PolyDeep

Intelligent system for real-time detection and classification of colorectal lesions using deep learning

A research project for better polyp detection and classifiation funded by the Spanish Ministry of Science, Innovation and Universities, through the National Programme for Research Aimed at the Challenges of Society 2017 call (DPI2017-87494-R)

What is PolyDeep?

PolyDeep is a research project that seeks to improve the detection and classification of colorectal polyps through colonoscopies.

To achieve this, PolyDeep proposes the development of a CAD system to assist the endoscopist during the endoscopy. The core of this CAD system consists of two Deep Learning models, one for detection and another one for classification, developed using a new polyp video and image dataset created in collaboration with the CHUO Hospital (Ourense, Spain).

More information →

Who we are?

The PolyDeep team is composed of researchers from the SING group (Universidade de Vigo), the GIODO group (Complexo Hospitalario Universitario de Ourense, CHUO) and the IT service of the CHUO.

The SING and GIODO groups also belong to the Instituto de Investigaciones Sanitarias Galicia Sur.

More information →