PyData Montreal Meetup #12

** Join our chat focused on DS&ML topics: http://bit.ly/ds-ml-chat **

PyData Montreal meetup #12:

• "Connecting physics and deep learning to generalize medical image analysis tasks" by Julien Cohen-Adad
• "Predicting complex ideas in Python using collaborative modelling" by Eleonore Fournier-Tombs

----------------------------------------------------------------------------------------------------
Agenda
6:00 pm—Doors open

6:20 pm—Connecting physics and deep learning to generalize medical image analysis tasks

Abstract:
Magnetic Resonance Imaging (MRI) can have multiple flavours: T1, T2, proton density, fMRI, diffusion MRI, etc. These so-called "Quantitative MRI" techniques are useful for monitoring pathologies such as multiple sclerosis and Alzheimer's disease. However, quantitative MRI data require complex analysis pipelines that are often executed manually and hence suffer from poor reproducibility. Deep learning (DL) appears to be an ideal candidate to help automatize certain analysis tasks.
Unfortunately, while dozens of DL papers applied to medical imaging are published every year, most methods have been validated in well-curated single-center datasets only. In the rare case where the code is publicly available, the algorithm usually fails when applied to other centers (a.k.a. Real life data!).
This happens because images across different centers have slightly different features than those used to train the algorithm (contrast, resolution, etc.), combined with the fact that low amount of data and manual labels are available. Recent DL techniques such as domain adaptation have tackled this issue. However, these techniques are not well adapted to our situation because in MRI, image features not only varies between centers, but also across a large number of acquisition parameters (e.g., repetition time, flip angle).
The purpose of this presentation is to sensitize the DL community to unmet needs in MRI analysis, and explore possible ways to leverage MRI physics to advance impactful DL applications in the medical domain.

About Julien:
Dr. Cohen-Adad is an Associate Professor at Polytechnique Montreal, Adjunct Professor in the Department of Neurosciences at University of Montreal, Associate Director of the Neuroimaging Functional Unit at the University of Montreal, and Canada Research Chair in Quantitative Magnetic Resonance Imaging. His research focuses on advancing quantitative methods with MRI for characterizing pathologies in the central nervous system. More info at: https://www.neuro.polymtl.ca/.

7:00 pm — Break

7:20 pm —"Predicting complex ideas in Python using collaborative modelling"

Abstract:
In this talk, Eleonore will present the process of predicting complex ideas using collaborative, user-centred modelling. She will talk about the path that led to the development of DelibAnalysis, an open-source Python package that is currently used by political science researchers in 6 different countries. This will include using a phased approach to involve non-technical users in model training, lowering the barrier of entry to machine learning and Python, developing data sharing agreements in order to obtain training datasets, and more.

About Eleonore:
Eleonore is a founder and lead data scientist at Bolero AI. She has a PhD in computational social science, and has worked as a data scientist in finance, international development and humanitarian aid. She is currently working on predictive financing for humanitarian crises at the United Nations, and is also leading the DelibAnalysis project, which measures the democratic quality of political debates.

8:00 pm — Break and networking
8:30 pm — Drinks & social hour at Baton Rouge https://goo.gl/maps/nEAe5SaMk5CTD2zj7