3D active shape modeling for cardiac MR and CT image segmentation
Hans C. van Assen · 2006
3D Active Shape Modeling is a technique to capture shape information from a training set containing characteristic shapes of, e.g., a heart. The description contains a mean shape, and shape variations (e.g. eigen deformations and eigen values). Many models based on these statistics, and used for medical purposes, are limited in their application by properties of the training set. These properties are, the radiological modality used for image acquisition (1), the orientation of the images (2), and the density of the data (3). In our model of the cardiac left ventricle, the limits above were relieved by not training on gray level information (1,2), using a Fuzzy Inference System for finding image features in CT and MR data (1), and weighted propagation of image features along the model surfaces (3). Evalutation of our model on both CT and MR showed almost equal performance. Evaluation of three different point-correspondences used for model- building did not clearly indicate one as best. By extended tuning using a grid-computing approach, and propagation of image features, we managed to achieve segmentation results on sparse data comparable to those of others on dense data. Our model is more widely applicable thanks to these developments.