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, and what is required for realizing deep learning-based personalized radiotherapy.
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 and Bias in Data Mining in Radiotherapy
Speaker: Dr. Marianne Aznar
July 2nd (Sat): Fairness and Bias in Medical AI: Deep Learning / Image Analysis Techniques in PET / MR Imaging and its Challenges
Speaker: Dr. Udunna Anazodo
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); Dr. Matthijs Kruis (Philips)
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): Using self-supervised and weakly supervised methods to make the most of limited annotated data
Speaker: Dr. Anne Martel
Obtaining large datasets with detailed annotations for medical imaging AI projects is a time consuming and expensive process as it usually requires the input of expert radiologists and pathologists. Collecting data to train outcome prediction models is even more challenging as the number of patients with both imaging and follow up data may be small, and only weak labels are available. This talk will describe several semi-supervised and self-supervised approaches which can make more efficient use of small, weakly labelled datasets. The focus will be on digital pathology but the methods described are applicable any medical imaging modality.
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): An Introduction to Radiomics and its Application for Outcome Prediction in Lung Cancer
Speaker: Dr. Sarah Mattonen
In this presentation Dr. Mattonen will introduce the concept of radiomics and describe the overall workflow. She will outline the different types of radiomic features and walk through an example of how radiomic features are calculated. Best practices for conducting radiomic studies will also be discussed as well as some of the available open-source tools for performing radiomic studies. She will end by describing some of the work her lab is doing on applying radiomics to multi-modal imaging for outcome prediction in lung cancer.
July 30th (Sat): Case-Based Repeatability of AI Classification on Multi-Modality Imaging of Breast Lesions Using DCE-MRI and FFDM
Speaker: Dr. Heather M. Whitney
Characterization of case-based repeatability can complement AI performance metrics. We investigated case-based repeatability of classification of breast lesions as malignant or benign using multi-modality human-engineered radiomic features extracted from both dynamic contrast-enhanced magnetic resonance (DCE-MR) and full field digital mammography (FFDM) images using a database of 78 lesions. Twenty-eight DCE-MR features describing shape, morphology, texture, and kinetics of contrast enhancement and 32 FFDM features describing size, shape, margin, and texture were extracted after the lesions had been segmented using previously established methods. FFDM features for each lesion were averaged across all views available. Case-based repeatability was investigated for three scenarios: (1) DCE-MR features alone, (2) FFDM features alone, and (3) all features (i.e., multi-modality). The case-based repeatability profile for each scenario was developed by separating features into training and test folds by case using a 0.632 bootstrap with 200 iterations. A random forest classifier from each training fold was applied to each test fold, resulting in the posterior probability of malignancy for each case, called the case-based output (CBO). The CBO was scaled to 50% prevalence. The median CBO and the width of its 95% CI (95CICBO) were determined for each case across bootstrap folds. 95CICBO was also reviewed for each pairwise comparison of features used for classification, assessed using the coefficient of determination. Using multi-modality features somewhat modified the case-based repeatability profile for the lesions. It also increased the repeatability of some cases but decreased it for others. The 95CICBO of individual cases demonstrated little correlation between modalities. Classification of breast lesions using multi-modality human-engineered radiomic features may change case-based repeatability.
Information regarding MIDRC, the Medical Imaging and Data Resource Center, will also be presented.
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