DeepSARS is an automatic deep learning system whose objective is the early identification and follow-up of patients at risk of acute respiratory distress syndrome. This project is developed by the Industrial University of Santander (UIS), the Santander Ophthalmology Foundation (FOSCAL) and the Autonomous University of Bucaramanga (UNAB), with the support of the Ministry of Science, Technology and Innovation (MINCIENCIAS).

The general objective of this project is to develop a computational strategy for the registration, quantification and representation of gait patterns in semi-controlled environments as support in telerehabilitation assistance processes. This approach allows recording videos of the displacement and particular movements of patients associated with musculoskeletal conditions, supporting the provision of tele-rehabilitation services in vulnerable regions of the country.

The main objective of the project is to develop a computational method for the characterization and quantification of cardiac patterns in cine-MRI sequences, using deep learning representations, to support the diagnosis of cardiovascular diseases. Heart disease is the leading cause of death globally, with more than 17.9 million deaths reported during 2016.

The general objective of this project is to identify and associate visual characteristics learned through supervised and self-supervised learning in deep learning models with nuclear pleomorphism in histological images of breast cancer. It should be noted that breast cancer is one of the most frequent manifestations of cancer that affects women in the world. According to the World Health Organization, the majority (69%) of deaths from this cancer are registered in developing countries.