Format

Send to

Choose Destination
See comment in PubMed Commons below
Comput Biol Med. 2014 Jun;49:46-59. doi: 10.1016/j.compbiomed.2014.03.003. Epub 2014 Mar 13.

Breast cancer detection from MR images through an auto-probing discrete Fourier transform system.

Author information

  • 1Faculty of Engineering and Technology, Multimedia University, Jalan Ayer Keroh Lama, 75450 Malacca, Malaysia. Electronic address: kssim@mmu.edu.my.
  • 2Faculty of Engineering and Technology, Multimedia University, Jalan Ayer Keroh Lama, 75450 Malacca, Malaysia.

Abstract

A computer-aided detection auto-probing (CADAP) system is presented for detecting breast lesions using dynamic contrast enhanced magnetic resonance imaging, through a spatial-based discrete Fourier transform. The stand-alone CADAP system reduces noise, refines region of interest (ROI) automatically, and detects the breast lesion with minimal false positive detection. The lesions are then classified and colourised according to their characteristics, whether benign, suspicious or malignant. To enhance the visualisation, the entire analysed ROI is constructed into a 3-D image, so that the user can diagnose based on multiple views on the ROI. The proposed method has been applied to 101 sets of digital images, and the results compared with the biopsy results done by radiologists. The proposed scheme is able to identify breast cancer regions accurately and efficiently.

Copyright © 2014 Elsevier Ltd. All rights reserved.

KEYWORDS:

Breast cancer detection; Discrete fourier transform; Lesion segmentation; Magnetic resonance imaging

[PubMed - indexed for MEDLINE]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Write to the Help Desk