Research lines
Over the last years, I have developed research in Artificial Intelligence across multiple fields of application, working on problems that range from food safety and psychology to education and architecture. Although my experience spans many domains, my current work is strongly focused on AI applied to medicine, particularly computer vision for medical imaging and the analysis of brain signals.
01
Medical imaging
My research in medical imaging centres on applying AI and computer vision techniques to support diagnosis, prognosis, and clinical decision-making. Over the years, I have worked with a wide range of imaging modalities, including ultrasound, thermography, and histopathology, and developed deep learning models for tumour detection, melanoma classification or breast cancer analysis.
02
Brain Signal Analysis
I also conduct research on brain-signal analysis, applying machine learning and deep learning to EEG, fMRI, and other neurological data. My work includes developing models to identify pathological brain states, analyse connectivity, and support diagnosis in conditions such as epilepsy, Parkinson’s disease, and cognitive or behavioural disorders.
03
Foundations of Deep Learning
I also have interests in the foundations of deep learning, with a strong emphasis on data quality and model reliability. This includes studying out-of-distribution (OOD) behaviour, measuring the trustworthiness of synthetic datasets, and analysing how data characteristics influence performance and generalisation.
04
Applications across domains
Throughout my career, I have applied machine learning and deep learning to a wide range of domains beyond medicine, including architectural heritage reconstruction, food safety prediction, audio enhancement, and educational analytics.
