I'm Dilermando Queiroz,
a Research Engineer and PhD candidate building AI systems that ensure fairness in medical imaging foundation models
matter?
Medical AI systems trained on biased datasets can yield disparate diagnostic accuracy across demographic subgroups, disproportionately affecting underrepresented populations. My research develops foundation models with fairness-aware training strategies to achieve equitable performance across patient demographics.
→ See my perspective paperExperiences
FairMI Project
Developing fairness frameworks for medical imaging foundation models (FairMI project, FAPESP-SNSF). Using self-supervised learning and distributed training on HPC. Published at MICCAI 2024 and ECCV 2024. Brazil-Switzerland collaboration.
→ See my publicationsIBM Research
Contributed to IBM-NASA Prithvi geospatial foundation model. Co-authored 2 publications (JAMES, AIES 2022) and filed 2 patents on parallel computing and AI-driven forecasting.
→ See my publicationsMathematics and Chemistry
Developed Python library for Geometric Algebra applications in computational chemistry. Work with molecular distance geometry problems using Nuclear Magnetic Resonance data.
→ See my library