Search

This paper presents a belief propagation approach to the segmentation of the major white matter tracts in diffusion tensor images of the human brain. Unlike tractography methods that sample multiple fibers to be bundled together, we define a Markov field directly on the diffusion tensors to separate the main fiber tracts at the voxel level. A prior model of shape and direction guides a full segmentation of the brain into known fiber tracts; additional, unspecified fibers; and isotropic regions. The method is evaluated on various data sets from an atlasing project, healthy subjects, and multiple sclerosis patients.

This paper presents a new atlas-based segmentation framework for the delineation of major regions in magnetic resonance brain images employing an atlas of the global topological structure as well as a statistical atlas of the regions of interest. A segmentation technique using fast marching methods and tissue classification is proposed that guarantees strict topological equivalence between the segmented image and the atlas. Experimental validation on simulated and real brain images shows that the method is accurate and robust.

A common goal in deformable registration applications is to produce a spatial transformation that is diffeomorphic, thereby preserving the topology of structures being transformed. Because this constraint is typically enforced only on the continuum, however, topological changes can still occur within discretely sampled images. This work discusses the notion of homeomorphisms in digital images, and how it differs from the diffeomorphic/homeomorphic concepts in continuous spaces commonly used in medical imaging.We review the differences and problems brought by considering functions defined on a discrete grid, and propose a practical criterion for enforcing digital homeomorphisms in the context of atlas-based segmentation.

This paper presents a novel approach for object segmentation in medical images that respects the topological relationships of multiple structures as given by a template. The algorithm combines advantages of tissue classification, digital topology, and level-set evolution into a topology-invariant multiple-object fast marching method. The technique can handle any given topology and enforces object-level relationships with little constraint over the geometry. Applied to brain segmentation, it sucessfully extracts gray matter and white matter structures with the correct spherical topology without topology correction or editing of the sub-cortical structures.

We present here a new method for correcting the topology of objects segmented from medical images. Whereas previous techniques alter a surface obtained from the hard segmentation of the object, our technique works directly in the image domain, propagating the topology for all isosurfaces of the object. From an analysis of topological changes and critical points in implicit surfaces, we introduce a topology progagation algorithm that enforces any desired topology using a fast marching technique. Compared to previous topology correction techniques, the method successfully corrects topology while effecting fewer changes to the original volume.

We propose a new method for removing topological defects in surfaces and volumes segmented from medical images. Unlike current topology correction approaches, we define a smoothing operator that acts solely on the image volume and can be integrated into segmentation procedures. The method is based on an analysis of the scalar field underlying the isosurface of interest, and performs only local changes. No assumptions are required on the structure to segment, or on the desired topology. We show that segmentation algorithms that incorporate toplogical smoothing produce results with fewer topological defects.

Partial volume effects are present in nearly all medical imaging data. These artifacts blur the boundaries between different regions, making accurate delineation of anatomical structures difficult. In this paper, we propose a method for unsupervised estimation of partial volume fractions in single-channel image data. Unlike previous methods, the proposed algorithm simultaneously estimates partial volume fractions, the means of the different tissue classes, as well as the the locations of tissue boundaries within the image. The latter allows the partial volume fractions to be constrained to represent pure or nearly pure tissue except along tissue boundaries. We demonstrate the application of the algorithm on simulated and real magnetic resonance images.

An algorithm is proposed for the fuzzy segmentation of two and three-dimensional multispectral magnetic resonance (MR) images that have been corrupted by intensity inhomogeneities, also known as shading artifacts. The algorithm is an extension of the two-dimensional adaptive fuzzy C-means algorithm (2-D AFCM) presented in previous work by the authors. This algorithm models the intensity inhomogeneities as a gain field that causes image intensities to smoothly and slowly vary through the image space. It iteratively adapts to the intensity inhomogeneities and is completely automated. In this paper, we fully generalize 2-D AFCM to three-dimensional (3-D) multispectral images. Because of the potential size of 3-D image data, we also describe a new, faster multigrid-based algorithm for its implementation. We show using simulated MR data that 3-D AFCM yields significantly lower error rates than both the standard fuzzy C-means algorithm and several other competing methods when segmenting corrupted images. Its efficacy is further demonstrated using real 3-D scalar and multispectral MR brain images.

Automatic segmentation and identification of cortical sulci play an important role in the study of brain structure and function. In this work, a method is presented for the automatic segmentation of sulcal regions of cortex. Unlike previous methods that extract the sulcal spaces within the cortex, the proposed method extracts actual regions of the cortical surface that surround sulci. Sulcal regions are segmented from the medial surface as well as the lateral and inferior surfaces. The method first generates a depth map on the surface, computed by measuring the distance between the cortex and an outer “shrink-wrap” surface. Sulcal regions are then extracted using a hierarchical algorithm that alternates between thresholding and region growing operations. To visualize the buried regions of the segmented cortical surface, an efficient technique for mapping the surface to a sphere is proposed. Preliminary results are presented on the geometric analysis of sulcal regions for automated identification.

Reconstruction of the human cerebral cortex from MR images is a fundamental step in human brain mapping and in applications such as surgical path planning. In a previous paper, we described a method for obtaining a surface representation of the central layer of the human cerebral cortex using fuzzy segmentation and a deformable surface model. This method, however, suffers from several problems. In this paper, we significantly improve upon the previous method by using a fuzzy segmentation algorithm robust to intensity inhomogeneities, and using a deformable surface model specifically designed for capturing convoluted sulci or gyri. We demonstrate the improvement over the previous method both qualitatively and quantitatively, and show the result of its application to six subjects. We also experimentally validate the convergence of the deformable surface initialization algorithm.

A method for finding the cortical surface of the brain from magnetic resonance images using a combination of fuzzy segmentation, isosurface extraction, and a deformable surface is presented. After MR images are acquired and preprocessed to remove extracranial tissue, fuzzy membership functions for gray matter, white matter, and cerebrospinal fluid are computed. An iterative procedure using isosurfaces of filtered white matter membership functions is then used to obtain a topologically correct estimate of the cortical surface. This estimate forms the initialization of a deformable surface, which is then allowed to converge to peaks of the gray matter membership function. We demonstrate the results of each step and show the final parameterized map of the medial layer of the cortex.