We’re excited to announce our sixth WiMLDS Montreal meetup! Whether you’re a data professional or simply curious, you are welcome regardless of your technical level or your gender. The talks will be entirely in English. Our meetup will be online in order to keep everybody safe.

A Zoom link will be provided prior to the meetup. We are limited to 100 participants on Zoom. So it will be based on a "first-come, first-served" basis at the time of the event.

=========
Agenda

5:45 pm — Zoom opens

6:00 pm — Barbara Decelle, Health Research Advisor @ IVADO
"Digital Health: Challenges and Opportunities"

6:20 pm — Christine Bakhous, Image Analysis Engineer @ EOS imaging
"Vertebra Pedicles Detection Using CNN in a 3D Spine Reconstruction From Biplanar Radiographs"
The 3D analysis of the scoliotic spine has a high potential in its clinical diagnosis and treatment. In a biplanar radiographs context, a 3D analysis requires a 3D reconstruction from a pair of 2D X-rays. Whether being fully-/semiautomatic or manual, this task is complex because of the noise, the structure superimposition and partial information due to a limited number of projections. The machine learning domain offers powerful and automatic tools for image analysis and structures extraction. In this context, a fully automatic 3D spine reconstruction method was proposed by Aubert et al. in 2017 where the Vertebral Body Centers (VBCs) are automatically detected using Convolutional Neural Network (CNN) and then used to regularize a set of geometrical parameters in a Statistical Shape Model (SSM) framework. In this global process, pedicles are inferred statistically during the SSM regularization. As an extension to the previous work, our research focused on the addition of a CNN-based regression model for pedicle detection allowing a better pedicle localization and improving the clinical parameters estimation (e.g. AVR, Cobb angle).

6:40 pm — Manon Ansart, Post-Doctoral Researcher @ ETS
"Automatic Prognosis in Alzheimer’s Disease: Current Methods and What’s Wrong With Them"
Patients suffering from mild cognitive impairment may or may not develop Alzheimer’s disease in the near future. Identifying those who will is crucial to adapt patient care and for clinical trial recruitment. We performed a systematic review of articles making this automatic prediction using machine learning methods. We read 172 articles, from which we extracted 234 experiments. I will first describe the current landscape of the field including the algorithms and features used for automatic prediction. I will then present a statistical analysis of which methodological choices lead to better performance. Finally, we will take a step back and look at methodological issues that are common in the field, where they come from, and what needs to be done to prevent them.

=========
Sharing

During the event, you can share content using #WiMLDSMontreal & @WiMLDS_Montreal

After the meet-up, all the slides will be available on our Medium page : https://medium.com/@WiMLDS_Montreal

---
Online meetup information :

WiMLDS is strongly inviting you to read our guidelines about organizing pleasant and successful online meetups : https://github.com/WiMLDS/online-meetups

---
Code of Conduct

WiMLDS is dedicated to providing a harassment-free experience for everyone. We do not tolerate harassment of participants in any form. All communication should be appropriate for a professional audience including people of many different backgrounds. Sexual language and imagery is not appropriate.

Be kind to others. Do not insult or put down others. Behave professionally. Remember that harassment and sexist, racist, or exclusionary jokes are not appropriate.

Thank you for helping make this a welcoming, friendly community for all. All attendees should read the full Code of Conduct before participating: https://github.com/WiMLDS/starter-kit/wiki/Code-of-conduct