3rd Swiss Medical Image Computing Day 2018

The Swiss Medical Image Computing Day brings together Swiss researchers working on topics related to medical image computing.

When and Where

The workshop will take place on April 25th, 2018 in the University of Bern, Hauptgebäude (Hochschulstrasse 4, Bern), Kuppelraum (top floor).


The workshop is free but registration to the event is mandatory. Please register here.


10:00 - 10:10
Raphael Sznitman
Welcome to the SMICD 2018
10:10 - 10:35
Tarun Anjali Bagumu (UNIGE/EPFL)
Extrapolating functional MRI data into the white matter via structurally-informed graph diffusion -Tarun.pdf (PDF, 6.2 MB)
10:35 - 11:00
Fabian Balsiger (UNIBE)
Magnetic Resonance Fingerprinting Reconstruction via Spatiotemporal Deep Learning
11:00 - 11:30
Coffee break
11:30 - 11:55
Roger Bermudez (EPFL) Getting the most out of your annotations with Transfer Learning - Bermudez.pdf (PDF, 4.0 MB)
11:55 - 12:20
Laurent Lejeune (UNIBE)
Video and volume ground truth annotation with sparse point supervision - Lejeune.pdf (PDF, 3.2 MB)
12:20 - 12:45
Neerav Karani (ETHZ)
Temporal Interpolation of Abdominal MRIs using CNNs
12:45 - 14:15
Lunch break


14:15 - 14:40
Jonathan Patiño (EPFL) White matter modelling with Diffusion MRI: From mesoscopic information to microstructure estimation
14:40 - 15:05
Guodong Zeng (UNIBE) Focused Semantic Segmentation of Medical Images via Deep Learning - Zeng.pdf (PDF, 6.5 MB)

15:05 - 15:30

Fabien Péan (ETHZ)

Musculoskeletal Modeling and Simulation of the Human Shoulder

15:30 - 16:00

Coffee break


16:00 - 17:00

Using Computer Vision for Computer-Aided Surgery by Augmenting Laparoscopy with Preoperative Image Data - slides (PDF, 6.2 MB)


Title: Using Computer Vision for Computer-Aided Surgery by Augmenting Laparoscopy with Preoperative Image Data

Abstract: Laparoscopy has many advantages but does not allow the surgeon to see through the organs and tissues nor to palpate them. Therefore, finding internal structures such as tumours may be extremely difficult. Augmented reality is an appealing idea to alleviate this problem but carries unresolved scientific and technical challenges. I will present our approach to these challenges and preliminary results. Our setup is simple monocular laparoscopy with no additional hardware. We use the preoperative MR or CT scan to augment the laparoscopy video by creating some sort of virtual transparency. The leading scientific challenge is preoperative 3D model to laparoscopy video registration. Our approach combines landmarks and visual cues. It works for simple cases but the general case is still largely open and in my opinion requires novel theoretical and practical computer vision results.

Biography: Adrien Bartoli has been a full Professor of Computer Science at Université Clermont Auvergne since fall 2009, with an upgrade to first-class in fall 2016, and a member of Institut Universitaire de France (2016-2021). He is currently leading the ENCOV (Endoscopy and Computer Vision) research group jointly with Michel Canis. He is holding an ERC Consolidator Grant (2013-2017). Previously, he was a permanent CNRS research scientist at Institut Pascal since fall 2004 where he led ComSee, the Computer Vision research group, jointly with Thierry Chateau. He was a Visiting Professor in DIKU at the University of Copenhagen between 2006-2009 and a postdoctoral researcher in the Visual Geometry Group at the University of Oxford under Andrew Zisserman in 2004. Adrien Bartoli obtained his Habilitation Degree (HDR) from Université Blaise Pascal in June 2008. He completed his PhD in the Perception group at INRIA Grenoble under Peter Sturm and Radu Horaud. Adrien Bartoli has received several awards including the 2004 Grenoble-INP PhD thesis prize, the 2007 best student paper award at CORESA, the 2008 CNRS médaille de bronze, the 2012 audience award at IPCAI, the 2015 second best paper award at CARE-MICCAI and the 2016 research prize from Université d'Auvergne. He received an outstanding reviewer award at ECCV'08, CVPR'10 and CVPR'15. Adrien Bartoli's main research interests include image registration and Shape-from-X for rigid and non-rigid scenarios, and machine learning within the field of theoretical and medical Computer Vision.

Previous events

1st Swiss Medical Image Computing Day

2nd Swiss Medical Image Computing Day



This scientific meeting is in part funded by the University of Bern.

Contact Raphael Sznitman for any questions.