My research aims at learning feature representations for medical image diagnosis facing common medical imaging data challenges. Namely limited data, class-imbalance, noisy annotations and data privacy for collaborative learning between different hospitals.
I have explored the role of architectural design in dealing with spatial information for several classification tasks. Also, I have investigated easing the optimization of the deep network parameters by gradually increasing the difficulty of the training samples. This gradual increase is based on the concept of curriculum learning and achieved with a data scheduler that controls the order and pace of the samples.
Lately, I have shifted to investigate meta-data-aware methods to avoid learning biases or shortcuts, as well as, research fairness metrics for patient subgroups, such as age, sex or ethnicity. We are organizing a webinar series: Datasets through the L👀king-Glass to better understand what are researchers doing with their (meta-) data.
Below there is a summary of the of research projects I have been working on: