• Home
  • Search
  • Medical Images Segmentation Using Learned Priors
  • https://doi.org/10.1007/978-1-4419-8204-9_4Copy DOI Icon

Medical Images Segmentation Using Learned Priors

  • Jan 1, 2011
  • Ayman El-Baz +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Objects of specific shapes in an image are typically segmented with a deformable model being zero level of a geometric-level set function specifying sign-alternate shortest distances to the object boundary from each pixel. The goal shapes are approximated by a linear combination of such 2D distance maps built for mutually aligned images of given training objects. Unfortunately, the approximate shapes may deviate much from the training ones because the space of the distance maps is not closed with respect to linear operations and the map for zero level of a particular linear combination need not coincide with the latter. To avoid this drawback, we propose a parametric deformable model with the energy tending to approach the learned shapes. Instead of the level sets formalism, the target shapes are approximated directly with linear combinations of distance vectors describing positions of the mutually aligned training shapes with respect to their common centroid. Such a vector space is now closed with respect to the linear operations and it is of much smaller dimensionality than the 2D distance maps. Thus our shape model is easily simplified with the PCA, and shape-dependent energy terms guiding the boundary evolution obtain very simple analytic form. Prior knowledge of visual appearance of the object is represented by Gibbs energies of its gray levels. To accurately separate the object from its background, each current empirical marginal probability distribution of gray values within a deformable boundary is also approximated with an adaptive linear combination of discrete Gaussians. Both the shape/appearance priors and the current probabilistic appearance description control the boundary evolution, the appearance-dependent energy terms having also simple forms due to analytical estimates. Experiments with natural images confirm robustness, accuracy, and high speed of the proposed approach.

Similar Papers
  • Research Article
  • Citations102

Accurate Lungs Segmentation on CT Chest Images by Adaptive Appearance-Guided Shape Modeling.

  • Sep 12, 2016
  • IEEE Transactions on Medical Imaging
  • Ahmed Soliman +8
  • Conference Article
  • Citations47

A Framework for Automatic Segmentation of Lung Nodules from Low Dose Chest CT Scans

  • Jan 01, 2006
  • A El-Baz +5
  • Book Chapter
  • Citations17

Cerebrovascular Segmentation by Accurate Probabilistic Modeling of TOF-MRA Images

  • Jan 01, 2005
  • Ayman El-Baz +2
  • Conference Article
  • Citations17

A statistical framework for the classification of infant DT images

  • Oct 01, 2014
  • Mahmoud Mostapha +7
  • Book Chapter
  • Citations2

Medical Image Segmentation Using Modified Level-Set Model with Multi-Scale Gradient* Vector Flow

  • Jan 01, 2010
  • Rajalida Lipikorn +4
  • Conference Article
  • Citations20

Actual morphing: a physics-based approach to blending

  • Jun 09, 2004
  • Shi‐Min Hu +2
  • Research Article
  • Citations5

SACNet: Shuffling atrous convolutional U‐Net for medical image segmentation

  • Dec 19, 2022
  • IET Image Processing
  • Shaofan Wang +3
  • Dissertation
  • Citations1

Image based approach for early assessment of heart failure.

  • Feb 12, 2015
  • Hisham Sliman
  • Book Chapter
  • Citations9

Conv-MCD: A Plug-and-Play Multi-task Module for Medical Image Segmentation

  • Jan 01, 2019
  • Balamurali Murugesan +5
  • Research Article
  • Citations1

An adaptive level set method for serial image segmentation

  • Dec 01, 2012
  • The Imaging Science Journal
  • Z L Fu +4
  • Research Article
  • Citations101

High-level prior-based loss functions for medical image segmentation: A survey

  • Jul 21, 2021
  • Computer Vision and Image Understanding
  • Rosana El Jurdi +4
  • Research Article
  • Citations3

From Few to More: Scribble-Based Medical Image Segmentation via Masked Context Modeling and Continuous Pseudo Labels.

  • Mar 01, 2026
  • IEEE journal of biomedical and health informatics
  • Zhisong Wang +5
  • Research Article

Multi-annotation agreement and prediction consistency networks: Improving semi-supervised segmentation of medical images with ambiguous boundaries.

  • Jan 01, 2026
  • Artificial intelligence in medicine
  • Shuai Wang +10
  • Book Chapter
  • Citations13

A Framework for Unsupervised Segmentation of Multi-modal Medical Images

  • Jan 01, 2006
  • Ayman El-Baz +4
  • Research Article
  • Citations35

2D shape morphing via automatic feature matching and hierarchical interpolation

  • Mar 12, 2009
  • Computers & Graphics
  • Wenwu Yang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.