Multi-scale textural feature extraction and particle swarm optimization based model selection for false positive reduction in mammography.

Journal: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
Published Date:

Abstract

The high number of false positives and the resulting number of avoidable breast biopsies are the major problems faced by current mammography Computer Aided Detection (CAD) systems. False positive reduction is not only a requirement for mass but also for calcification CAD systems which are currently deployed for clinical use. This paper tackles two problems related to reducing the number of false positives in the detection of all lesions and masses, respectively. Firstly, textural patterns of breast tissue have been analyzed using several multi-scale textural descriptors based on wavelet and gray level co-occurrence matrix. The second problem addressed in this paper is the parameter selection and performance optimization. For this, we adopt a model selection procedure based on Particle Swarm Optimization (PSO) for selecting the most discriminative textural features and for strengthening the generalization capacity of the supervised learning stage based on a Support Vector Machine (SVM) classifier. For evaluating the proposed methods, two sets of suspicious mammogram regions have been used. The first one, obtained from Digital Database for Screening Mammography (DDSM), contains 1494 regions (1000 normal and 494 abnormal samples). The second set of suspicious regions was obtained from database of Mammographic Image Analysis Society (mini-MIAS) and contains 315 (207 normal and 108 abnormal) samples. Results from both datasets demonstrate the efficiency of using PSO based model selection for optimizing both classifier hyper-parameters and parameters, respectively. Furthermore, the obtained results indicate the promising performance of the proposed textural features and more specifically, those based on co-occurrence matrix of wavelet image representation technique.

Authors

  • Imad Zyout
    Communications, Electronics and Computer Engineering Department, Tafila Technical University, Tafila 66110, Jordan. Electronic address: izyout@ttu.edu.jo.
  • Joanna Czajkowska
    Department of Computer Science and Medical Equipment, Faculty of Biomedical Engineering, Silesian University of Technology, ul. Roosevelta 40, 41-800 Zabrze, Poland.
  • Marcin Grzegorzek
    Institute for Vision and Graphics, University of Siegen, Hoerlindstr. 3, 57076 Siegen, Germany.