2024 Summer school on deep learning for medical imaging, 5th Edition
Welcome to the 2024 summer school on deep learning for medical imaging!
This school is intended for medical imaging beginners and experts (students, post-docs, research professionals, and professors) who are eager to discover the fundamentals of deep learning and how it translates to medical imaging. We will walk you through the basics of machine learning all the way to the latest deep learning breakthroughs applied to medical imaging. As shown in the planning, the school has both oral presentations (15 hours) and 4 hands-on sessions of 3 hours each. During the hands-on sessions, the participants will be guided through the dos and don'ts of machine learning programs for medical imaging. Please see the program for more details.
Should you be a machine learning / deep learning expert to attend the school? NO! That is the point of this school!
Should you be a programming expert to attend the hands-on session? NO! Only basic skills in Python programming are required.
We have enough room to accommodate 70 on-site participants. So do not wait and register!
Since we anticipate that more than 70 people will register to our summer school, we will grant the possibility for people to virtually attend the school in an asynchronous manner. These virtual participants will not be permitted on-site participation but will have access to the recorded videos as well as the hands-on session material towards the end of the school.
Please note that this school has been labeled by the MICCAI Society and the French National Scientific Research Counsil (MaDICS research group).
We would also like to thank our sponsors for their generous contributions.
NOTE : THE 2025 EDITION OF THE DLMI SCHOOL WILL BE HELD IN LYON, FRANCE
Important Dates
· January 15, 2024: Registration opening
· May 24, 2024: Registration deadline
· June 15, 2024: Registration cancellation deadline (visa issues)
· July 8-12, 2024: Summer school
· July 6, 2024: Evening event
Rates
365CAN$ for students
465CAN$ for non-students
115CAN$ for virtual asynchronous participation
Inclusions
For the on-site participants, fees include 5 days of classes and hands-on sessions, coffee breaks, lunches, welcome cocktail and evening event at the museum. Please note that those fees do NOT include hotel.
Cancellation policy
NO REFUND POLICY: Please note that we shall provide NO REFUND under any circumstances outside visa problems. We are aware that getting a visiting visa can be difficult for some. For that reason, we shall allow a refund (with a transaction fee of 20 CAN$ - courtesy of the international banking system) before June 15, 2024 for those experiencing a visa problem. NO REFUND will be allowed after that date however. If you need an invitation letter, please contact jose.dolz@etsmtl.ca.
Click here for the videos of the oral presentations + the code and video tutorials for the hands on sessions. The password has been sent to you by e-mail.
Monday July 8th
8h00 - 9h00 Registration and Breakfast
9h00 - 9h15 Welcome talk
9h15 - 10h30 Basics of deep learning Part 1 (P-M Jodoin)
Perceptron and multi-layer perceptron, stochastic gradient descent, learning rate, logistic regression, activation function, regularization (L1/L2/dropout/early stopping), etc.
10h30 - 10h45 Coffee Break
10h45 - 12h00 Basics of deep learning Part 2 (P-M Jodoin)
Perceptron and multi-layer perceptron, stochastic gradient descent, learning rate, logistic regression, activation function, regularization (L1/L2/dropout/early stopping), etc.
12h00 - 13h30 Lunch at the ETS
13h30 - 15h00 Basics of deep learning Part 3 (C. Desrosiers)
Weights initialization, forward and backward propagation, batch size, convolution neural nets (CNN), feature maps, pooling, pretraining and transfer learning, applications
15h00 - 15h30 Coffee break
15h30 - 17h00 Convolutional neural networks (M. Sdika)
Common CNN architectures for classification (VGGNet, ResNet, ...) and localization (FasterRCNN, Yolo) and segmentation (encoder-Decoder, U-Net, ENet, ...)
17h30 - 19h30 Cocktail at the ETS
Tuesday, July 9
8h30 - 9h00 Breakfast
9h00 - 10h30 Generative and adversarial methods for medical imaging (M-H Shateri)
GANs, autoencoders, VAE and their application to medical imaging.
10h30 - 11h00 Coffee Break
11h00 - 12h30 Advanced concepts in deep learning Part 1 (N. Thome)
RNN, Attention, Transformers, ViT, etc.
12h30 - 14h00 Lunch at the ETS
15h00 - 15h30 Coffee break
14h00 - 16h30 Hands-on session 1: Introduction
Classification from machine learning to deep learning
16h30 - 18h00 Poster session
Wednesday, July 10
8h30 - 9h00 Breakfast
9h00 - 10h30 Uncertainty and explainability (M. Sdika)
Quality, uncertainty, calibration, explainability.
10h30 - 11h00 Coffee Break
11h00 - 12h30 Typical medical imaging issues (M. Havaei)
Domain adaptation, privacy protection and federated learning, adversarial learning, common pitfalls, incomplete data, etc.
