Addressing fairness in artificial intelligence for medical imaging
Nature Communications, 2022
I am currently working on the development of artificial intelligence models for the analysis of medical images with the ultimate goal of transferring these tools to the clinical scenario as support systems for different actors in the medical field.
As part of this process, I focus on the validation and analysis of their algorithmic fairness prior to their effective integration with the other components of health information systems. To carry out these tasks I essentially use Python with libraries such as scikit-learn, Keras, PyTorch and django.
In my most recent work, we evaluated the state of the art of fairness in the field of medical image computing. We discuss the meaning of fairness in this area and comment on potential sources of bias, as well as available strategies to mitigate it. Finally, we analyze the current state of the field, identifying strengths and highlighting vacant areas, challenges and opportunities.
Nature Communications, 2022
delHospital Ediciones, 2021
Fundación para el Desarrollo Regional, 2022
Innova Salud Digital, 2022
Innova Salud Digital, 2021
Innova Salud Digital, 2021
Artificial Intelligence, Medical Image Computing, Clinical Decision Support Systems
Group website
Informatics applied to clinical research, Bioengineering, Big Data, Data Science, Artificial Intelligence
Interface development, Simulation, Data entry, Data Visualization
Advisor: Dr. Rodrigo Echeveste
Co-Advisor: Dr. Enzo Ferrante
Thesis plan: Contributions to translational artificial intelligence: new fair and adaptive machine learning methods for dermoscopies processing in clinical scenarios.
Thesis: Design and implementation of a skills training system for minimally invasive surgery
Academic exchange in the 4th year of the Biomedical Engineering course (Biomedical Imaging itinerary)