Computerized Analysis of Mammographic Images for Detection and Characterization of Breast Cancer

The identification and interpretation of the signs of breast cancer in mammographic images from screening programs can be very difficult due to the subtle and diversified appearance of breast disease. This book presents new image processing and pattern recognition techniques for computer-aided detection and diagnosis of breast cancer in its various forms. The main goals are: (1) the identification of bilateral asymmetry as an early sign of breast disease which is not detectable by other existing approaches; and (2) the detection and classification of masses and regions of architectural distortion, as benign lesions or malignant tumors, in a unified framework that does not require accurate extraction of the contours of the lesions. The innovative aspects of the work include the design and validation of landmarking algorithms, automatic Tabár masking procedures, and various feature descriptors for quantification of similarity and for contour independent classification of mammographic lesions. Characterization of breast tissue patterns is achieved by means of multidirectional Gabor filters. For the classification tasks, pattern recognition strategies, including Fisher linear discriminant analysis, Bayesian classifiers, support vector machines, and neural networks are applied using automatic selection of features and cross-validation techniques. Computer-aided detection of bilateral asymmetry resulted in accuracy up to 0.94, with sensitivity and specificity of 1 and 0.88, respectively. Computer-aided diagnosis of automatically detected lesions provided sensitivity of detection of malignant tumors in the range of [0.70, 0.81] at a range of falsely detected tumors of [0.82, 3.47] per image. The techniques presented in this work are effective in detecting and characterizing various mammographic signs of breast disease.

Autorentext

Paola Casti graduated with honors in Medical Engineering in 2011 from the University of Rome Tor Vergata, with a thesis titled ""Development and validation of a computer-aided detection system for the identification of bilateral asymmetry in mammographic images."" In 2015,she received a Ph.D. in Telecommunications and Microelectronics Engineering with the mention of Excellent Quality Cum Laude. The title of her dissertation was ""Development of an innovative system for early detection and characterization of breast cancer."" During her engineering studies, she was a four-time winner of the annual student award of excellence (given to the top 1% of engineering students) from the University of Rome Tor Vergata. In 2009, she was awarded 1st place in a student competition for the mechanical analysis and computer-aided design of a patented prosthesis, with a project titled ""Multi-configurable Wrist Joint Prosthesis."" She collaborated with the National Institute of Health (Istituto Superiore di Sanita, ISS) in 2009 on a project for microtomographic evaluation of bone substitutes and the obtained results have been published in the Rapporti ISTISAN of the ISS. In 2012, she was selected as one of the young researcher participants of the IEEE EMBS International Summer School on Biomedical Imaging, held in Ile de Berder, Brittany, France. She has coauthored several papers in international peer-reviewed journals, a number of papers in proceedings of international conferences, and technical reports. Her research interests are in signal and image analysis for medical applications, pattern recognition and classification, and computer-aided diagnosis. At present, she is working with the Department of Electronics Engineering of the University of Rome Tor Vergata with a research contract.Arianna Mencattini received an M.S. degree in Electronic Engineering from the University of Rome Tor Vergata, Rome, Italy in 2000, summa cum laude, and a Ph.D. in 2004 for her research on fuzzy logic systems for modelling from the same University. In 2001, she received the award of a Young Researchers Grant and in 2004-2005 she had a scholarship from the Sixth Framework Programme of the European Community at the University of Rome Tor Vergata. Since 2006 she has been an Assistant Professor at the Department of Electronic Engineering, University of Rome Tor Vergata. She is member of the Italian Electrical and Electronic Measurement Group. At present, she teaches a course on image processing. Her main research interests are related to image processing techniques for the development of computed-assisted diagnosis systems, analysis of speech and facial expressions for automatic emotion recognition, and design of novel cell tracking algorithms for immune-cancer interaction analysis. She is the Principal Investigator of the project ""PainTCare, Personal pAIn assessemeNT by an enhanCed multimodAl architecture,"" funded by the University of Rome Tor Vergata, for the automatic assessment of pain in postsurgical patients, and team member of the Project Horizon 2020 ""PhasmaFOOD: Portable photonic miniaturised smart system for on-the-spot food quality sensing."" She has coauthored more than 70 papers in international journals and conferences.Marcello Salmeri received a M.Sc. degree in Electronic Engineering and a Ph.D. in Electronic Engineering from the University of Rome Tor Vergata, in 1989 and 1993, respectively. He is currently an Associate Professor with the Department of Electronic Engineering, University of Rome Tor Vergata, and Coordinator of the Electronic Engineering courses. His research interests include signal and image processing; theory, applications, and implementations of fuzzy systems; and pattern recognition. He is the author of about 100 publications in the fields of electronics, measurement, and data analisys.Rangaraj Mandayam Rangayyan is Professor Emeritus of Electrical and Computer Engineering at the University of Calga

Inhalt
Preface.- Acknowledgments.- Introduction.- Experimental Setup and Databases of Mammograms.- Multidirectional Gabor Filtering.- Landmarking Algorithms.- Computer-aided Detection of Bilateral Asymmetry.- Design of Contour-independent Features for Classification of Masses.- Integrated CADe/CADx of Mammographic Lesions.- Concluding Remarks.- References.- Authors' Biographies.