12h30 - 14h00 Lunch at the ETS
14h00 - 17h00 Hands-on session 2: Segmentation using deep learning
18:00 Social event (Aura)
Thursday, July 11
8h30 - 9h00 Breakfast
9h00 - 10h30 Weakly supervised deep learning (J.Dolz + C. Desrosiers)
Weakly supervised segmentation, constrained CNN losses, semantic segmentation, semi-supervised learning
10h30 - 11h00 Coffee Break
11h00 - 12h30 Round table
What are the challenges for AI to break into clinic?
feat. Nicolas Thome, Sylvain Bouix, Hadi Chakor,
Laurent Létourneau-Guillon
12h30 - 14h00 Lunch at the ETS
14h00 - 17h00 Hands-on session 3: Variational Autoencoders
Auto-encoders, convolutional auto-encoders, variational auto-encoders, latent spaces
18h00 - 21h30 Banquet dinner
Friday, July 12
8h30 - 9h00 Breakfast
9h00 - 10h30 Advanced concepts in deep learning Part 2 (J. Dolz)
foundation models, language-image pre-training, parameter efficient fine-tuning, prompt learning
10h30 - 11h00 Coffee Break
11h00 - 12h30 MONAI : open-source, community-supported framework for Deep learning in healthcare imaging (E. Kerfoot)
Framework, Data Transformation, Common Network Definitions, Training Workflows, Tutorials, Model Zoo
12h30 - 12h45 Closing remarks
12h45 - 14h00 Lunch at the ETS
14h00 - 17h00 Hands-on session 4: Foundation models
Those participating to the onsite event need to bring a laptop computer with a working WIFI connection. The hands on sessions will be held on the saturncloud.io online environment. So no need of a fancy hardware nor a specific operating system. And... oh yes! bring a happy face, it will be fun!
We're thrilled to organize the 5th edition of our summer school. This summer school is aimed at both novice and more experienced researchers in medical imaging who wish to deepen their knowledge in machine learning and its application to various problems in this field. As before, the school will accommodate for on-site and virtual participation.
The school consist of talks, poster sessions, networking sessions, a round table discussion and 4 hands on sessions.
Sponsorship Tiers
Gold $3000+
* Acknowledgements during introductory talk.
* T-Shirts of the summer school
* Opportunity for an oral presentation from a member of the sponsor organization
* Logo on the conference's splash screen
* Logo on the summer school website
Silver $1500
* Logo on the conference's splash screen
* Logo on the summer school website
Bonze $750
* Logo on the summer school website
How are we planning on spending the budget ?
The budget will be used for expenses related to the conference logistics. We are seeking financial support to contribute towards the stipends of students who are integral to the organization of our summer school, as well as to fund the GPU usage from the Saturn Cloud provider.
Unused budget
As for the previous editions of the summer school, any remaining budget will be rolled over to next year’s event.
The previous editions of the school on deep learning for medical imaging were held in 2019 at the Université de Lyon, France and online in 2021, then at the ETS in 2022 and back in Lyon in 2023. These schools were organized with the full logistic and financial support of the LabEx PRIMES and the CREATIS lab.
Organizing committee
· Pierre-Marc Jodoin (Université de Sherbrooke, Canada)
· Christian Desrosiers (École de technologie supérieure, Canada)
· Jose Dolz (École de technologie supérieure, Canada)
· Thomas Grenier (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Michaël Sdika (Université de Lyon, CREATIS, LabEx PRIMES, France)
Scientific committee (alphabetic order)
· Olivier Bernard (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Christian Desrosiers (École de technologie supérieure, Canada)
· Jose Dolz (École de technologie supérieure, Canada)
· Nicolas Duchateau (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Rémi Émonet (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Thomas Grenier (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Pierre-Marc Jodoin (Université de Sherbrooke, Canada)
· Carole Lartizien (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Fabien Millioz (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Bruno Montcel (Université de Lyon, CREATIS, LabEx PRIMES, France)
· Emmanuel Roux (Université de Lyon, CREATIS, LabEx PRIMES, France)
Venue and Accommodation
Ecole de Technologie Supérieure
The summer school will be held in Pavillon A of the ETS (Ecole de Technologie Supérieure) of Montreal, located at the corner of Peel and Notre-Dame streets. The exact address is 1100 Notre-Dame St W, Montreal.
The auditorium room number is A-1600
Visa
Most people need a visitor's visa or an Electronic Travel Authorization (eTA) to travel to Canada - not both. Some people may only need their valid passport. List of visa-exempt countries. You can find out if you need a visa here.
For those who need a visa, more information can be found on the Canada immigration website. Also, please send us an email for a letter of invitation (required to apply for a visa).
NOTE : please bear in mind that applying for a Canadian Visa may take up to three months.
How to reach us
By metro
One easy way of reaching the ETS is through the subway. Hop into the nearest metro station to your hotel, go to the Lucien L'allier or Bonavanture stations on the orange line, and walk to the ETS (5 minute walk).
By bicycle
Where ever you are in Montreal, you can easily bike your way around through a large network of cycle paths. In fact, Montreal has been ranked the 18th most bicycle friendly city in the world according to the Copenhagen index. Don't have a bike? No problem, rent a bixi! With 700 bixi stations, you probably have one right next to your Hotel.
By car
You may drive to the ETS which has an underground parking lot. But beware! the parking can be full!
By bus
The bus lines 35, 36, 74 and 107 passes near the ETS. Click here for a bus map. You may also go on the Montreal transit society web site for more details.
