Topologically controlled segmentation of 3D magnetic resonance images of the head by using morphological operators

Abstract

This paper proposes a new data-driven segmentation technique of 3D T1-weighted magnetic resonance scans of human head. This technique serves to the construction of individual head models. Several structures of the head are extracted. The morphology-oriented approach combined with an extensive use of topological constraints provides a robust and automatic method requiring minimum user intervention. This new approach is suitable to applications where the topology is one of the main constraints. The originality of the approach lies in the satisfaction of such constraints and in an e ort towards robustness.

Component-Trees and Multivalued Images: Structural Properties

“…From an applicative point of view, component-trees have been involved in the development of several image processing and analysis techniques. Most of them are devoted to filtering or segmentation [8], [14], [15], [16], [17]. Other applications have also been considered, for instance, image registration [7], [18], image retrieval [19], [20], image classification [21], interactive visualisation [22], multithresholding [23] or document binarisation [24].…”

Unsupervised 2D gel electrophoresis image segmentation based on active contours

“…Morphological operations, including dilation and erosion, are capable of preserving topological properties such as connectivity and homotopy [34], whereas they are suitable for detecting intensity peaks associated with protein spots in 2D-GE images.…”

Segmentation of Complex Images Based on Component-Trees: Methodological Tools

“…As mentioned above, component-trees have been considered for the development of image segmentation methods, mainly in the field of (bio)medical imaging, and in particular for: dermatological data [10], wood micrographs [6], cerebral MRI [4], CT/MR angiography [19], or confocal microscopy [12].…”

“…It has to be noticed that their use is often only devoted to one specific step of the segmentation (marker selection in [4]), or to perform filtering [19,12], i.e. to remove "useless" parts of the processed image, leading to a superset of an actual segmentation.…”