Conference Paper

Adaptive segmentation of internal brain structures in pathological MR images depending on tumor types

CNRS, Ecole Nat. Superieure des Telecommun., Paris
DOI: 10.1109/ISBI.2007.356920 Conference: Biomedical Imaging: From Nano to Macro, 2007. ISBI 2007. 4th IEEE International Symposium on
Source: IEEE Xplore


This paper introduces a novel methodology for the segmentation of internal brain structures in MRI volumes in the presence of a tumor. The proposed method relies on an initial segmentation of the tumor. Based on the tumor's type, a set of spatial relations between internal structures, remaining stable even in presence of the pathology, is established. Segmentation and recognition of surrounding anatomical structures are based on prior knowledge about their spatial arrangement. Segmentation results on tumors inducing small or large deformations are provided to illustrate the potential of the approach.

Download full-text


Available from: Jamal Atif
  • Source
    • "As shown in Refs. [21] [22], spatial relations improve the robustness of the segmentation of the structures even in the presence of pathologies. Another class of methods segment multiple objects simultaneously. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Segmenting the heart in medical images is a challenging and important task for many applications. In particular, segmenting the heart in CT images is very useful for cardiology and oncological applications such as radiotherapy. Although the majority of methods in the literature are designed for ventricle segmentation, there is a real interest in segmenting the heart as a whole in this modality. In this paper, we address this problem and propose an automatic and robust method, based on anatomical knowledge about the heart, in particular its position with respect to the lungs. This knowledge is represented in a fuzzy formalism and it is used both to define a region of interest and to drive the evolution of a deformable model in order to segment the heart inside this region. The proposed method has been applied on non-contrast CT images and the obtained results have been compared to manual segmentations of the heart, showing the good accuracy and high robustness of our approach.
    Full-text · Article · Aug 2008 · Pattern Recognition
  • Source
    • "For instance, tumors inducing little deformation will not lead to a modification of the spatial relations used for the segmentation with respect to the ones used in the normal cases. On the contrary, tumors inducing strong deformations will lead to adaptation of the spatial relations, especially metrical ones [31]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Current electronic patient record (EPR) implementations do not incorporate medical images, nor structural information extracted from them, despite images increasing role for diagnosis. This paper presents an integration framework into EPRs of anatomical and pathological knowledge extracted from segmented magnetic resonance imaging (MRI), applying a graph of representation for anatomical and functional information for individual patients. Focusing on cerebral tumors examination and patient follow-up, multimedia EPRs were created and evaluated through a 3D navigation application, developed with open-source libraries and standards. Results suggest that the enhanced clinical information scheme could lead to original changes in the way medical experts utilize image-based information.
    Full-text · Article · May 2008 · Computers in Biology and Medicine
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Sequential methods for knowledge-based recognition of structures re-quire to define in which order the structures have to be recognized. We propose to address this problem by integrating pre-attention mech-anisms, in the form of a saliency map, in the determination of the or-der. As pre-attention mechanisms extract knowledge from an image without object recognition in ad-vance and do not require any a pri-ori knowledge on the image, they provide useful knowledge for guid-ing object segmentation and recog-nition. Additionally, we make use of generic knowledge of the scene, expressed as spatial relations, since they play a crucial role in model-based image recognition and inter-pretation due to their stability com-pared to many other image appear-ance characteristics. Graphs are well adapted to represent this infor-mation, and finding an order then amounts to find a path in a graph. The proposed algorithms are applied on brain image understanding.
    Full-text · Article · Jan 2008
Show more