Article on diabetic retinopathy wins Best Paper Award in the USA

The article "MedAL: Accurate and Robust Deep Active Learning for Medical Image Analysis", in which three INESC TEC’s researchers are co-authors, namely Pedro Costa and Adrian Galdran, collaborators of the Centre for Biomedical Engineering Research (C-BER) at the time of the paper, and Aurélio Campilho, current coordinator of C-BER and Full Professor at the Faculty of Engineering of the University of Porto, received a “best paper award” at ICMLA 2018 - 17th Conference on Machine Learning and Application.

The event took place in Orlando, United States of America, between 17 and 20 December 2018 at a conference that has been continuously organised for 15 years and is considered to be one of the best in the area with a rate of acceptance of articles of about 31%.

This article was the result of the collaboration between the researchers from C-BER and the researchers from the University of Carnegie Mellon (USA). The article describes the work developed in the SCREEN-DR project. SCREEN-DR aims to create a platform for the screening of diabetic retinopathy, which is the main cause for blindness in the industrialised world. Using Machine Learning and Computer Vision techniques, this platform will allow a more efficient and accurate response by the healthcare providers in three situations: assessment of the image quality, detection of normal retinal images and assignment of a degree of the pathology severity.

The researcher mentioned in this news piece is associated with UP-FEUP.