Abstract

Introduction:Visual inspection by magnetic resonance (MR) images cannot detect microscopic tissue changes occurring in MS in normal appearing white matter (NAWM) and may be perceived by the human eye as having the same texture as normal white matter (NWM). The aim of the study was to evaluate computer aided diagnosis (CAD) system using texture analysis (TA) in MR images to improve accuracy in identification of subtle differences in brain tissue structure.Material and Methods:The MR image database comprised 50 MS patients and 50 healthy subjects. Up to 270 statistical texture features extract as descriptors for each region of interest. The feature reduction methods used were the Fisher method, the lowest probability of classification error and average correlation coefficients (POE+ACC) method and the fusion Fisher plus the POE+ACC (FFPA) to select the best, most effective features to differentiate between MS lesions, NWM and NAWM. The features parameters were used for texture analysis with principle component analysis (PCA) and linear discriminant analysis (LDA). Then first nearest-neighbour (1-NN) classifier was used for features resulting from PCA and LDA. Receiver operating characteristic (ROC) curve analysis was used to examine the performance of TA methods.Results:The highest performance for discrimination between MS lesions, NAWM and NWM was recorded for FFPA feature parameters using LDA; this method showed 100% sensitivity, specificity and accuracy and an area of Az = 1 under the ROC curve.Conclusion:TA is a reliable method with the potential for effective use in MR imaging for the diagnosis and prediction of MS.

Highlights

  • Visual inspection by magnetic resonance (MR) images cannot detect microscopic tissue changes occurring in Multiple sclerosis (MS) in normal appearing white matter (NAWM) and may be perceived by the human eye as having the same texture as normal white matter (NWM)

  • The feature reduction methods used were the Fisher method, the lowest probability of classification error and average correlation coefficients (POE+ACC) method and the fusion Fisher plus the POE+ACC (FFPA) to select the best, most effective features to differentiate between MS lesions, NWM and NAWM

  • The highest performance for discrimination between MS lesions, NAWM and NWM was recorded for FFPA feature parameters using linear discriminant analysis (LDA); this method showed 100% sensitivity, specificity and accuracy and an area of = 1 under the Receiver operating characteristic (ROC) curve

Read more

Summary

Introduction

Visual inspection by magnetic resonance (MR) images cannot detect microscopic tissue changes occurring in MS in normal appearing white matter (NAWM) and may be perceived by the human eye as having the same texture as normal white matter (NWM). Magnetic resonance imaging (MRI) has been the most frequently-used technique since the 1980s for evaluating MS lesions within the brain and spinal cord and to monitor its progress (Thompson et al, 2000; Young et al, 1981). Texture analysis detects pathological changes that cannot be perceived by the human eye using conventional MRI techniques. This mathematical technique increases quantification of and information about macroscopic MS lesions in the brain that are usually undetectable using conventional measurement of lesion volume and number (Fazekas et al, 1999). The present study provides additional information to support this method

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call