BAYESIAN TECHNIQUE (MEDICAL IMAGE SEGMENTATION) FOR IMAGE CLASSIFYING REGISTRATION

Abstract

In this paper, we propose a new model in which the similarity criterion is adapted locally to images by classification of image intensity dependencies. Defined in a Bayesian framework, the similarity criterion is a mixture of probability distributions describing dependencies on two classes. The model also includes a class map which locates pixels of the two classes and weights the two mixture components. The registration problem is formulated both as an energy minimization problem and as a Maximum A Posteriori (MAP) estimation problem. It is solved using a gradient descent algorithm. In the problem formulation and resolution, the image deformation and the class map are estimated at the same time, leading to an original combination of registration and classification that we call image classifying registration. Finally, we illustrate the interest of our model on two real applications from medical imaging: templatebased segmentation of contrast-enhanced images and lesion detection in mammograms. We also conduct an evaluation of our model on simulated medical data and show its ability to take into account spatial variations of intensity dependencies while keeping good registration accuracy.

Authors and Affiliations

Sumangla Pawar

Keywords

Related Articles

 Wireless Body Area Networks and Its Emerging Technologies in Real Time Applications

 With the rapid improvement of wireless communication and semiconductor technologies, the body area sensor network (BASN) is fast developing. The BASN which is also referred to as the WBAN (Wireless Body Area Netw...

 Design and Implementation of 1kva Uninterrupted Power Supply

 The power conditioner designed to deliver an output of 1.0KVA basically it’s composed of a battery control circuit, the inverter and automatic voltage regulator. The inverter stage is the part that will take powe...

 NEW FRAMEWORK FOR ANALYSIS OF CAPTCHA SECURITY FOR HARD AI PROBLEMS

 The ability area between people and bots in acknowledging connected and distorted figures becomes progressively smaller with advances of segmentation and Optical Character Recognition (OCR) technologies. This trend...

 Study of Active Contour Modelling for Image Segmentation: A Review

 Active contour models are widely used for image segmentation. In this paper the study of various active contour models based on Chan-Vese approach is given. Partial differential equation based method widely used o...

 Microstrip Antenna with Two Circular Grooves Corrugated in Ground Plane

 In this paper we present a proposed design of microstrip antenna with enhanced gain and radiation pattern by two circular grooves corrugated ground plane instead of no grooved ground plane conventional aperture-co...

Download PDF file
  • EP ID EP133118
  • DOI -
  • Views 61
  • Downloads 0

How To Cite

Sumangla Pawar (2015).  BAYESIAN TECHNIQUE (MEDICAL IMAGE SEGMENTATION) FOR IMAGE CLASSIFYING REGISTRATION. International Journal of Engineering Sciences & Research Technology, 4(12), 197-202. https://europub.co.uk/articles/-A-133118