Informatics Publishing Limited

A. Shenbagarajan ¹, V. Ramalingam ¹, C. Balasubramanian ², S. Palanivel ¹

Affiliations
1 Department of Computer Science and Engineering, Annamalai University, Chidambaram - 608002, Tamil Nadu, IN
2 Department of Computer Science and Engineering, P. S. R. Rengasamy College of Engineering for Women, Sivakasi - 626140, Tamil Nadu, IN

Abstract

Background: Magnetic Resonance Images (MRI) is an important medical diagnosis tool for the detection of tumours in brain as it provides the detailed information associated to the anatomical structures of the brain. MRI images help the radiologist to find the presence of abnormal cell growths or tumours. MRI image analysis plays a vital role in diagnosis of brain tumours in the earlier stages and treatment of diseases. Methods: Therefore, this paper introduces an efficient MRI brain image analysis method, where, the MRI brain images are classified into normal, non cancerous (benign) brain tumour and cancerous (malignant) brain tumour. This proposed method follows four steps, 1. Pre-processing, 2. Segmentation, 3. Textural and shape feature extraction and 4. Classification. In this proposed MRI image analysis using the region based Active Contour Method (ACM) used for segmentation and Artificial Neural Network (ANN) based Levenberg-Marquardt (LM) algorithm used for classification process, which used to efficiently classify the MRI image as normal and Tumourous. Findings: The results revealed that the proposed MRI brain image tumour diagnosis process is accurate, fast and robust. The classifier based MRI brain image processing approach produced the best MRI brain image classification with use of feature extraction and segmentation results, in terms of accuracy. Best overall classification accuracy results were obtained using the given DioCom Images; The performance results proven that there is not sufficient result given to the classification process when it perform separately. With the use of ACM segmentation and feature extraction approaches, the proposed LM classification approach provides better classification accuracy than the existing approach. Application: The proposed MRI image based brain tumour analysis would efficiently deal with segmentation and classification process for brain tumour analysis with use of feature extraction methods, so this method can yield the better result of brain tumour diagnosis in advance where this method  using in medical fields.

Keywords

Active Contour Method (ACM), Artificial Neural Network (ANN) based Levenberg-Marquardt (LM) Algorithm, Magnetic Resonance Images (MRI)

Full Text

   

Shenbagarajan Anantharajan ¹, A. Siva Ganesh ², V. Rajesh Kumar ¹, C. Balasubramanian ²

Affiliations
1 Department of Computer Science and Engineering, P.S.R. Rengasamy College of Engineering for Women, IN
2 Department of Computer Science and Engineering, P.S.R. Engineering College, IN

Abstract

In this proposed method, various types of noise models are subjected to an image and apply the nonlinear filter to reconstruct the original image from degraded image. Image restoration is a technique to attempt of reconstructs the original image by using a degraded phenomenon. In this paper the Lucy-Richardson filter is reconstruct the degraded image which closely resembles the original image. This paper deals with the various noise models and nonlinear filter. Objective of this paper is to study the various noise models and restoration filters in depth at restoration area.

Keywords

Noises, Non Linear Filter, Restoration, Convolution.

Full Text