Robust active appearance models and their application to medical image analysis

• Published in: IEEE transactions on medical imaging 2005-09, Vol.24 (9), p.1151-1169
• Main Authors: Beichel, R., Bischof, H., Leberl, F., Sonka, M.
• Format: Article
• Language: English
• Subjects: Active appearance model; Active appearance models (AAMs); Algorithms; Artificial Intelligence; Biomedical imaging; Computer graphics; Computer Simulation; Diagnostic Imaging - methods; Humans; Image analysis; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image motion analysis; Image segmentation; Image texture analysis; Imaging, Three-Dimensional - methods; Information Storage and Retrieval - methods; Magnetic resonance imaging; mean-shift; model-based segmentation; Models, Biological; Noise robustness; Pattern Recognition, Automated - methods; Reproducibility of Results; robust matching; Sensitivity and Specificity; Shape; Studies; Subtraction Technique
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2005.853237

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.