TU Darmstadt / ULB / TUbiblio

Automatic Pancreas Segmentation in Contrast Enhanced CT Data Using Learned Spatial Anatomy and Texture Descriptors

Erdt, Marius and Kirschner, Matthias and Drechsler, Klaus and Wesarg, Stefan and Hammon, Matthias and Cavallaro, Alexander (2011):
Automatic Pancreas Segmentation in Contrast Enhanced CT Data Using Learned Spatial Anatomy and Texture Descriptors.
IEEE Press, New York, In: 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, DOI: 10.1109/ISBI.2011.5872821,
[Conference or Workshop Item]

Abstract

Pancreas segmentation in 3-D computed tomography (CT) data is of high clinical relevance, but extremely difficult since the pancreas is often not visibly distinguishable from the small bowel. So far no automated approach using only single phase contrast enhancement exist. In this work, a novel fully automated algorithm to extract the pancreas from such CT images is proposed. Discriminative learning is used to build a pancreas tissue classifier that incorporates spatial relationships between the pancreas and surrounding organs and vessels. Furthermore, discrete cosine and wavelet transforms are used to build computationally inexpensive but meaningful texture features in order to describe local tissue appearance. Classification is then used to guide a constrained statistical shape model to fit the data. Cross-validation on 40 CT datasets yielded an average surface distance of 1.7 mm compared to ground truth which shows that automatic pancreas segmentation from single phase contrast enhanced CT is feasible. The method even outperforms automatic solutions using multiple-phase CT both in accuracy and computation time.

Item Type: Conference or Workshop Item
Erschienen: 2011
Creators: Erdt, Marius and Kirschner, Matthias and Drechsler, Klaus and Wesarg, Stefan and Hammon, Matthias and Cavallaro, Alexander
Title: Automatic Pancreas Segmentation in Contrast Enhanced CT Data Using Learned Spatial Anatomy and Texture Descriptors
Language: English
Abstract:

Pancreas segmentation in 3-D computed tomography (CT) data is of high clinical relevance, but extremely difficult since the pancreas is often not visibly distinguishable from the small bowel. So far no automated approach using only single phase contrast enhancement exist. In this work, a novel fully automated algorithm to extract the pancreas from such CT images is proposed. Discriminative learning is used to build a pancreas tissue classifier that incorporates spatial relationships between the pancreas and surrounding organs and vessels. Furthermore, discrete cosine and wavelet transforms are used to build computationally inexpensive but meaningful texture features in order to describe local tissue appearance. Classification is then used to guide a constrained statistical shape model to fit the data. Cross-validation on 40 CT datasets yielded an average surface distance of 1.7 mm compared to ground truth which shows that automatic pancreas segmentation from single phase contrast enhanced CT is feasible. The method even outperforms automatic solutions using multiple-phase CT both in accuracy and computation time.

Publisher: IEEE Press, New York
Uncontrolled Keywords: Forschungsgruppe Medical Computing (MECO), Business Field: Digital society, Research Area: Confluence of graphics and vision, Computed tomography (CT), Automatic segmentation, Statistical shape models (SSM), Pancreas
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
Date Deposited: 12 Nov 2018 11:16
DOI: 10.1109/ISBI.2011.5872821
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item