Automatic evolutionary medical image segmentation using deformable models

Abstract

Abstract-This paper describes a hybrid level set approach to medical image segmentation. The method combines regionand edge-based information with the prior shape knowledge introduced using deformable registration. A parameter tuning mechanism, based on Genetic Algorithms, provides the ability to automatically adapt the level set to different segmentation tasks. Provided with a set of examples, the GA learns the correct weights for each image feature used in the segmentation.The algorithm has been tested over four different medical datasets across three image modalities. Our approach has shown significantly more accurate results in comparison with six stateof-the-art segmentation methods. The contributions of both the image registration and the parameter learning steps to the overall performance of the method have also been analyzed.

Automatic stage identification of Drosophila egg chamber based on DAPI images

“…Chan-Vese segmentation method: The Chan-Vese segmentation algorithm 41 has been successfully used in a wide range of medical applications in lesion and tumor segmentation 42 43 44 .The Chan-Vese algorithm segments an image by minimizing an energy function that balances out foreground-background boundary length, foreground area, and purity of the foreground and background. We applied the algorithm to segmentation of the gray scale image from the previous step ( Fig.…”

An Active Contour Model Based on Adaptive Threshold for Extraction of Cerebral Vascular Structures

“…Among these techniques, the ACM has been widely applied in medical image segmentation because of its easy extensibility. The ACM is based on geometric curve evolution theory and the essential idea of that technique is to evolve the initial curve or surface to the boundaries of target objects driven by internal forces and external forces [ 18 ]. Active contours can be implicitly presented by the level-set methods, which put original curves into higher dimensional spaces to research and are achieved in numerical computations by the Eulerian approach [ 19 ].…”