TY - GEN
T1 - Feature-driven model-based segmentation
AU - Qazi, Arish A.
AU - Kim, John
AU - Jaffray, David A.
AU - Pekar, Vladimir
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2011
Y1 - 2011
N2 - The accurate delineation of anatomical structures is required in many medical image analysis applications. One example is radiation therapy planning (RTP), where traditional manual delineation is tedious, labor intensive, and can require hours of clinician's valuable time. Majority of automated segmentation methods in RTP belong to either model-based or atlas-based approaches. One substantial limitation of model-based segmentation is that its accuracy may be restricted by the uncertainties in image content, specifically when segmenting low-contrast anatomical structures, e.g. soft tissue organs in computed tomography images. In this paper, we introduce a non-parametric feature enhancement filter which replaces raw intensity image data by a high level probabilistic map which guides the deformable model to reliably segment low-contrast regions. The method is evaluated by segmenting the submandibular and parotid glands in the head and neck region and comparing the results to manual segmentations in terms of the volume overlap. Quantitative results show that we are in overall good agreement with expert segmentations, achieving volume overlap of up to 80%. Qualitatively, we demonstrate that we are able to segment low-contrast regions, which otherwise are difficult to delineate with deformable models relying on distinct object boundaries from the original image data.
AB - The accurate delineation of anatomical structures is required in many medical image analysis applications. One example is radiation therapy planning (RTP), where traditional manual delineation is tedious, labor intensive, and can require hours of clinician's valuable time. Majority of automated segmentation methods in RTP belong to either model-based or atlas-based approaches. One substantial limitation of model-based segmentation is that its accuracy may be restricted by the uncertainties in image content, specifically when segmenting low-contrast anatomical structures, e.g. soft tissue organs in computed tomography images. In this paper, we introduce a non-parametric feature enhancement filter which replaces raw intensity image data by a high level probabilistic map which guides the deformable model to reliably segment low-contrast regions. The method is evaluated by segmenting the submandibular and parotid glands in the head and neck region and comparing the results to manual segmentations in terms of the volume overlap. Quantitative results show that we are in overall good agreement with expert segmentations, achieving volume overlap of up to 80%. Qualitatively, we demonstrate that we are able to segment low-contrast regions, which otherwise are difficult to delineate with deformable models relying on distinct object boundaries from the original image data.
KW - head and neck cancer
KW - model-based segmentation
KW - probability maps
KW - radiation therapy
KW - voxel classification
UR - http://www.scopus.com/inward/record.url?scp=79957995809&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79957995809&partnerID=8YFLogxK
U2 - 10.1117/12.877693
DO - 10.1117/12.877693
M3 - Conference contribution
AN - SCOPUS:79957995809
SN - 9780819485045
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2011
T2 - Medical Imaging 2011: Image Processing
Y2 - 14 February 2011 through 16 February 2011
ER -