SASHIMI2018: Simulation and Synthesis in Medical Imaging

SASHIMI2018 short a
9:30 – 9:35 Opening remarks
9:35 – 11:05 Oral Session
9:35 – 9:50 Model-Based Generation of Synthetic 3D Time-Lapse Sequences of Multiple Mutually Interacting Motile Cells with Filopodia Igor Peterlik, David Svoboda, Vladimir Ulman, Dmitry Sorokin, Martin Maška
9:50 – 10:05 Deep Harmonization of Inconsistent MR Data for Consistent Volume Segmentation Blake Dewey, Can Zhao, Aaron Carass, Jiwon Oh, Peter Calabresi, Peter van Zijl, Jerry Prince
10:05 – 10:20 Deep Boosted Regression for MR to CT Synthesis Kerstin Klaser, Pawel Markiewicz, Marta Bianca Maria Ranzini, Wenqi Li, Marc Modat, Brian Hutton, David Atkinson, Kris Thielemans, Jorge Cardoso, Sebastien Ourselin
10:20 – 10:35 Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networks Chengjia Wang, Gillian Macnaught, Georgios Papanastasiou, Tom MacGillivray, David Newby
10:35 – 10:50 Generating Magnetic Resonance Spectroscopy Imaging Data of Brain Tumours from Linear, Non-Linear and Deep Learning Models Nathan Olliverre, Guang Yang, Greg Slabaugh, Constantino Carlos Reyes-Aldasoro, Eduardo Alonso
10:50 – 11:05 RS-Net: Regression-Segmentation 3D CNN for Synthesis of Full Resolution Missing Brain MRI in the Presence of Tumours Raghav Mehta, Tal Arbel
11:05 – 11:15 Break
11:15 – 12:00 Poster Session  
A machine learning approach to diffusion MRI partial volume estimation Emmanuel Vallee, Wenchuan Wu, Francesca Galassi, Saad Jbabdi, Stephen Smith
Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data size Yuta Hiasa, Yoshito Otake, Masaki Takao, Takumi Matsuoka, Kazuma Takashima, Aaron Carass, Jerry Prince, Nobuhiko Sugano, Yoshinobu Sato
Data augmentation using synthetic lesions improves machine learning detection of microbleeds from MRI Saba Momeni, Amir Fazllolahi, Pierrick Bourgeat, Parnesh Raniga, Paul Yates, Nawaff Yassi, Desmond Patricia, Yongsheng Gao, Jurgen Fripp, Olivier Salvado
Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks Hoo Chang Shin, Neil Tenenholtz, Jameson Rogers, Christopher Schwarz, Matthew Senjem, Jeffrey Gunter, Katherine Andriole, Mark Michalski
Lung Nodule Synthesis Using CNN-based Latent Data Representation Dario Oliveira, Matheus Viana
Tubular Network Formation Process Using 3D Cellular Potts Model David Svoboda, Tereza Nečasová, Lenka Tesařová, Pavel Šimara
Deep Learning based Coronary Artery Motion Artifact Compensation using Style-Transfer Synthesis in CT Images Sunghee Jung, Soochahn Lee, Byunghwan Jeon, Yeonggul Jang, Hyuk-Jae Chang
MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer’s Classification Apoorva Sikka, Skand Vishwanath Peri, Deepti R Bathula
12:00 – 13:00 Keynote Talk The U-net does its job – so what next? Olaf Ronneberger
13:00 – 13:20 Panel discussion
13:20 – 13:30 Closing remarks

Note: Tentative schedule as of September 2018.

 

Guidelines for presentations

The guidelines for SASHIMI 2018 presentations mostly follow the guidelines for MICCAI presentations.

Oral presentations

Each oral presentation is allocated a 15 minute slot: talks must not exceed 12 minutes, leaving 2-3 minutes for questions.

Presenters will be able to use their own laptop or use the laptop provided (bring your own USB stick and arrive early). Please prepare your slides in 16:9 ratio aspect.

Poster presentations

The maximum poster size is 95cm x 175cm (width x height). Note this is portrait format.

Organization committee

image
University of Sheffield, UK
image
ETH Zurich, Switzerland
image
University of Pennsylvania, USA
image
Inria Paris, France