Robust active appearance models and their application to medical image analysis

Reinhard Beichel; Horst Bischof; Franz Leberl; Milan Sonka

doi:10.1109/TMI.2005.853237

Back

Robust active appearance models and their application to medical image analysis

Journal article

Peer reviewed

Robust active appearance models and their application to medical image analysis

Reinhard Beichel, Horst Bischof, Franz Leberl and Milan Sonka

IEEE transactions on medical imaging, Vol.24(9), pp.1151-1169

09/2005

DOI: 10.1109/TMI.2005.853237

PMID: 16156353

View Online

Abstract

Active appearance models (AAMs) have been successfully used for a variety of segmentation tasks in medical image analysis. However, gross disturbances of objects can occur in routine clinical setting caused by pathological changes or medical interventions. This poses a problem for AAM-based segmentation, since the method is inherently not robust. In this paper, a novel robust AAM (RAAM) matching algorithm is presented. Compared to previous approaches, no assumptions are made regarding the kind of gray-value disturbance and/or the expected magnitude of residuals during matching. The method consists of two main stages. First, initial residuals are analyzed by means of a mean-shift-based mode detection step. Second, an objective function is utilized for the selection of a mode combination not representing the gross outliers. We demonstrate the robustness of the method in a variety of examples with different noise conditions. The RAAM performance is quantitatively demonstrated in two substantially different applications, diaphragm segmentation and rheumatoid arthritis assessment. In all cases, the robust method shows an excellent behavior, with the new method tolerating up to 50% object area covered by gross gray-level disturbances.

Reproducibility of Results

Information Storage and Retrieval - methods

Artificial Intelligence

Humans

Image Interpretation, Computer-Assisted - methods

Imaging, Three-Dimensional - methods

Subtraction Technique

Diagnostic Imaging - methods

Algorithms

Models, Biological

Computer Simulation

Sensitivity and Specificity

Image Enhancement - methods

Pattern Recognition, Automated - methods

Details

Title: Subtitle: Robust active appearance models and their application to medical image analysis
Creators: Reinhard Beichel - Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/2, A-8010 Graz, Austria. beichel@icg.tu-graz.ac.at
Horst Bischof
Franz Leberl
Milan Sonka
Resource Type: Journal article
Publication Details: IEEE transactions on medical imaging, Vol.24(9), pp.1151-1169
DOI: 10.1109/TMI.2005.853237
PMID: 16156353
NLM abbreviation: IEEE Trans Med Imaging
ISSN: 0278-0062
eISSN: 1558-254X
Publisher: Institute of Electrical and Electronics Engineers; United States
Grant note: R01-HL071809 / NHLBI NIH HHS
Language: English
Date published: 09/2005
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Injury Prevention Research Center; Ophthalmology and Visual Sciences
Record Identifier: 9984046903202771

Metrics

14 Record Views

61 Times Cited - Web of Science

See more details