SICAP project

Last updated on Aug 15, 2022
Go to Project Site

The SICAP project aimed to support the cancer diagnostic of prostate cancer. It focused on cancer detection and gradation. It explored several approaches and frameworks to deal with this problem.

Research
Miguel López-Pérez
Miguel López-Pérez
Postdoctoral Researcher

My research interests include Gaussian Processes, ML in digital pathology and weakly supervised methods.

Publications

Classifying Prostate Histological Images Using Deep Gaussian Processes on a New Optical Density Granulometry-Based Descriptor
We introduce the use of a new optical density descriptor together with deep gaussian processes for cancer detection in histological prostate images. This combination outperforms the current state of the art in histopathology both shallow classifiers and deep neural networks like InceptionV3, Xception and VGG19 with an AUC value higher than 0.98.
Miguel López-Pérez, Adrián Colomer, María A. Sales, Valery Naranjo, Rafael Molina
Cite Dataset Project DOI
A new optical density granulometry-based descriptor for the classification of prostate histological images using shallow and deep Gaussian processes
Ángel E. Esteban, Miguel López-Pérez, Adrián Colomer, María A. Sales, Rafael Molina, Valery Naranjo
Cite Dataset Project DOI