A ranklet-based image representation for mass classification in digital mammograms

Masotti, Matteo (2006) A ranklet-based image representation for mass classification in digital mammograms. Medical Physics, 33 (10). pp. 3951-3961.

This is the most updated version of the document.

Full text available as:
[thumbnail of masotti2006aRanklet.pdf]
Download (829kB) | Preview


Regions of interest (ROIs) found on breast radiographic images are classified as either tumoral mass or normal tissue by means of a support vector machine classifier. Classification features are the coefficients resulting from the specific image representation used to encode each ROI. Pixel and wavelet image representations have already been discussed in one of our previous works. To investigate the possibility of improving classification performances, a novel nonparametric, orientation-selective, and multiresolution image representation is developed and evaluated, namely a ranklet image representation. A dataset consisting of 1000 ROIs representing biopsy-proven tumoral masses (either benign or malignant) and 5000 ROIs representing normal breast tissue is used. ROIs are extracted from the digital database for screening mammography collected by the University of South Florida. Classification performances are evaluated using the area Az under the receiver operating characteristic curve. By achieving Az values of 0.978±0.003 and 90% sensitivity with a false positive fraction value of 4.5%, experiments demonstrate classification results higher than those reached by the previous image representations. In particular, the improvement on the Az value over that achieved by the wavelet image representation is statistically relevant with the two-tailed p value <0.0001. Besides, owing to the tolerance that the ranklet image representation reveals to variations in the ROIs' gray-level intensity histogram, this approach discloses to be robust also when tested on radiographic images having gray-level intensity histogram remarkably different from that used for training.

Document type
Masotti, Matteo
Ranklet Transform, Wavelet Transform, Support Vector Machine, Mammography, Medical Image Processing, Image Classification
Deposit date
25 Oct 2006
Last modified
16 May 2011 12:04

Other metadata

Available versions of this document

This work may be freely consulted and used, may be reproduced on a permanent basis in a digital format (i.e. saving) and can be printed on paper with own personal equipment (without availing of third -parties services), for strictly and exclusively personal, research or teaching purposes, with express exclusion of any direct or indirect commercial use, unless otherwise expressly agreed between the user and the author or the right holder. It is also allowed, for the same purposes mentioned above, the retransmission via telecommunication network, the distribution or sending in any form of the work, including the personal redirection (e-mail), provided it is always clearly indicated the complete link to the page of the Alma DL Site in which the work is displayed. All other rights are reserved.



Staff only: View the document