A Genetic Algorithm-Based Level Set Curve Evolution for Prostate Segmentation on Pelvic CT and MRI Images

A Genetic Algorithm-Based Level Set Curve Evolution for Prostate Segmentation on Pelvic CT and MRI Images

Payel Ghosh (Portland State University, USA), Melanie Mitchell (Portland State University, USA), James A. Tanyi (Oregon Health and Science University, USA) and Arthur Hung (Oregon Health and Science University, USA)
DOI: 10.4018/978-1-60566-956-4.ch006
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

A novel genetic algorithm (GA) is presented here that performs level set curve evolution using texture and shape information to automatically segment the prostate on pelvic images in computed tomography and magnetic resonance imaging modalities. Here, the segmenting contour is represented as a level set function. The contours in a typical level set evolution are deformed by minimizing an energy function using the gradient descent method. In these methods, the computational complexity of computing derivatives increases as the number of terms (needed for curve evolution) in the energy function increase. In contrast, a genetic algorithm optimizes the level-set function without the need to compute derivatives, thereby making the introduction of new curve evolution terms straightforward. The GA developed here uses the texture of the prostate gland and its shape derived from manual segmentations to perform curve evolution. Using these high-level features makes automatic segmentation possible.
Chapter Preview
Top

Literature Review

Segmentation is the process of demarcating an object of interest on an image. Before segmentation can be performed properties of the object that set it apart from the rest of the image must be determined. These properties can be image pixel-based properties such as edges, texture, pixel intensity variation inside the object, or object-level properties such as shape, size, orientation, or location with respect to other objects. The pixel-based features are referred to as low-level features because they can be inferred using simple image processing routines on an image. For example, edges of an image can be derived using a gradient operator on the image pixel values. The object-level features on the other hand, are so-called high-level features because they involve an extra step of finding an appropriate concept to describe a particular feature. For example, “size” of an object can be determined using the distance between two pixels located in the opposite extremities of the object or by the diameter of a circle enclosing the object.

Complete Chapter List

Search this Book:
Reset