Program
Note that this year workshop will be held virtually with the same format and platform of the MICCAI 2020 main conference. More details about the workshop platform will be available later on this page.
| 9:15 – 9:30 UTC | Welcome |
| 9:30 – 11:00 UTC | MyoPS Challenge |
| 9:30 – 9:35 | Introduction |
| 9:35 – 9:45 | Stacked BCDU-net with semantic CMR synthesis: application to Myocardial Pathology Segmentation challenge. (Carlos Mart́ın-Isla, Maryam Asadi-Aghbolaghi, Polyxeni Gkontra, Victor M. Campello, Sergio Escalera, Karim Lekadir) |
| 9:45 – 9:55 | EfficientSeg: A Simple but Efficient Solution to Myocardial Pathology Segmentation Challenge (Jianpeng Zhang, Yutong Xie, Zhibin Liao, Johan Verjans, Yong Xia) |
| 9:55 – 10:05 | Two-stage Method for Segmentation of the Myocardial Scars and Edema on Multi-sequence Cardiac Magnetic Resonance (Yanfei Liu, Maodan Zhang, Qi Zhan, Dongdong Gu, Guocai Liu) |
| 10:05 – 10:15 | Multi-Modality Pathology Segmentation Framework: Application to Cardiac Magnetic Resonance Images (Zhen Zhang, Chenyu Liu, Wangbin Ding, Sihan Wang, Chenhao Pei, Mingjing Yang, Liqin Huang) |
| 10:15 – 10:25 | Myocardial Edema and Scar Segmentation using a Coarse-to-Fine Framework with Weighted Ensemble (Shuwei Zhai, Ran Gu, Wenhui Lei, Guotai Wang) |
| 10:25 – 10:30 | Q&A (oral session) |
| 10:30 – 10:45 | Graphical Abstract Session |
| Exploring ensemble applications for multi-sequence myocardial pathology segmentation (Markus J. Ankenbrand, David Lohr,Laura M. Schreiber) | |
| Max-Fusion U-Net for Multi-Modal Pathology Segmentation with Attention and Dynamic Resampling (Haochuan Jiang, Chengjia Wang, Agisilaos Chartsias, Sotirios A.Tsaftaris) | |
| Fully automated deep learning based segmentation of normal, infarcted and edema regions from multiple cardiac MRI sequences (Xiaoran Zhang, Michelle Noga, Kumaradevan Punithakumar) | |
| CMS-UNet: Cardiac Multi-task Segmentation in MRI with a U-shaped Network (Weisheng Li, Linhong Wang, Sheng Qin) | |
| Automatic Myocardial Scar Segmentation from Multi-Sequence Cardiac MRI using Fully Convolutional Densenet with Inception and Squeeze-Excitation Module (Tewodros Weldebirhan Arega, StéphanieBricq) | |
| Dual Attention U-net for Multi-Sequence Cardiac MR Images Segmentation (Hong Yu, Sen Zha, Yubin Huangfu, Chen Chen, Meng Ding, Jiangyun Li) | |
| Accurate Myocardial Pathology Segmentation with Residual U-Net (Altunok Elif, Oksuz Ilkay) | |
| Stacked and Parallel U-Nets with Multi-Output for Myocardial Pathology Segmentation (Zhou Zhao, Nicolas Boutry, ÉlodiePuybareau) | |
| Dual-path Feature Aggregation Network Combined Multi-layer Fusion for Myocardial Pathology Segmentation with Multi-sequence Cardiac MR (Feiyan Li, Weisheng Li) | |
| Cascaded Framework with Complementary CMR Information for Myocardial Pathology Segmentation (Jun Ma) | |
| CMRadjustNet: Recognition and standardization of cardiac MRI orientation via multi-tasking learning and deep neural networks (Ke Zhang, Xiahai Zhuang) | |
| 10:45 – 10:55 | Q&A (poster session) |
| 10:55 – 11:00 | Summary and Award |
| 11:00 – 12:30 UTC | M&MS Challenge |
| 11:00 – 11:10 | Challenge presentation |
| 11:10 – 11:25 | A generalizable deep-learning approach for cardiac magnetic resonance image segmentation using image augmentation and attention U-Net (Fanwei Kong fanwei_kong@berkeley.edu) |
