INVESTIGATION ON MAMMOGRAPHIC IMAGE COMPRESSION AND MICROCALCIFICATION ANALYSIS USING MULTIWAVELETS AND NEURAL NETWORKS

In digital mammography, the resulting electronic image is very large in size, which poses a significant challenge to the transmission, storage, and manipulation of images. Microcalcification is one of the earliest signs of breast cancer, and it tends to appear in small-sized, low-contrast radiopacit...

Full description

Saved in:
Bibliographic Details
Published in:Applied artificial intelligence 2013-02, Vol.27 (2), p.77-85
Main Authors: Ragupathy, U. S., Tamilarasi, A., Thangavel, K.
Format: Article
Language:English
Subjects:
Breast cancer
Classification
Comparative analysis
Compressed
Expert systems
Image compression
Mammography
Neural networks
Radiopacity
Scalars
Signal to noise ratio
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In digital mammography, the resulting electronic image is very large in size, which poses a significant challenge to the transmission, storage, and manipulation of images. Microcalcification is one of the earliest signs of breast cancer, and it tends to appear in small-sized, low-contrast radiopacities in the high-frequency spectrum of a mammographic image. Scalar wavelets excel multiwavelets in terms of peak-signal-to-noise ratio (PSNR), but fail to capture high-frequency information. This study proposes mammographic image compression and microcalcification detection in original and compressed reconstructed images using multiwavelets and neural networks. It also details the classification results obtained through the multiwavelet-based scheme in comparison with the existing scalar wavelet-based scheme. For a testing sample of 30 images, the proposed classification scheme outperforms the scalar wavelet-based classification by a sensitivity of 2.23% and specificity of 3.4% for original (uncompressed) images. Also, it increases the sensitivity by 2.72% and specificity by 8.4% for compressed reconstructed images. This increase in sensitivity and specificity demonstrates a better performance of the proposed detection scheme.
ISSN:0883-9514
1087-6545
DOI:10.1080/08839514.2013.760403