Data Fusion Techniques for Breast Cancer Detection

• Grant number: 24/08242-8
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: October 01, 2024
• End date: September 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: João Paulo Papa
• Grantee: Jawaher Abdu Mohammed Altuweity
• Host Institution: Faculdade de Ciências (FC). Universidade Estadual Paulista (UNESP). Campus de Bauru. Bauru , SP, Brazil
• Associated research grant: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry, AP.CEPID

Abstract

Assisted disease diagnosis through medical imaging, clinical data, and text description has been paramount in recent years. Allied with the astonishing and promising results machine learning delivers, one may achieve even more accurate performance when using all available data sources. On the other hand, we face the problem of combining different data modalities. How to ensure one modality will not bias others, how to learn proper weights for each data source, and how to encode them are some challenges that data fusion techniques address. This proposal investigates shortcomings in breast cancer detection using different imaging (mammography, tomosynthesis, and ultrasonography) and textual (clinical data and physician report) data. The researcher involved in the proposal will investigate data fusion techniques at feature and decision levels and will be in touch with prominent scientists from Sao Paulo State and other countries. We expect the researcher to be involved in other activities, such as working with the lab partners and attending seminars. This proposal links to a more significant FAPESP project (CeMEAI - Center for Mathematical Sciences Applied to Industry), contributing to the medical industry and applied research. Besides, we expect to bring new advances in data fusion strategies concerning Computer Science and machine learning research areas.