titoli, abstracts, parole chiave >>>
A Completely automated CAD system for mass detection in a large mammographic database

Bellotti, Roberto and De Carlo, Francesco and Tangaro, Sonia and Gargano, Gianfranco and Maggipinto, Giuseppe and Castellano, Marcello and Massafra, Raffaella and Cascio, Donato and Fauci, Francesco and Magro, Rosario and Raso, Giuseppe and Lauria, Adele and Forni, Giustina and Bagnasco, Stefano and Cerello, Piergiorgio and Zanon, Eugenio and Cheran, Sorin Cristian and Lopez Torres, Ernesto and Bottigli, Ubaldo and Masala, Giovanni Luca Christian and Oliva, Piernicola and Retico, Alessandra and Fantacci, Maria Evelina and Cataldo, Rossella and De Mitri, Ivan and De Nunzio, Giorgio (2006) A Completely automated CAD system for mass detection in a large mammographic database. Medical Physics, Vol. 33 (8), p. 3066-3075. ISSN 0094-2405. Article.

Full text not available from this repository.

DOI: 10.1118/1.2214177


Mass localization plays a crucial role in computer-aided detection (CAD) systems for the classification of suspicious regions in mammograms. In this article we present a completely automated classification system for the detection of masses in digitized mammographic images. The tool system we discuss consists in three processing levels: (a) Image segmentation for the localization of regions of interest (ROIs). This step relies on an iterative dynamical threshold algorithm able to select iso-intensity closed contours around gray level maxima of the mammogram. (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 gray level intensity. As the images under study were recorded in different centers and with different machine settings, eight GTSDM features were selected so as to be invariant under monotonic transformation. In this way, the images do not need to be normalized, as the adopted features depend on the texture only, rather than on the gray tone levels, too. (c) ROI classification by means of a neural network, with supervision provided by the radiologist’s diagnosis. The CAD system was evaluated on a large database of 3369 mammographic images [2307 negative, 1062 pathological (or positive), containing at least one confirmed mass, as diagnosed by an expert radiologist]. To assess the performance of the system, receiver operating characteristic (ROC) and free-response ROC analysis were employed. The area under the ROC curve was found to be Az=0.783±0.008 for the ROI-based classification. When evaluating the accuracy of the CAD against the radiologist-drawn boundaries, 4.23 false positives per image are found at 80% of mass sensitivity.

Item Type:Article
ID Code:4527
Uncontrolled Keywords:Mammography, diseases, image classification, medical image processing, image segmentation, sensitivity analysis, iterative methods, neural nets, statistical analysis, image texture, breast cancer, mammographic mass detection, image processing, computer-aided detection (CAD), textural features, neural network
Subjects:Area 02 - Scienze fisiche > FIS/07 Fisica applicata (a beni culturali, ambientali, biologia e medicina)
Divisions:001 Università di Sassari > 03 Istituti > Matematica e fisica
Publisher:American Association of Physicists in Medicine
Deposited On:08 Sep 2010 13:42

I documenti depositati in UnissResearch sono protetti dalle leggi che regolano il diritto d'autore

Repository Staff Only: item control page