Paul Okwija Mugume

Research Interests

My interests are at the intersection of AI/ML, medical image analysis, and Point-of-Care technologies and their potential to make quality healthcare accessible to resource-constrained and disadvantaged regions in Africa. I am currently exploring the use of foundation models for medical image segmentation and labelling, local (private) deployment of LLMs, development of agentic AI systems, amongst other things, towards developing clinically viable low-cost solutions that can reduce the burden on medical personnel and extend the reach of expert-level care to underserved areas.

Projects

Title: Model Assisted Labelling for the acceleration of medical image annotation

I am currently working on collecting and curating medical image data and utilizing foundation vision models to reduce the burden and time taken to annotate the data. This will support the development and training of models for segmenting uterine fibroids in 2D ultrasound imaging. This is part of a larger project that aims to automatically detect high-risk pregnancies using portable 2D ultrasound machines and machine learning in low-resource settings in Uganda.

Previous Education and Professional Experiences

Education

BSc. Electrical Engineering - Makerere University [2023]

Experience

Research Engineer - Marconi Lab [ Sept, 2022 - ]

Risk Engineer - UAP Old Mutual Uganda [April, 2023 - Jan, 2024]

Field Engineer Trainee - SLB Uganda [Jan, 2024 - Jan, 2025]

Teaching Assistant - Marconi Lab/Makerere [ Sept, 2022 - Apr, 2023]