A New Method for Segmentation of Multiple Sclerosis (MS) Lesions on Brain MR Images

Journal Title: روش های هوشمند در صنعت برق - Year 2015, Vol 6, Issue 21

Abstract

Automatic segmentation of multiple sclerosis (MS) lesions in brain MRI has been widely investigated in recent years with the goal of helping MS diagnosis and patient follow-up. In this study we applied gaussian mixture model (GMM) to segment MS lesions in MR images. Usually, GMM is optimized using expectation-maximization (EM) algorithm. One of the drawbacks of this optimization method is that, it does not convergence to optimal maximum or minimum. Starting from different initial points and saving best result, is a strategy which is used to reach the near optimal. This approach is time consuming and we used another way to initiate the EM algorithm. Also, FAST- Trimmed Likelihood Estimator (FAST-TLE) algorithm was applied to determine which voxels should be rejected. The automatically segmentation outputs were scored by two specialists and the results show that our method has capability to segment the MS lesions with Dice similarity coefficient (DSC) score of 0.82.

Authors and Affiliations

Simin Jafari, Ali Reza Karimian

Keywords

Related Articles

Designing a Two-Phase BLDC Motor and Finite-Element Analysis of Stator Slots Structure Effects on the Motor Operation

Designing a two-phase brushless direct current motor (BLDC) and analyzing effects of stator slots structure on the motor operation are main objectives of this paper. At first BLDC motor with three different structures fo...

A New Control System for a Dual Stator-Winding Cage Rotor Induction Generator in Direct Grid Connected Condition with Maximum Power point tracking of Wind Turbine

In this research a new control system for MPPT in a grid connected three-phase squirrel cage induction wind turbo-generator is presented. This generator is consisted of two Isolated three-phase windings. The first windin...

Simultaneous Design and Simulation of Synergetic Power System Stabilizers and a Thyristor-Controller Series Capacitor in Multi-Machine Power Systems

Power system stabilizers (PSSs) are usually utilized for damping synchronous generator torque in order to reduce these oscillations by producing complementary control signals for the generator excitation system. In this...

Short-Term Load Forecasting of Distribution Power System for Weekdays Using Old Data

Estimation of daily load in distribution companies which is performed to present the results to the DMS, is necessary. Daily load forecasting of power systems has traditionally been considered. Because load patterns are...

New DC/DC High Step Up Isolated Converter with ZVS

In this paper we presents a soft switch sepic, flyback converter. At first the converter have hard switching in main switch and completely analysis then added auxiliary circuit for soft switching Auxiliary circuit in the...

Download PDF file
  • EP ID EP327655
  • DOI -
  • Views 94
  • Downloads 0

How To Cite

Simin Jafari, Ali Reza Karimian (2015). A New Method for Segmentation of Multiple Sclerosis (MS) Lesions on Brain MR Images. روش های هوشمند در صنعت برق, 6(21), 21-30. https://europub.co.uk./articles/-A-327655