A Probabilistic Framework for Point-Based Shape Modeling in Medical Image AnalysisUsing the GGM-SSM as a Prior for Segmentation
A Probabilistic Framework for Point-Based Shape Modeling in Medical Image Analysis: Using the...
Hufnagel, Heike
2011-08-16 00:00:00
[Segmentation algorithms play a major role in medical image analysis. However, due to typical medical image characteristics as poor contrasts, grey value inhomogeneities, contour gaps, and noise the automatic segmentation of many anatomical structures remains a challenge. Low-level algorithms as region growing, thresholding or simple edge-detection are often bound to fail or require heavy user interaction to lead to acceptable segmentation results in 3D images. In order to overcome these problems, a very popular approach is to employ models which incorporate a priori knowledge about mean and variance of shape or grey levels of the structure of interest. These models serve to constrain the resulting segmentation contour to probable shapes as defined by the underlying training data set. The concept of shape priors in segmentation methods has been analysed in section 2.4.]
http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.pnghttp://www.deepdyve.com/lp/springer-journals/a-probabilistic-framework-for-point-based-shape-modeling-in-medical-C02tVadAjE
A Probabilistic Framework for Point-Based Shape Modeling in Medical Image AnalysisUsing the GGM-SSM as a Prior for Segmentation
[Segmentation algorithms play a major role in medical image analysis. However, due to typical medical image characteristics as poor contrasts, grey value inhomogeneities, contour gaps, and noise the automatic segmentation of many anatomical structures remains a challenge. Low-level algorithms as region growing, thresholding or simple edge-detection are often bound to fail or require heavy user interaction to lead to acceptable segmentation results in 3D images. In order to overcome these problems, a very popular approach is to employ models which incorporate a priori knowledge about mean and variance of shape or grey levels of the structure of interest. These models serve to constrain the resulting segmentation contour to probable shapes as defined by the underlying training data set. The concept of shape priors in segmentation methods has been analysed in section 2.4.]
To get new article updates from a journal on your personalized homepage, please log in first, or sign up for a DeepDyve account if you don’t already have one.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.