A number of methods for medical image analysis will be presented and their application to real cases will be discussed. In particular, attention will be focused on computer-aided detection (CAD) systems for lung nodule diagnosis in thorax-computed tomography (CT) and breast cancer detection in mammographic images. In the first case both a region growing (RG) algorithm for lung parenchymal tissue extraction and an active contour model (ACM) for anatomic lung contour detection will be described. In the second case, we will focus on a Haralik's textural feature extraction scheme for the characterization of the regions of interest (ROIs) of the mammogram and a supervised neural network for the classification of the ROIs. © 2010 Springer Science+Business Media B.V.
Digital image processing in medical applications
Sabina Tangaro;Roberto Bellotti;Francesco De Carlo;Gianfranco Gargano
2010-01-01
Abstract
A number of methods for medical image analysis will be presented and their application to real cases will be discussed. In particular, attention will be focused on computer-aided detection (CAD) systems for lung nodule diagnosis in thorax-computed tomography (CT) and breast cancer detection in mammographic images. In the first case both a region growing (RG) algorithm for lung parenchymal tissue extraction and an active contour model (ACM) for anatomic lung contour detection will be described. In the second case, we will focus on a Haralik's textural feature extraction scheme for the characterization of the regions of interest (ROIs) of the mammogram and a supervised neural network for the classification of the ROIs. © 2010 Springer Science+Business Media B.V.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
