TU Darmstadt / ULB / TUbiblio

Fast Automatic Liver Segmentation Combining Learned Shape Priors with Observed Shape Deviation

Erdt, Marius and Steger, Sebastian and Kirschner, Matthias and Wesarg, Stefan (2010):
Fast Automatic Liver Segmentation Combining Learned Shape Priors with Observed Shape Deviation.
IEEE Computer Society, Los Alamitos, Calif., In: Twenty-Third IEEE Symposium on Computer-Based Medical Systems, [Conference or Workshop Item]

Abstract

We present a novel statistical shape model approach for fully automatic CT liver segmentation. Unlike previous techniques, our method combines learned local shape priors with constraints that are directly derived from the current curvature of the model in order to restrict adaptation to regions where large deformations are expected and observed. Our approach is based on a multi-tiered framework that is more robust against model initialization errors than existing methods, because the model's degrees of freedom are step-wise increased. We evaluated our method on a large data base of 86 CT liver scans from different vendors, protocols, varying resolution and contrast enhancement. For comparison, 50 of the scans were taken from 2 public data bases, one of it being the MICCAI'07 liver segmentation challenge data base. Evaluation shows state of the art results with an average mean surface distance between 1.3 mm and 1.85 mm compared to ground truth depending on the image resolution. With an average segmentation time of 45 seconds our approach outperforms other automatic methods.

Item Type: Conference or Workshop Item
Erschienen: 2010
Creators: Erdt, Marius and Steger, Sebastian and Kirschner, Matthias and Wesarg, Stefan
Title: Fast Automatic Liver Segmentation Combining Learned Shape Priors with Observed Shape Deviation
Language: English
Abstract:

We present a novel statistical shape model approach for fully automatic CT liver segmentation. Unlike previous techniques, our method combines learned local shape priors with constraints that are directly derived from the current curvature of the model in order to restrict adaptation to regions where large deformations are expected and observed. Our approach is based on a multi-tiered framework that is more robust against model initialization errors than existing methods, because the model's degrees of freedom are step-wise increased. We evaluated our method on a large data base of 86 CT liver scans from different vendors, protocols, varying resolution and contrast enhancement. For comparison, 50 of the scans were taken from 2 public data bases, one of it being the MICCAI'07 liver segmentation challenge data base. Evaluation shows state of the art results with an average mean surface distance between 1.3 mm and 1.85 mm compared to ground truth depending on the image resolution. With an average segmentation time of 45 seconds our approach outperforms other automatic methods.

Publisher: IEEE Computer Society, Los Alamitos, Calif.
Uncontrolled Keywords: Forschungsgruppe Medical Computing (MECO), Model based segmentations, Computed tomography (CT), Active shape models (ASM)
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: Twenty-Third IEEE Symposium on Computer-Based Medical Systems
Date Deposited: 12 Nov 2018 11:16
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item