Skip to main content

Statistically Efficient Structured Prediction for Computer Vision and Medical Imaging

Objective

Inference in medical imaging is an important step for disease diagnosis, tissue segmentation, alignment with an anatomical atlas, and a wide range of other applications. However, imperfections in imaging sensors, physical limitations of imaging technologies, and variation in the human population mean that statistical methods are essential for high performance. Statistical learning makes use of human provided ground truth to enable computers to automatically make predictions on future examples without human intervention. At the heart of statistical learning methods is risk minimization - the minimization of the expected loss on a previously unseen image. Textbook methods in statistical learning are not generally designed to minimize the expected loss for loss functions appropriate to medical imaging, which may be asymmetric and non-modular. Furthermore, these methods often do not have the capacity to model interdependencies in the prediction space, such as those arising from spatial priors, and constraints arising from the volumetric layout of human anatomy. We aim to develop new statistical learning methods that have these capabilities, to develop efficient learning algorithms, to apply them to a key task in medical imaging (tumor segmentation), and to prove their convergence to optimal predictors. To achieve this, we will leverage the structured prediction framework, which has shown impressive empirical results on a wide range of learning tasks. While theoretical results giving learning rates are available for some algorithms, necessary and sufficient conditions for consistency are not known for structured prediction. We will consequently address this issue, which is of key importance for algorithms that will be applied to life critical applications, e.g. segmentation of brain tumors that will subsequently be targeted by radiation therapy or removed by surgery. Project components will address both theoretical and practical issues.

Field of science

  • /natural sciences/computer and information sciences/artificial intelligence/computer vision
  • /medical and health sciences/clinical medicine/radiology/medical imaging

Call for proposal

FP7-PEOPLE-2012-CIG
See other projects for this call

Funding Scheme

MC-CIG - Support for training and career development of researcher (CIG)

Coordinator

KATHOLIEKE UNIVERSITEIT LEUVEN
Address
Oude Markt 13
3000 Leuven
Belgium
Activity type
Higher or Secondary Education Establishments
EU contribution
€ 58 333,33
Administrative Contact
Stijn Delaure (Dr.)

Participants (1)

INSTITUT NATIONAL DE RECHERCHE ENINFORMATIQUE ET AUTOMATIQUE

Participation ended

France
EU contribution
€ 41 666,67
Address
Domaine De Voluceau Rocquencourt
78153 Le Chesnay Cedex
Activity type
Research Organisations
Administrative Contact
Mireille Moulin (Mrs.)