Papers by Olivier Cuisenaire
International Journal of Computer Assisted Radiology and Surgery, 2006
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Stroke, 2002
Bookmarks Related papers MentionsView impact
A relatively large class of information theoretical measures, including e.g. mutual information o... more A relatively large class of information theoretical measures, including e.g. mutual information or normalized entropy, has been used in multi-modal medical image registration. Even though the mathematical foundations of the different measures were very similar, the final expressions turned out to be surprisingly different. Therefore one of the main aims of this paper is to enlight the relationship of different objective functions by introducing a mathematical framework from which several known optimization objectives can be deduced. Furthermore we extend existing measures in order to be applicable on image features different than image intensities and introduce "feature efficiency" as a very general concept to qualify such features. The presented framework is very general and not at all restricted to medical images. Still we want to discuss the possible impact of our theoretical framework for the particular problem of medical image registration, where the feature space has traditionally been fixed to image intensities. Our theoretical approach is very general though and can be used for any kind of multi-modal signals, such as for the broad field of multi-media applications.
Bookmarks Related papers MentionsView impact
IEEE Transactions on Medical Imaging, 2005
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
IEEE Transactions on Medical Imaging, 2006
Bookmarks Related papers MentionsView impact
We present a hierarchical multi-object surface-based deformable atlas for the automatic localizat... more We present a hierarchical multi-object surface-based deformable atlas for the automatic localization and identification of brain structures in MR images. The atlas is a multi-object mesh of 3D fully connected surfaces built upon a face centered cubic grid. The registration of the atlas to a patient's MR image is done in two steps: a global registration followed by a multi-object active surface deformation. First, the cortical surface and the ventricular system are segmented using directional watersheds. The global registration is a second degree transformation whose coefficients minimize a distance measure between these surfaces and the equivalent surfaces in the atlas. As a refinement step, the globally registered atlas surfaces are locally deformed using multi-object active surfaces. The external force driving the surfaces towards the edges in the image is a decreasing function of the gradient, and includes prior image information. The active surface equations are then solved using the finite element method. The surfaces of the multi-object mesh are deformed in a hierarchical way, starting with objects exhibiting very well defined features in the image to objects showing less obvious features. Experiments involving several sub-cortical atlas objects are presented.
Bookmarks Related papers MentionsView impact
IEEE Transactions on Medical Imaging, 2004
Bookmarks Related papers MentionsView impact
Experimental Brain Research, 2002
A sound that we hear in a natural setting allows us to identify the sound source and localize it ... more A sound that we hear in a natural setting allows us to identify the sound source and localize it in space. The two aspects can be disrupted independently as shown in a study of 15 patients with focal right-hemispheric lesions. Four patients were normal in sound recognition but severely impaired in sound localization, whereas three other patients had difficulties in recognizing sounds but localized them well. The lesions involved the inferior parietal and frontal cortices, and the superior temporal gyrus in patients with selective sound localization deficit; and the temporal pole and anterior part of the fusiform, inferior and middle temporal gyri in patients with selective recognition deficit. These results suggest separate cortical processing pathways for auditory recognition and localization.
Bookmarks Related papers MentionsView impact
We present an automatic and unsupervised method for non-rigid registration of 3D magnetic resonan... more We present an automatic and unsupervised method for non-rigid registration of 3D magnetic resonance (MR) images with the Stockholm Computerized Brain Atlas (CBA). This method can be used in the context of multimodal medical image registration, fusion and automatic brain segmentation. In these applications anatomical images (MR) are coregistered with low spatial resolution functional imaging modalities (PET and SPECT) and fused with the neurological database of the CBA. The proposed matching method is based on the minimization of a 3D Chamfer distance function between the surface of the brain extracted from the MR image and the CBA brain surface. The surface-to-surface distance function is efficiently calculated by using a precomputed point-to-surface Euclidean distance map. The non-rigid inter-patient transformation of the CBA is modeled by a generalized 3D second order transformation. This transformation is easily differentiable and, as a consequence, fast and efficient minimization methods can be used. First, a quasi-rigid, first order transformation is computed. Then, the matching is improved by introducing the second order coefficients into the transformation. After this global matching, a local adaptation of the CBA is performed by a morphing method. The combination of a second order global transformation with a 3D local morphing allows the user to obtain a registration accuracy of one pixel, i.e. a mean distance between the surface of the brain in the MR image and the CBA of one pixel, which is significantly better than what can be expected from a human operator.
Bookmarks Related papers MentionsView impact
By propagating a vector for each pixel, we show that nearly Euclidean distance maps can be produc... more By propagating a vector for each pixel, we show that nearly Euclidean distance maps can be produced quickly by a region growing algorithm using hierarchical queues. Properties of the propagation scheme are used to detect potentially erroneous pixels and correct them by using larger neighbourhoods, without significantly affecting the computation time. Thus, Euclidean distance maps are produced in a time comparable to its commonly used chamfer approximations.
Bookmarks Related papers MentionsView impact
Computer Vision and Image Understanding, 1999
Bookmarks Related papers MentionsView impact
Journal of Neuroscience Methods, 2000
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Medical image processing is a demanding domain, both in terms of CPU and memory requirements. The... more Medical image processing is a demanding domain, both in terms of CPU and memory requirements. The volume of data to be processed is often large (a typical MRI dataset requires 10 MBytes) and many processing tools are only useful to the physician if they are ...
Bookmarks Related papers MentionsView impact
Bookmarks Related papers MentionsView impact
Pattern Recognition, 2006
Bookmarks Related papers MentionsView impact
Uploads
Papers by Olivier Cuisenaire