fatcat:nml2woh6ibbzzfcdcda2wfstnq

Abstract: Studying Robustness of Semantic Segmentation under Domain Shift in Cardiac MRI [chapter]

Peter M. Full, Fabian Isensee, Paul F. Jäger, Klaus Maier-Hein
2021 Informatik aktuell  
In this work, we systematically study challenges and opportunities of domain transfer across images from multiple clinical centres and scanner vendors.  ...  Our proposed method ranked first at the Multi-Centre,  ...  Our proposed method ranked first at the Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge (M&Ms).  ... 
doi:10.1007/978-3-658-33198-6_64 fatcat:d63kby5hivf5blmbdzfeac2s3q

Multi-view SA-LA Net: A framework for simultaneous segmentation of RV on multi-view cardiac MR Images [article]

Sana Jabbar, Syed Talha Bukhari, Hassan Mohy-ud-Din
2021 arXiv   pre-print
Multi-view SA-LA model was extensively evaluated on the MICCAI 2021 Multi- Disease, Multi-View, and Multi- Centre RV Segmentation Challenge dataset (M&Ms-2021).  ...  M&Ms-2021 dataset consists of multi-phase, multi-view cardiac MR images of 360 subjects acquired at four clinical centers with three different vendors.  ...  The most recent challenge hosted from MICCAI platform was the Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac Image Segmentation Challenge (M&Ms-2020).  ... 
arXiv:2110.00682v1 fatcat:2oy7ytmuhjfvjazr4kn3mrpfz4

Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI (M&Ms-2) [article]

Carlos Martín-Isla, José F. Rodríguez Palomares, Andrea Guala, Sergio Escalera, Karim Lekadir
2021 Zenodo  
The M&Ds challenge is the first international competition to date on cardiac right ventricle segmentation and diagnosis combining data from different centres, vendors and diseases at the same time.  ...  It will evaluate the generalisation ability of machine/deep learning and cross-domain transfer learning techniques for abnormal cardiac imaging right ventricle segmentation and righ ventricle related disease  ...  Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI (M&Ms-2) Provide a timetable for the challenge.  ... 
doi:10.5281/zenodo.4573983 fatcat:wiilsibbzzbulefyxtbufmpzvi

Disentangled Representations for Domain-generalized Cardiac Segmentation [article]

Xiao Liu, Spyridon Thermos, Agisilaos Chartsias, Alison O'Neil, Sotirios A. Tsaftaris
2020 arXiv   pre-print
Robust cardiac image segmentation is still an open challenge due to the inability of the existing methods to achieve satisfactory performance on unseen data of different domains.  ...  In this paper, we propose two data augmentation methods that focus on improving the domain adaptation and generalization abilities of state-to-the-art cardiac segmentation models.  ...  Experiments on the diverse dataset from the STACOM 2020 Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge (M&Ms challenge) show the superiority of the proposed augmentation  ... 
arXiv:2008.11514v1 fatcat:fysrlawdqrdexay3qrii6abs5q

Multi-center, multi-vendor automated segmentation of left ventricular anatomy in contrast-enhanced MRI [article]

Carla Sendra-Balcells, Víctor M. Campello, Carlos Martín-Isla, David Vilades Medel, Martín Luís Descalzo, Andrea Guala, José F. Rodríguez Palomares, Karim Lekadir
2021 arXiv   pre-print
This work investigates for the first time multi-center and multi-vendor LV segmentation in LGE-MRI, by proposing, implementing and evaluating in detail several strategies to enhance model generalizability  ...  The results obtained based on a new multi-center LGE-MRI dataset acquired in four clinical centers in Spain, France and China, show that the combination of data augmentation and transfer learning can lead  ...  Entitled "Multi-Center, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms)", the study demonstrated that single-center, single-vendor neural networks do not generalize naturally when segmenting  ... 
arXiv:2110.07360v2 fatcat:6udrjjyurra6va6lnywtlrtpay

A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark [article]

Yunhe Gao, Mu Zhou, Di Liu, Zhennan Yan, Shaoting Zhang, Dimitris N. Metaxas
2022 arXiv   pre-print
The key designs incorporate desirable inductive bias, hierarchical modeling with linear-complexity attention, and multi-scale feature fusion in a spatially and semantically global manner.  ...  To tackle these challenges, we present UTNetV2 as a data-scalable Transformer towards generalizable medical image segmentation.  ...  The M&Ms (Multi-centre, multi-vendor, and multi-disease cardiac segmentation) and M&Ms-2 (Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI) 40 are challenges in  ... 
arXiv:2203.00131v3 fatcat:dmuh4yga4rahzjjdy4ttg7eei4

Style Curriculum Learning for Robust Medical Image Segmentation [article]

Zhendong Liu, Van Manh, Xin Yang, Xiaoqiong Huang, Karim Lekadir, Víctor Campello, Nishant Ravikumar, Alejandro F Frangi, Dong Ni
2021 arXiv   pre-print
Extensive experiments on the public M&Ms Challenge dataset demonstrate that our proposed framework can generalise deep models well to unknown distributions and achieve significant improvements in segmentation  ...  This is particularly pronounced in multi-centre studies involving data acquired using multi-vendor scanners, with variations in acquisition protocols.  ...  Extensive experiments on public data from the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge [3] show that our method outperforms all 2D methods, and is on par with  ... 
arXiv:2108.00402v1 fatcat:t3ogxbgauvhhvkc7ifoqhjadcm

Automatic Segmentation of Left Ventricle in Cardiac Magnetic Resonance Images [article]

Garvit Chhabra, J. H. Gagan, J. R. Harish Kumar
2022 arXiv   pre-print
We report validations on 320 scans containing 5,273 annotated slices which are publicly available through the Multi-Centre, Multi-Vendor, and Multi-Disease Cardiac Segmentation (M&Ms) Challenge.  ...  Segmentation of the left ventricle in cardiac magnetic resonance imaging MRI scans enables cardiologists to calculate the volume of the left ventricle and subsequently its ejection fraction.  ...  We would also like to thank the organizers of the M&Ms challenge for providing us with a diverse collection of cardiac MR studies.  ... 
arXiv:2201.12805v1 fatcat:7qxylovxojaa5agajzrvonu3ay

Style-invariant Cardiac Image Segmentation with Test-time Augmentation [article]

Xiaoqiong Huang, Zejian Chen, Xin Yang, Zhendong Liu, Yuxin Zou, Mingyuan Luo, Wufeng Xue, Dong Ni
2020 arXiv   pre-print
Second, we build up a robust cardiac segmentation model based on the U-Net structure.  ...  In this paper, we propose a novel style-invariant method for cardiac image segmentation.  ...  The framework was trained and evaluated on the Multi-Centre, Multi-Vendor & Multi-Disease Cardiac Image Segmentation Challenge (M&Ms 2020) dataset [2] .  ... 
arXiv:2009.12193v1 fatcat:xejpzshrgzeapaaxgte2j7d76m

Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?

Youssef Skandarani, Pierre-Marc Jodoin, Alain Lalande
2021 Algorithms  
To do so, we gauged the performance of three segmentation models, namely U-Net, Attention U-Net, and ENet, trained with different loss functions on expert and non-expert ground truth for cardiac cine–MRI  ...  Evaluation was done with classic segmentation metrics (Dice index and Hausdorff distance) as well as clinical measurements, such as the ventricular ejection fractions and the myocardial mass.  ...  Acknowledgments: We would like to acknowledge Ivan Porcherot for the tremendous work in annotating the data sets. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/a14070212 fatcat:b3hsk6sj25adhl7qkh7xsxceca
« Previous Showing results 1 — 15 out of 519 results