When available, position(s) are posted below.
For more details and to apply, please refer to the Queen’s University Career Services website.
Summer Work Experience Program (SWEP)
Position Title:
Applying open-source deep learning models to improve cell segmentation and cell phenotyping on multiplex immunofluorescence images
Term:
May to Aug 2026
Position Description:
Recent developments in multiplex immunofluorescence staining and quantitative image analysis techniques have enabled precise spatial assessment of tumors and the associated immune microenvironment on formalin-fixed and paraffin-embedded (FFPE) specimens.
As pathologists, we are interested in implementing these techniques in the diagnostic laboratory, which requires optimization of the technical workflow for robustness, accuracy, and scalability.
This project will introduce to the students the overall technical pipeline of multiplex staining and analysis, with particular focus on optimizing several key areas of the multiplex image analysis workflow, through close collaboration with departmental computational scientist.
We will use diagnostic bone marrow specimens from multiple myeloma or myelodysplastic syndrome patients, with the goal of characterizing key T cell and NK cell subsets within the tumor immune microenvironment.
Master (MSc) Degree Program in the Department of Pathology and Molecular Medicine
Position Title:
Development of Multiplex Staining Panel and Validation of Machine Learning and Quantitative Image Analysis Workflow to Assess Bone Marrow Tumor Immune Microenvironment
Position Description:
Full-time graduate student position to work using advanced microscopy and image analysis technique to transform diagnostic assessment of tumor immune microenvironment.
Student will be involved in the entire pipeline of multiplex (10-plex) staining panel development, whole-slide confocal imaging, and down-stream analysis of multiple myeloma and MDS/AML bone marrow specimens.
Familiarity and prior work experience in Python, R, Linux, and other programming skill would be highly valued. Whole-slide fluorescence images will be analyzed using existing open-source or commercial platforms.
Relevant machine learning and deep learning models will be applied to improve accuracy of nuclear segmentation, and cell classification (cell phenotyping).
Data and information science skillset is highly valued to oversee batch-able and scalable workflow to process high number of patient samples.
Basic biostatistics skill is needed for general data analysis, and for implementation of appropriate spatial statistics package for whole-slide image analysis.
Strong performance in prior course work in human biology and immunology would be preferred.
Candidates who are interested in a career in health care services (i.e. diagnostic medicine, laboratory technology, laboratory information system), pharma or biotech, and who have strong training in computer science, computational biology, information science, biostatistics, applied mathematics, bioengineering, or other relevant fields are encouraged to apply.