A segmentation method based on dynamic programming for breast mass in MRI images

  • Authors:

  • Jihong Liu;Weina Ma;Soo-Young Lee

  • Affiliations:

  • College of Information Science and Engineering, Northeastern University, Shenyang, China and Brain Science Research Center, Korea Advanced Institute of Science and Technology, Daejeon, Korea;College of Information Science and Engineering, Northeastern University, Shenyang, China;Brain Science Research Center, Korea Advanced Institute of Science and Technology, Daejeon, Korea

  • Venue:
  • ICMB'08 Proceedings of the 1st international conference on Medical biometrics
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

The tumor segmentation in Breast MRI image is difficult due to the complicated galactophore structure. The work in this paper attempts to accurately segment the abnormal breast mass in MRI(Magnetic resonance imaging) Images. The ROI (Region of Interest) is segmented using a novel DP (Dynamic Programming) based optimal edge detection technique. DP is an optimal approach in multistage decision-making. The method presented in this paper processes the object image to get the minimum cumulative cost matrix combining with LUM nonlinear enhancement filter, Gaussian preprocessor, nonmaximum suppression and double-threshold filtering, and then trace the whole optimal edge. The experimental results show that this method is robust and efficient on image edge detection and can segment the breast tumor area more accurately.