The following hotels are nearby the venue:
Best Western Plus Montreal Downtown- Hotel Europa (Walking distance from ETS: 1.0 km)
Novotel Montreal Center (Walking distance from ETS: 1.0 km)
Montreal Marriott Chateau Champlain (Walking distance from ETS: 500 m)
Hotel Bonaventure Montreal (Walking distance from ETS: 500 m)
Hôtel Alt Montréal (Walking distance from ETS: 500 m)
Best Western Ville-Marie Hotel & Suites (Walking distance from ETS: 1.3 km)
A big thank you to all of our sponsors!
Gold : LabexPrime, Diagnose, CHUS
Silver: Université de Sherbrooke, Google, INSAVALOR
Bronze: SIMS
Speakers
Pierre-Marc Jodoin is from the University of Sherbrooke, Canada where he works as a full professor since 2007. He specializes in the development of novel techniques for machine learning and deep learning applied to computer vision and medical imaging. He mostly works in video analytics and brain and cardiac image analytics. He is the co-director of the Sherbrooke AI platform and co-founder of the medical imaging company called "Imeka.ca" which specializes in MRI brain image analytics. web site: http://info.usherbrooke.ca/pmjodoin/
Prof. Desrosiers obtained a Ph.D. in Applied Mathematics from Polytechnique Montreal in 2008, and was a postdoctoral researcher at the University of Minnesota with prof George Karypis. In 2009, he joined École de technologie supérieure (ÉTS) as professor in the Departement of Software and IT Engineering. He is codirector of the Laboratoire d’imagerie, de vision et d’intelligence artificielle (LIVIA) and a member of the REPARTI research network. He has over 100 publications in the fields of machine learning, image processing, computer vision and medical imaging, and has served on the scientific committee of several important conferences in these fields.
Jose Dolz is Associate Professor in the Department of Software and IT Engineering at the École de Technologie Supérieure (ETS) Montreal. Prior to be appointed Assistant Professor, he was a post-doctoral fellow at the ETS Montreal. Dr. Dolz obtained his B.Sc and M.Sc in the Polytechnic University of Valencia, Spain, and his Ph.D. at the University of Lille 2, France, in 2016. Dr. Dolz was recipient of a Marie-Curie FP7 Fellowship (2013-2016) to pursue his doctoral studies. His current research focuses on deep learning, medical imaging, optimization and learning strategies with limited supervision. He authored over 50 fully peer-reviewed papers, many of which published in the top venues in medical imaging (MedIA/TMI/MICCAI/IPMI), vision (CVPR) and learning (NeurIPS, ICML).
Michaël Sdika is a full member of the CREATIS lab in Lyon, France. His current research field focuses on the development of new analysis method based on deep learning for medical data. His main contributions are centered around image registration, atlas based segmentation, structure localization and machine learning for MR image of the nervous central system.
Dr. Thomas Grenier is Associate Professor at the University of Lyon Electrical Engineering department and at the CREATIS lab in Lyon, France.
His research focuses on longitudinal analysis of medical data to study evolution as Multiple Sclerosis lesions, functional activity (muscle and hydrocephaly). Most of these studies involve a segmentation task and dedicated pre and post processing steps. Clustering (spatio-temporal mean-shift), semi-supervised (multi-atlas with machine learning) or fully supervised (DNN) schemes are used to solve such problems considering their specific constraints.
Mohammadhadi Shateri (Member, IEEE) received the B.Sc. degree (with Hons.) in electrical engineering from the Amirkabir University of Technology, Tehran, Iran, in 2012, the M.Sc. degree (with Hons.) in electrical engineering from the University of Manitoba, Winnipeg, MB, Canada, in 2017, and the Ph.D. in electrical engineering from McGill University, Montreal, QC, Canada, in 2021. He is now a professor at the École de Technologie Supérieure (ETS). His research interests include machine learning, deep learning, and reinforcement learning with application to data analytics.
His research interests include machine learning and deep learning for understanding low-level signals, e.g. vision, time series, acoustics, etc. He also explores solutions for combining low-level and higher-level data for multi-modal data processing. His current application domains are essentially targeted towards healthcare, physics and autonomous vehicles.
He is involved in several French, European and international collaborative research projects on artificial intelligence and deep learning.
Mohammad Havaei is a Senior Research Scientist at Google. His research interest is focused on algorithmic fairness especially in the context of transfer learning. Mohammad's background is in the areas of computer vision, generative models and transfer learning. Before joining Google, he was a Research Scientist at Imagia where he focused on developing machine learning models applicable to medical image analysis.
Dr Eric Kerfoot is a Software Architect in Medical Engineering in the Department of Biomedical Engineering, School of Biomedical Engineering & Imaging Sciences.
Location
Ecole de technologie supérieure de Montréal
1111 Rue Notre-Dame Ouest
Montréal, Québec
Canada, H3C 1K3
Dates
Registration period:
January 15, 2024 - 9:00 PM EST - May 28, 2024 - 11:00 AM EDT
Contact us
If you have any questions, please contact pierre-marc.jodoin@usherbrooke.ca
