Profile Image

Jillian Cardinell

Master of Science Candidate

I'm a M.Sc. student at McGill supervised by Professor Tal Arbel at the Probabilistic Vision Group (PVG). For my M.Sc. thesis, I'm focusing on adapting deep learning methods to biases across different Multiple Sclerosis imaging datasets. Previously, during my B.Eng at Ryerson University, I held two research assistant positions. During those positions, I worked with a wide variety of medical computer vision problems including Augmented Reality for surgical navigation, Optical Coherence Tomography for retinal and skin imaging, and deep learning methods for maternal fetal MRI.

You can find my complete CV here.

Research Interests

  • Medical Image Analysis
  • Deep Learning
  • Domain Adaptation
  • Computer vision

Education

  • B.Eng

    Ryerson University, Toronto, Canada

    CGPA: 3.98/4.0 (4.24/4.33)

  • M.Sc.

    McGill University, Montreal, Canada

    CGPA: 4.0/4.0

Experience

  • Research Assistant

    Ryerson University and St. Michael's Hosptial, Canada

  • Research Assistant

    Ryerson University and Sunnybrook Health Sciences Centre, Canada


Cohort Bias Adaptation in Aggregated Datasets for Lesion Segmentation

B. Nichyporuk, J. Cardinell, J. Szeto, R. Mehta, D.L. Arnold, S.Tsaftaris and T. Arbel, "Cohort Bias Adaptation in Federated Datasets for Lesion Segmentation", in Proceedings of the MICCAI 2021 Workshop: 3rd MICCAI Workshop on Domain Adaptation and Representation Transfer (DART), held in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021), held virtually (Strasbourg, France), September 2021. Won Best Paper Award of the DART workshop

Consensus Learning with Multi-Rater Labels for Segmenting and Detecting New Lesions

B. Nichyporuk, K. Vasilevski, A. Hu, C. Myers-Colet, J. Cardinell, J. Szeto, J.P. Falet, E. Zimmermann, J. Schroeter, D. L. Arnold, and T. Arbel. “Consensus Learning with Multi-Rater Labels for Segmenting and Detecting New Lesions,” MSSEG-2 challenge proceedings (2021): Multiple sclerosis new lesions segmentation challenge using a data management and processing infrastructure.


2021, made with in pure Bootstrap 4, inspired by Academic Template for Hugo