Learn medical image analysis and deep learning in Python
June 11th – August 6th, 2022
days
hours minutes seconds
until
Week 3 Workshop: Deep learning framework (Pytorch): Tensors and Autograd
McMedHacks is back!
McMedHacks is an 8-week-long program that aims to teach students and researchers fundamentals of medical image analysis and deep learning in Python. It consists of a series of in-depth workshop demos with Google Colab and seminar series given by leaders in the field. McMedHacks is a program organized by the EngerLab at McGill Medical Physics Unit and the Lady Davis Institute. EngerLab is a part of McGill Centre for Translational Research in Cancer as well as the Cancer Research Network. Last year’s participants can be found here! See Program from 2021 here!
NEW to this year’s edition:
- Three (prep) weeks prior to June 11th on Intro to Python Programming for Python beginners (See McMedHacks 2022 Program below).
- In-depth introduction in popular deep learning framework PyTorch.
- Step-by-step introduction from classical machine learning to traditional deep learning to advanced techniques and their applications in medical image analysis.
- EXTRA sessions during weekdays on top of regular sessions on the weekend on special techniques.
Learning Objectives:
- Familiarity with Fundamentals of image analysis
- Familiarity with Fundamentals of machine learning
- Introducing a deep learning framework (Pytorch)
- Introducing Fully supervised medical image segmentation
- Introducing Concepts in weakly and self-supervised learning
- Radiomics and Treatment Outcome Prediction
McMedHacks 2022 Statistics
McMedHacks 2022 attracted 1000+ registrations from 62 countries!
With levels of educations:
From fields of studies and domains
They heard about McMedHacks through
McMedHacks 2022 Program
(10:30 AM – 12:30 PM Eastern Daylight Time of the following dates)
Prep Weeks: Intro to Python Programming (Optional)
May 16th (Mon): Introduction to Python
Instructor: Dr. Farhad Maleki
May 23rd (Mon): Object-oriented programming with Python
Instructor: Hunter Buckhorn
June 6th (Mon): Scientific programming with Python
Instructor: Saman Rahbar
Week 1: Introduction to Classical Machine Learning
June 11th (Sat): Opening Ceremony
Speakers: Dr. Shirin Abbasinejad Enger and Dr. Gerald Batist
Workshops
June 12th (Sun): Introduction to Classical Machine Learning
Instructor: Dr. Najeeb Khan
June 15th (Wed): Classical Machine Learning: A Case Study XGBoost
Instructor: Dr. Zahra Azizi
June 17th (Fri): Introduction to Image Processing: Image IO and Image Transformations
Instructors: Sébastien Quetin and Yujing Zou
Week 2: Fundamentals of Image (Pre-)Processing
Seminars
June 18th (Sat): Deep Learning Model Generalizability & Clinical Translation from an Academic Researcher’s Perspective
Speaker: Dr. Julien Cohen-Adad
How does pre-processing of medical images affect the model generalizability, especially for training multi-modal medical imaging tasks?
June 18th (Sat): Image-guided brachytherapy
Speaker: Dr. Marjory Jolicoeur
Workshops
June 19th (Sun): Fundamentals of Image (Pre-)Processing: Quality Assurance Prior to Deep Learning Model Training
Instructor: Kiri Stern
Week 3: Deep Learning Fundamentals
Seminars
June 25th (Sat): Using prediction models in clinical practice:
Introduction of an NTCP-model based selection approach for proton therapy in esophageal cancer
Speaker: Dr. Maaike Berbee
To date prediction models are slowly finding their way into clinical practice. They are for example being used to facilitate shared decision making and, in the Netherlands, to selectively offer proton therapy to those patients who are expected to benefit from proton therapy. In this talk I will show how we validated a model to predict 2-year mortality in order to implement a model-based selection approach for proton therapy in esophageal cancer patients. Besides going through this example we will discuss the questions “Why do we need models of treatment effects in medicine” and “How to get models into wide use in the clinic”.
June 25th (Sat): Deep learning for radiotherapy outcome prediction using dose data
Speaker: Dr. Ane Appelt
Modern radiotherapy uses complex dose planning software to estimate and optimise the radiation dose delivered to the individual patient, based on 3D anatomical imaging. Consequently, we have detailed 3D data on the distribution of radiation dose to different parts of the body for every patient treated for radiotherapy – and, if we can predict who will get tumour control and/or toxicity, we can adjust this dose distribution to achieve the optimal ratio between the two. However, most traditional methods for outcome prediction only use very reduced data representations as input to the prediction models (e.g. ‘mean dose to an organ’), not the full 3D data. I’ll describe how we might apply CNN-based methods for classification to the problem of identifying ‘toxic’ radiation dose distributions; treating the dose information as just another type of image. But I’ll also discuss some of the pitfalls of this approach, and the large – and still unsolved – step of feeding the model output back into the radiotherapy treatment planning process.