| 11:25 – 11:40 | Histogram Matching Augmentation for Domain Adaptation with Application to Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Image Segmentation (Jun Ma junma@njust.edu.cn) |
| 11:40 – 11:55 | Deidentifying MRI data domain by iterative backpropagation (Mario Parreño maparla@prhlt.upv.es) |
| 11:55 – 12:10 | Semi-supervised Cardiac Image Segmentation via Label Propagation and Style Transfer (Yao Zhang zhangyao215@mails.ucas.ac.cn) |
| 12:10 – 12:25 | The Effect of Data Augmentation on Robustness against Domain Shifts in cMRI segmentation (Peter M. Full p.full@dkfz-heidelberg.de) |
| 12:25 – 12:30 | Closing and awards |
| 12:30 – 14:00 UTC | Lunch break + Regular Posters |
| Poster 01: A cartesian grid representation of left atrial appendages for deep learning-based estimation of thrombogenic risk predictors, (César Acebes Pinilla) | |
| Poster 02: Automatic Detection of Landmarks for Fast Cardiac MR Image Registration, (Mia Mojica, Mihaela Pop, Mehran Ebrahimi) | |
| Poster 03: Automatic multiplanar CT reformatting from trans-axial into left ventricle short-axis view, (Marta Nuñez Garcia, Nicolas Cedilnik, Shuman Jia, Hubert Cochet, Maxime Sermesant) | |
| Poster 04: PC-U Net: Learning to Jointly Reconstruct and Segment the Cardiac Walls in 3D from CT Data, (Meng Ye, Qiaoying Huang, DONG YANG, Pengxiang Wu, Jingru Yi, Leon Axel, Dimitris Metaxas) | |
| Poster 05: Shape constrained CNN for cardiac MR segmentation with simultaneous prediction of shape and pose parameters, (Sofie Tilborghs, Tom Dresselaers, Piet Claus, Jan Bogaert, Frederik Maes) | |
| Poster 06: Quality-aware semi-supervised learning for CMR segmentation, (Bram Ruijsink, Esther Puyol Anton, Ye Li, Wenjia Bai, Reza Razavi, Andrew King) | |
| Poster 07: Left atrial ejection fraction estimation using SEGANet for fully automated segmentation of CINE MRI, (Ana Lourenço, Eric Kerfoot, Connor Dibblin, Ebraham Alskaf, Mustafa Anjari, Anil Bharath, Andrew King, Henry Chubb, Teresa Correia, Marta Varela) | |
| Poster 08: 4D Flow Magnetic Resonance Imaging for Left Atrial Haemodynamic Characterization and Model Calibration, (Xabier Morales, Jordi Mill, Gaspar Delso, Marta Sitges, Ada Doltra, Filip Loncaric, Bart Bijnens, Oscar Camara) | |
| Poster 09: Segmentation-free Estimation of Aortic Diameters from MRI Using Deep Learning, (Axel Aguerreberry, Alain Lalande, Ezequiel de la Rosa, Elmer Fernández) | |
| 14:00 – 15:00 UTC | The right ventricle – The no longer forgotten chamber Keynote speaker: Associate Professor Pamela Moceri, MD, PhD Although it has been under studied as compared to the left ventricle, the recognition of the central role of the right ventricle is growing in a large number of pathologies. The right ventricle is anatomically and functionally different than the left ventricle. This prevents us from extrapolating our knowledge of left-ventricular physiology and pathophysiology to the right ventricle. Distinct right ventricular patterns are observed in pressure overload, volume overload and RV cardiomyopathy. Imaging, new right ventricular function quantification tools and modeling RV response to different loading conditions may help us better understand the mechanisms of right ventricular failure and thus prevent it. Pamela