========================================================

	   Dataset: MM-S2MRPH-F03

	Morphological features of mammographic masses
	      Greece, Feb.2003
 
	        Release Notes

	Copyright (c) 2016 by Harris V. Georgiou

========================================================
   Release:     Aug 3, 2016

   - Version:  1.1a
   - Format:   .mat
========================================================


This file contains important information about the
current version of the dataset package.

Downloading and using this material hints that you
accept the EULA/Terms-of-Use (please read carefully).

We welcome your comments and suggestions.

_______________________________________________
WHAT'S IN THIS PACKAGE?

-  Overview
-  Available file formats
-  Files and Datasets
-  License Agreement

_______________________________________________
OVERVIEW

In localized breast cancers, the morphology and shape characteristics
of the detected masses have been established as factors of great 
importance in the discrimination between fibroadenomas, cysts and
carcinomas, due to inherent anatomical differences directly related 
to malignancy. Approximately 80—85% of diagnostic information is 
retrieved from the mammographic appearance of the mass.

This package contains efficient datasets of simple yet effective shape 
features, employed in the original and multi-scaled spectral representations
of the boundary, for the characterization of the mammographic mass. Their
analysis consists of (a) the investigation of the original radial distance 
measurements under the complete spectrum of signal analysis, (b) the
application of curve feature extractors of morphological characteristics.

The files also include the full radial-distance and spectral registration
of 142 localized masses in mammograms, as well as a set of qualitative
features that have been proven as of outmost importance regarding the true
pathology in each case. For the construction of the raw material for these 
datasets, 130 of the 142 MLO mammograms containing a mass were selected by 
an expert physician for digitization, including a total of 46 benign mass 
cases and 84 mass malignancies of various types (12 were marked 'unreliable').

The digitized mammograms were subsequently transformed digitally to a 
resolution of 63 mm (400 dpi) at 8-bit gray level, which is consistent 
with other typical image databases of digitized mammograms that are used 
as a reference in similar studies.

Detailed information about the files and the structure of the datasets 
are available in the manifest file (S2_data_morph_directory.pdf).

For further information see:

* M. Mavroforakis, H. Georgiou, et.al.
"Significance Analysis of Qualitative Mammographic Features Using Linear 
Classifiers, Neural Networks and Support Vector Machines", 
European Journal of Radiology, 54 (2005) 80-89. 
(doi:10.1016/j.ejrad.2004.12.015)

* H. Georgiou, M. Mavroforakis, et. al.
"Multi-scaled Morphological Features for the Characterization of 
Mammographic Masses Using Statistical Classification Schemes",
Artificial Intelligence in Medicine, 41 (1) (2007), pp.39-55.
(doi:10.1016/j.artmed.2007.06.004)

_______________________________________________
AVAILABLE FILE FORMATS

The datasets are available in the following formats (included):

*.mat	: Matlab/Octave native data file (workspace)

_______________________________________________
FILES AND DATASETS

Root folder:	MM-S2MRPH-F03\

	(For full description see: S2_data_morph_directory.pdf)

_______________________________________________
LICENSE AGREEMENT

This material was produced primarily for academic research and educational purposes. 
Downloading and using this material implies acceptance of the Creative Commons
License: Attribution-NonCommercial-ShareAlike 4.0 International (BY-NC-SA), 2016.
* http://creativecommons.org/licenses/by-nc-sa/4.0/

Copyright (c) 2016 by Harris V. Georgiou (MSc,PhD) -- http://xgeorgio.info


--