Segmentation, registration, and measurement of shape variation via image object shape

Abstract

A model of object shape by nets of medial and boundary primitives is justified as richly capturing multiple aspects of shape and yet requiring representation space and image analysis work proportional to the number of primitives. Metrics are described that compute an object representation's prior probability of local geometry by reflecting variabilities in the net's node and link parameter values and that compute a likelihood function measuring the degree of match of an image to that object representation. A paradigm for image analysis of deforming such a model to optimize a posterior probability is described, and this paradigm is shown to be usable as a uniform approach for object definition, object-based registration between images of the same or different imaging modalities, and measurement of shape variation of an abnormal anatomical object compared with a normal. Examples of applications of these methods in radiotherapy, surgery, and psychiatry are given.

Morphometric analysis of lateral ventricles in schizophrenia and healthy controls regarding genetic and disease-specific factors

“…Shape analysis is an approach to quantify subtle differences in brain structure that could potentially enhance the identification of brain structural abnormalities associated with neurologic and psychiatric illnesses such as schizophrenia. Different shape analysis methods have been suggested in recent years, such as shape analysis through sparse 3D landmarks (16,17), dense point models (14,18,19), parametric boundary models (20,21), medial models (22)(23)(24), or deformable registration (25)(26)(27)(28). We developed methods of shape analysis, which have been adequately validated with reliable results (19,20).…”

Statistics of Pose and Shape in Multi-object Complexes Using Principal Geodesic Analysis

“…Changes in terms of local translation, bending and widening can be more naturally expressed by medial, rather than surface, representations. Pizer et al [6,16] developed an object representation by a mesh of medial atoms. The shape and structure of the skeletal sheet of atoms, as well as a local width function, define the object.…”

“…Whereas Tsai et al [4] and Yang et al [5] describe statistical Martin Styner, Kevin Gorczowski, Tom Fletcher, Ja Yeon Jeong, Stephen M. Pizer, Guido Gerig, Multi-Object Statistics using Principal Geodesic Analysis in a Longitudinal Pediatric Study, Springer Lecture Notes in Computer Science LNCS, Proc. MIAR conference, to appear August 2006 object modeling by level-sets, we propose explicit deformable shape modeling with a sampled medial mesh representation called m-rep, introduced by Pizer et al [6].…”

Computer aided diagnosis in chest radiography

“…Brejl and Sonka [25] have described a scheme similar to ASMs but with a non-linear shape and appearance model that is optimized with an energy function after an exhaustive search to find a suitable initialization. Pizer et al [200] describe an object model that consists of linked primitives which can be fitted to images using methods similar to ASMs. Cootes and Taylor have explored active appearance models (AAMs) as an alternative to ASMs.…”