Machine Learning at the FNNDSC

How is Machine Learning being used at the FNNDSC?

The FNNDSC uses various Machine Learning (ML) approaches, in particular Neural Networks in a variety of research and development efforts.

 

Our focus is less on creating new Neural Network algorithms/architectures and more on using existing tools to aid research.  Specific focus areas include outcome prediction in HIE patient cohorts and fetal image reconstruction, while more general development addresses how to rapidly deploy ML pipelines for a range of possible medical informatics domains.

 

Who are contact points for ML at the FNNDSC

 

Dr Yangming Ou is using Neural Networks and Support Vector Machines in HIE research efforts.

Dr Kiho Im is using Neural Networks to improve fetal image reconstruction

pipelines.

Dr Rudolph Pienaar leads the development of generic ML training and deployment infrastructure to be used in a wide variety of problem settings, including models of segmentation on brain images, continuous training infrastructure, lung CT/radiograph models, and more.