Moceri is Associate Professor (MD, PhD) in Cardiology In Nice (France, Centre Hospitalier Universitaire de Nice). She is responsible of the local competence center for the management of pulmonary hypertension and complex congenital heart diseases. Her clinical and research activity focus mainly on imaging the right ventricle: echocardiography, diagnosis and patient care in pulmonary hypertension or congenital heart disease. She combines clinical data to statistical modeling of right ventricular shape and function. |
| 15:00 – 16:30 UTC | Regular Oral Session |
| 15:00 – 15:11 | A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI (Nick Byrne, James Clough, Giovanni Montana, Andrew King) |
| 15:11 – 15:22 | Estimation of imaging biomarker’s progression in post-infarct patients using cross-sectional data (Marta Nuñez Garcia, Nicolas Cedilnik, Shuman Jia, Hubert Cochet, Marco Lorenzi, Maxime Sermesant) |
| 15:22 – 15:33 | Graph convolutional regression of cardiac depolarization from sparse endocardial maps (Felix Meister, Tiziano Passerini, Chloe Audigier, Èric Lluch, Viorel Mihalef, Hiroshi Ashikaga, Andreas Maier, Henry Halperin, Tommaso Mansi) |
| 15:33 – 15:44 | Measure Anatomical Thickness from Cardiac MRI with Deep Neural Networks (Qiaoying Huang, Eric Chen, Hanchao Yu, Yimo Guo, Terrence Chen, Dimitris Metaxas, Shanhui Sun) |
| 15:44 – 15:55 | PIEMAP: Personalized Inverse Eikonal Model from cardiac Electro-Anatomical Maps (Thomas Grandits, Simone Pezzuto, Jolijn Lubrecht, Thomas Pock, Gernot Plank, Rolf Krause) |
| 15:55 – 16:06 | Towards meshfree patient-specific mitral valve modeling (Judit Ros, Oscar Camara, Uxio Hermida, Bart Bijnens, Hernán G. Morales) |
| 16:06 – 16:17 | Modelling Fine-rained Cardiac Motion via Spatio-temporal Graph Convolutional Networks to Boost the Diagnosis of Heart Conditions (Ping Lu, Wenjia Bai, Daniel Rueckert, Alison Noble) |
| 16:17 – 16:28 | Estimation of Cardiac Valve Annuli Motion with Deep Learning (Eric Kerfoot, Carlos Escudero King, Tefvik Ismail, David Nordsletten, Renee Miller) |
| 16:30 – 18:00 UTC | EMIDEC Challenge |
| 16:30 – 16:45 | Presentation of the EMIDEC challenge and of the dataset. Alain LALANDE (Dijon, France). |
| 16:45 – 16:55 | Comparison of a Hybrid Mixture Model and a CNN for the Segmentation Myocardial Pathologies in Delayed Enhancement MRI. Markus HUELLEBRAND et al. (Berlin, Germany) |
| 16:55 – 17:05 | Cascaded Convolutional Neural Network for Automatic Myocardial Infarction Segmentation from Delayed- Enhancement Cardiac MRI. Yichi ZHANG (Beijing, China) |
| 17:05 – 17:15 | Cascaded Framework for Myocardial Infarction Segmentation from Delayed-Enhancement Cardiac MRI. Jun MA (Nanjing, China) |
| 17:15 – 17:25 | Automatic Myocardial Disease Prediction From Delayed-Enhancement Cardiac MRI and Clinical Information. Ana LOURENCO et al. (London, UK) |
| 17:25 – 17:35 | SM2N2: A Stacked Architecture for Multimodal Data and its Application to Myocardial Infarction Detection. Rishabh SHARMA et al. (Houston, USA) |
| 17:35 – 17:45 | A Hybrid Network for Automatic Myocardial Infarction Segmentation in Delayed Enhancement-MRI. Sen YANG et al. (Chengdu, China) |
| 17:45 – 18:00 | Results of the challenge and concluding remarks. Zhihao CHEN (Belfort, France) |
| 18:00 – 18:30 UTC | Closing and Prize |