MEDICAL IMAGING LAB

The IAL works on the development and optimisation of methods which will help in the analysis of the data, with particular interest in the study of medical images. To this end, the IAL group develops computer vision and image processing algorithms which include techniques such as image segmentation, image characterization, pattern recognition, object detection, statistical signal processing, and image registration. Furthermore, the capabilities of IAL include image analysis for a variety of imaging modalities including X-rays, magnetic resonance imaging (MRI), ultrasound (US), and computed tomography (CT).

Research areas

Multiple sclerosis (MS) diagnosis and folow up

Multiple sclerosis diagnosis and folow up

Development and validation of automatic tools which allow detection, segmentation and characterization of brain MRI images, with particular interest in multiple sclerosis lesions. These tools are very useful to diagnose and follow-up the disease by looking at the evolution of the brain lesions and brain atrophy in patients. The aims of our projects in this line are to develop new automatic computerized tools to extract robust MRI biomarkers. This will enable a new paradigm that will provide the basis for improving the diagnosis and monitoring of MS and stratification of patients by introducing objectivity and simplifying the daily clinical practice.

Breast cancer diagnosis

Breast Cancer Diagnosis

The group is engaged in Computer-Aided Detection (CADe) and Computer-Aided Diagnosis (CADx) of breast cancer in X-ray mammograms, breast US and breast MRI. Furthermore, the group is currently developing computer application tools to combine breast images from different technologies (digital mammography, MRI and US). The aim of these tools is to help radiologists to improve breast cancer diagnosis by producing more efficient models.

Prostate cancer localization

Prostate cancer localization

The team has also developed a CADx application which uses multiparametric MRI information for improving prostate cancer diagnosis. The aim here is to help in the diagnosis and to improve also the biopsy process by fusing information coming from MRI and ultrasound images.

PROJECTS

PUBLICATIONS

https://www.udg.edu/ca/instituts/VICOROB/Publicacions