Mass lesion detection in mammographic images using Haralik textural features

In this article we present a classification system for an automatic detection of masses in digitized mammographic images. The systems consists in three main processing levels: a) image segmentation for the localization of regions of interest (ROIs); b) ROI characterization by means of textural features computed from the Gray Tone Spatial Dependence Matrix (GTSDM), containing second order spatial statistics information on the pixel grey level intensity; c) ROI classification by means of a neural network, with supervision provided by the radiologist’s diagnosis. The CAD system was developed and evaluated using a database of N I = 3369 mammographic images: the breakdown of the cases was N In = 2307 negative images, and N Ip = 1062 pathological (or positive) images, containing at least one confirmed mass, as diagnosed by an expert radiologist. To examine the performance of the overall CAD system, receiver operating characteristic (ROC) and free-response ROC (FROC) analysis were employed. The area under the ROC curve was found to be A z = 0.78 ± 0.008 for ROI-based classification. When evaluating the accuracy of the CAD against the radiologist-drawn boundaries, 4.23 false positive per image (FPpI) are found at 80% mass sensitivity.

[1]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[2]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[3]  S. Feig,et al.  Increased benefit from shorter screening mammography intervals for women ages 40‐49 years , 1997, Cancer.

[4]  Richard W. Conners,et al.  A Theoretical Comparison of Texture Algorithms , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  L. Tabár,et al.  REDUCTION IN MORTALITY FROM BREAST CANCER AFTER MASS SCREENING WITH MAMMOGRAPHY Randomised Trial from the Breast Cancer Screening Working Group of the Swedish National Board of Health and Welfare , 1985, The Lancet.

[6]  Francesco Fauci,et al.  Search of microcalcification clusters with the CALMA CAD station , 2002, SPIE Medical Imaging.

[7]  R. Bird,et al.  Analysis of cancers missed at screening mammography. , 1992, Radiology.

[8]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[9]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[10]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[11]  Francesco Fauci,et al.  A massive lesion detection algorithm in mammography. , 2005, Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics.

[12]  Geoffrey Cox,et al.  Experiments in Lung Cancer Nodule Detection Using Texture Analysis and Neural Network Classifiers , 1992 .

[13]  Piernicola Oliva,et al.  Comparison of imaging properties of several digital radiographic systems , 2001 .

[14]  Nico Karssemeijer,et al.  Computer-aided detection versus independent double reading of masses on mammograms. , 2003, Radiology.

[15]  U Bottigli,et al.  [Application of a computer-aided detection (CAD) system to digitalized mammograms for identifying microcalcifications]. , 2001, La Radiologia medica.

[16]  S Tangaro,et al.  GPCALMA: a Grid-based Tool for Mammographic Screening , 2004, Methods of Information in Medicine.

[17]  A. Retico,et al.  Mammogram Segmentation by Contour Searching and Mass Lesions Classification With Neural Network , 2004, IEEE Transactions on Nuclear Science.

[18]  S Tangaro,et al.  A completely automated CAD system for mass detection in a large mammographic database. , 2006, Medical physics.

[19]  R. Prevete,et al.  The MAGIC-5 Project: medical applications on a GRID infrastructure connection , 2004, IEEE Symposium Conference Record Nuclear Science 2004..

[20]  S. Cheran,et al.  “Classifiers Trained on dissimilarity representation of medical pattern : A comparative study” , 2005 .

[21]  Azriel Rosenfeld,et al.  A Comparative Study of Texture Measures for Terrain Classification , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[22]  Mohan M. Trivedi,et al.  Segmentation of a high-resolution urban scene using texture operators , 1984, Comput. Vis. Graph. Image Process..

[23]  S. Bagnasco,et al.  Mammogram segmentation by contour searching and massive lesion classification with neural network , 2004, IEEE Symposium Conference Record Nuclear Science 2004..

[24]  R. M. Haralick,et al.  Textural features for image classification. IEEE Transaction on Systems, Man, and Cybernetics , 1973 .