Workshops
June 26th (Sun): Deep Learning Fundamentals
Instructor: Hunter Buckhorn
June 29th (Wed): Deep Learning Framework (PyTorch): Tensors and Autograd
Instructors: Sébastien Quetin and Yujing Zou
Week 4: Deep Learning Framework (PyTorch): Model Training and Evaluation
Seminars
July 2nd (Sat): Fairness & Bias in Data mining in radiotherapy
Speaker: Dr. Marianne Aznar
July 2nd (Sat): Fairness & Bias in Medical AI: Deep Learning / Image Analysis Techniques in PET / MR Imaging and its Challenges
Speaker: Dr. Udunna Anazoddu
Workshops
July 3rd (Sun): Deep Learning Framework (PyTorch): Model Training and Evaluation
Instructor: Dr. Mohammad Reza Mehebbian
July 6th (Wed): Deep Learning Framework (PyTorch): Implement your own Image Classifier
Instructor: Dr. Mohammad Reza Mehebbian
Week 5: Fully Supervised Medical Image Segmentation
Seminars
July 16th (Sat): Implementation of Deep Learning Software from an Industry Perspective
Speakers: Dr. Karl Otto, Dr. Joshua Giambattista, Carter Kolbeck and Jon Giambattista (Limbus AI)
July 16th (Sat): Implementation of Deep Learning Software from a Regulatory Perspective
Speaker: Dr. Andreu Badal
What is the FDA approval process when deciding whether or not to commercialize a research product?
Workshops
July 17th (Sun): Fully Supervised Medical Image Segmentation
Instructor: Hunter Buckhorn
July 20th (Wed): Deep Learning Framework (PyTorch): Tensorboard
Instructors: Sébastien Quetin and Yujing Zou
Week 6: Deep Learning Framework (PyTorch): Implement U-Net
Seminars
July 23rd (Sat): Decreasing Annotation Labour for Digital Pathology Segmentation and Downstream Outcome Prediction Models
Speaker: Dr. Anne Martel
Bottlenecks in digital pathology whole-slide-image (WSI) deep learning models and weakly supervised learning techniques, biomarkers extracted from WSI used in clinical decision support system.
July 23rd (Sat): Instance Segmentation on Colonoscopy Images
Speaker: To be confirmed
Workshops
July 24th (Sun): Deep Learning Framework (PyTorch): Implement U-Net
Instructor: Dr. Mohammad Reza Mehebbian
July 27th (Wed): Deep Learning Model Generalizability: Pitfalls and Best Practices
Instructor: Dr. Katie Ovens
Week 7: Supervised, Weakly Supervised, Semi-Supervised, and Unsupervised Learning
Seminars
July 30th (Sat): Clinical Decision Support Systems: Distributed Learning for Radiomics and Outcome Prediction
Speaker: To be confirmed
Creating generalizable models while keeping patient privacy in mind. Multi-institutional studies using Federated Learning. An introduction to the precision-medicine-toolbox. What to do with small datasets across institutions?
July 30th (Sat): Clinical Decision Support Systems: Use of Multimodality Imaging in AI and Outcome Prediction
Speaker: To be confirmed
State-of-the-art models based on multimodality images, generalizable ground-truths in segmentations, and fusion methods among multiple medical imaging modalities.
Workshops
July 31st (Sun): Weakly Supervised, Semi-Supervised, and Unsupervised Learning
Instructors: Dr. Farhad Maleki and Hossein Jafarzadeh
August 3rd (Wed): Radiomics and Treatment Outcome Prediction
Instructor: Dr. Ibrahim Chamseddine
Week 8: Closing ceremony
August 6th (Sat): Closing Ceremony
Speakers: Dr. Sylvain Baillet and Dr. Shirin Abbasinejad Enger
Our 2021 McMedHacks Workshop Participants
In its first edition in 2021, McMedHacks gained 356 registrations from participants of 38 different countries from undergraduates, to PhDs and MDs. A vast number of disciplines and professions were represented, dominated by medical physics students, academic, and clinical medical physicists. The program received high participant feedback average scores of 4.768, 4.478, 4.579, 4.292, 4.84 out of five for the qualities of presentation, workshop session, tutorial and mentor, assignments, and course delivery, respectively.
with various levels of education
from 38+ countries
Our Sponsors
Sponsor us!
This workshop series and hackathon would not be possible without the generous support of our sponsors. Thank you!!