Machine learning in medical imaging

Marleen de Bruijne - University Medical Center Rotterdam
Date and time
Tuesday, May 12, 2015 at 5:00 PM - 16:45 rinfresco, 17:00 inizio seminario
Ca' Vignal 1, Floor terra, Lecture Hall E
Programme Director
Manuele Bicego
External reference
Publication date
May 7, 2015
Computer Science  


Quantitative analysis of medical imaging data plays an increasingly important role both in large-scale clinical studies and in diagnosis, monitoring, and prognosis of disease in individual patients. Traditionally, medical image analysis techniques measure factors that are already known to be related to disease, such as for instance the density of lung tissue or the size of certain brain structures. The current availability of large databases that combine medical images with other patient data allows for a more data-driven approach in which the important characteristics related to disease outcome are learned directly from a training data set. This talk will cover different approaches to learn models of shape, appearance, and motion from imaging data. I will present techniques to address common issues in large medical imaging studies: differences between images acquired with varying scan protocols, weakly annotated data, and reconstruction of missing data. Applications are in lung, cardiovascular, and brain imaging

© 2002 - 2021  Verona University
Via dell'Artigliere 8, 37129 Verona  |  P. I.V.A. 01541040232  |  C. FISCALE 93009870234