3D imaging in medicine
Using deformable surfaces to segment 3-D images and infer differential structures
CVGIP: Image Understanding
Shape Modeling with Front Propagation: A Level Set Approach
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active Contours: The Application of Techniques from Graphics,Vision,Control Theory and Statistics to Visual Tracking of Shapes in Motion
Shape and topology constraints on parametric active contours
Computer Vision and Image Understanding
Tamed Snake: A Particle System for Robust Semi-automatic Segmentation
MICCAI '99 Proceedings of the Second International Conference on Medical Image Computing and Computer-Assisted Intervention
Topologically adaptable snakes
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Multicriterion Decision in Management: Principles and Practice
Multicriterion Decision in Management: Principles and Practice
Hi-index | 0.00 |
This paper presents a variation of the classic algorithm of active contours in order to improve the visualization of 3D reconstruction of anatomical structures in medicine. This 3D reconstructions are made from the obtained contours. This variation of active contour enables a better behavior of them.Other authors have already used snakes (active contours) for segmenting shapes in medical images. But they usually fail in accurately adjust to the desired contour.The proposed variation introduce a new kind of energy in the classical formula of active contours. This new energy is based in the computation of distance to several supervised lures that attract the snake points. Once the lures are selected, the active contours work in a fully automated way. This new variation of active contours have been tested on CT medical images to segment contours of different bone structures. The results show that the proposed active contour is superior in results to the classical method. We have used a multiple criteria decision making framework for obtaining the final conclusions of this survey.The new variation proposed for active contours works better for detecting vertebrae contours in CT images. In addition, a new energy and use of lures for active contours have been introduced.