8:30-8:35 Welcome and agenda
8:35-9:15 Keynote lecture
Keynote speaker: Professor Sotirios A. Tsaftaris (University of Edinburgh, UK)

Title: Disentangled representation learning in medical imaging.

The detection of disease, segmentation of anatomy and other classical analysis tasks, have seen incredible improvements due to deep learning. Yet these advances need lots of data: for every new task, new modality, new hospital more training data are needed. In this talk, I will show how deep neural networks can learn latent and disentangled embeddings suitable for several analysis tasks in the heart. Within a multi-task learning setting I will show that the same framework can learn embeddings drawing supervision from self-supervised tasks that use reconstruction and also temporal dynamics overall reducing considerably need for annotation. I will discuss how different architectural choices can solve key problems in multimodal data processing and critically also allow us to learn reducing need for image-level annotations by obtaining supervision also from text-based health records. I will conclude by highlighting challenges for deep learning in healthcare in general.

9:15-10:30 Regular papers
9:15-9:27 EP Anton, B Ruijsink, J Clough, I Oksuz, D Rueckert, R Razavi, A King
Assessing the Impact of Blood Pressure on Cardiac Function Using Interpretable Biomarkers and Variational Autoencoders
9:27-9:40 Z Tan, Y Duan, Z Wu, J Feng, J Zhou
A Cascade Regression Model for Anatomical Landmark Detection
9:40-9:52 V van Hal, D Zhao, K Gilbert, TPB Gamage, C Mauger, RN Doughty, ME Legget, J Zhao, A Nalar, O Camara, AA Young, VY Wang, M Nash
Comparison of 2D Echocardiography and Cardiac Cine MRI in the Assessment of Regional Left Ventricular Wall Thickness
9:52-10:05 M Di Folco, P Clarysse, P Moceri, N Duchateau​
Learning interactions between cardiac shape and deformation: application to pulmonary hypertension
10:05-10:17 X Morales, J Mill, KA Juhl, A Olivares, G Jimenez-Perez, RR Paulsen, O Camara
Deep Learning Surrogate of Computational Fluid Dynamics for Thrombus Formation Risk in the Left Atrial Appendage
10:17-10:30 J Krebs, T Mansi, N Ayache, H Delingette
Probabilistic Motion Modeling from Medical Image Sequences: Application to Cardiac Cine-MRI
10:30-10:45 Coffee break
10:45-12:00 CRT-EPIGGY19 Challenge
10:45-11:00 O Camara
Best (and worst) practices for organizing a challenge on cardiac biophysical models during AI summer: the CRT-EPiggy19 challenge
11:00-11:10 ​Cedilnik, M Sermesant
Electrophysiological Model Personalisation to Porcine in-vivo Data for Paced Activation Prediction
11:10-11:20 KA Mountris, E Pueyo​
Evaluation of meshless methods for cardiac electrophysiological simulations based on porcine experimental data
11:20-11:30 C Albors, E Lluch, JM, R Doste, O Camara, M De Craene, H Morales​
Prediction of electrical activation patterns after cardiac resynchronization therapy in porcine hearts with meshless models
11:30-11:40 JF Gomez, B Trenor, R Sebastian
Prediction of CRT activation sequence by personalization of biventricular model from electroanatomical maps
11:40-11:50 S Khamzin, A Dokuchaev, O Solovyova
Optimization of CRT therapy device based on personalized computer model
11:50-12:00 Challenge wrap-up
12:00-12:36 Regular poster teaser (2 min for each poster)
12:36-14:00 Lunch, poster presentation, scoring

List of all poster presentations

14:00-15:15 LV Full Quantification Challenge
14:00-14:20 Challenge data and description from the organizers
14:20:14:30 N Gessert, A Schlaefer
Left Ventricle Quantification Using Direct Regression with Segmentation Regularization and Ensembles of Pretrained 2D and 3D CNNs
14:30-14:40 JC Acero, H Xu, E Zacur, J Schneider, P Lamata, A Bueno-Orovio, V Grau​
Left Ventricle Quantification with Cardiac MRI : Deep Learning Meets Statistical Models of Deformation
14:40-14:50 S Tilborghs, F Maes​​
Left Ventricular Parameter Regression From Deep Feature Maps of a Jointly Trained Segmentation CNN
14:50-15:00 Z Zhao, N Boutry, E Puybareau, T Géraud
A Two-Stages Temporal-Like Fully Convolutional Network Framework for Left Ventricle Segmentation
15:00-15:15 Challenge wrap-up
15:15-15:30 Coffee break
15:30-17:00 Multi-Sequence Cardiac MR Segmentation Challenge
15:30-15:40 Challenge introduction
15:40-15:53 C Chen, C Ouyang, G Tarroni, J Schlemper, H Qiu, W Bai, D Rueckert​
Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation
15:53-16:06 VM Campello, C Martin-Isla, CI Morcillo, MAG Ballester, K Lekadir​
Combining Multi-Sequence and Synthetic Images for Improved Segmentation of Late Enhanced Cardiac MRI
16:06-16:19 J Wang, H Huang, C Chen, W Ma, Y Huang, X Ding​
Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network
16:19-16:32 X Wang, S Yang, M Tang, Y Wei, X Han, L He, J Zhang​
SK-Unet: an Improved U-net Model with Selective Kernel for the Segmentation of Multi-sequence Cardiac MR
16:32-16:45 S Vesal, N Ravikumar, A Maier​
Automated Multi-sequence Cardiac MRI Segmentation Using Domain Adaptation
16:45-16:58 H Roth, W Zhu, D Yang, Z Xu, D Xu​
Cardiac Segmentation of LGE MRI with Noisy Labels
17:00-17:15 Closing and awards