Quercus

Estudio comparativo del rendimiento de distintas funciones de pérdida (AUFL, DSCL, CE) aplicadas a la segmentación de lesiones pulmonares por COVID-19 en imágenes de tomografía computarizada.

We have just published a comprehensive analysis on how the choice of loss function affects the segmentation of COVID-19 lung infections in computed tomography.

New publication from our lab evaluating SAM’s capabilities for medical image segmentation.

Segment Anything Model (SAM), developed by Meta, demonstrates exceptional performance in medical image segmentation, particularly for lung CT scans and chest X-rays, achieving an average Jaccard index of 91.45% and an average Dice score of 94.95% with minimal user intervention. In particular, SAM exceeds the 70% threshold recommended in the literature and rivals state-of-the-art models explicitly designed for medical segmentation.

Intel’s academic GPU donation program supports i3 lab.

Our paper “Impact of ChatGPT on the evaluation methods of a Computer Engineering degree” has won the best paper award at JENUI 2023!

Generative Artificial Intelligences have experienced significant evolution in recent years and, especially, in 2022. One of the AIs …

Copyright Analysis in Multimedia Pieces Broadcast in Audiovisual Media using Machine Learning

Cloud-based Platform for On-demand Music Generation by Artificial Intelligence