Computerized analysis of mammographic images for detection and characterization of breast cancer

Medientyp: E-Book

Titel: Computerized analysis of mammographic images for detection and characterization of breast cancer

Beteiligte: Casti, Paola [Verfasser:in]; Mencattini, Arianna [Verfasser:in]; Salmeri, Marcello [Verfasser:in]; Rangayyan, Rangaraj M. [Verfasser:in]

Erschienen: San Rafael, California: Morgan & Claypool, 2017
Cham: Springer International Publishing, 2017.
Cham: Imprint: Springer, 2017.

Umfang: 1 Online-Ressource (1 PDF (xx, 166 pages)); illustrations

Sprache: Englisch

DOI: 10.1007/978-3-031-01664-6

ISBN: 9783031016646; 9781681731575

Identifikator:

Schlagwörter: Breast Radiography ; Radiography, Medical Digital techniques ; Breast Cancer Diagnosis Data processing ; Engineering. ; Biophysics. ; Biomedical engineering. ; Mammography methods ; Breast Neoplasms diagnostic imaging ; Electronic books

Entstehung:

Anmerkungen: Part of: Synthesis digital library of engineering and computer science. - Includes bibliographical references (pages 147-162). - Compendex. INSPEC. Google scholar. Google book search. - Title from PDF title page (viewed on August 7, 2017)
1. Introduction -- 1.1 Breast cancer and mammography -- 1.1.1 Breast cancer statistics -- 1.1.2 Mammography screening programs -- 1.1.3 The mammographic examination -- 1.1.4 Mammographic signs of breast disease -- 1.1.5 BI-RADS mammographic density categories -- 1.1.6 TabĐar masking -- 1.1.7 Drawbacks and limitations of mammography -- 1.2 Computer-aided detection and diagnosis with mammography -- 1.2.1 The role of CAD as a second reader -- 1.2.2 Clinical utility of CAD systems -- 1.2.3 Statistical evaluation of diagnostic performance -- 1.3 Scope and organization of the book -- 1.3.1 Aims of the work -- 1.3.2 Overview --

Beschreibung: 2. Experimental setup and databases of mammograms -- 2.1 Databases of mammograms -- 2.1.1 FFDM database -- 2.1.2 MIAS database -- 2.1.3 DDSM -- 2.2 Validation strategy -- 2.3 Remarks --

3. Multidirectional Gabor filtering -- 3.1 Extraction of directional components -- 3.2 The family of Gabor filters -- 3.2.1 The real Gabor filter -- 3.2.2 Multidirectional filtering -- 3.2.3 Choice of filter parameters -- 3.3 Remarks --

4. Landmarking algorithms -- 4.1 Landmarking of biomedical images -- 4.2 State of the art -- 4.2.1 Previous work on detection of the pectoral muscle -- 4.2.2 Previous work on detection of the nipple -- 4.2.3 Previous work on segmentation of the breast region -- 4.3 Detection of the pectoral muscle -- 4.3.1 Overview of the methods -- 4.3.2 Dataset and experimental setup -- 4.3.3 Methods -- 4.3.4 Results and discussion -- 4.4 Detection of the nipple -- 4.4.1 Overview of the methods -- 4.4.2 Dataset and experimental setup -- 4.4.3 Methods -- 4.4.4 Results and discussion -- 4.5 Extraction of the breast skin-line -- 4.5.1 Overview of the methods -- 4.5.2 Dataset and experimental setup -- 4.5.3 Methods -- 4.5.4 Results and discussion -- 4.6 Remarks --

5. Computer-aided detection of bilateral asymmetry -- 5.1 Patterns of asymmetry -- 5.2 Bilateral asymmetry in mammograms -- 5.3 State of the art -- 5.4 Overview of the methods -- 5.5 Dataset and experimental setup -- 5.6 TabĐar masking procedures -- 5.7 Extraction of directional components -- 5.8 Method 1: analysis of phase similarity -- 5.8.1 Calculation of rose diagrams -- 5.8.2 Computation of the angular similarity index -- 5.8.3 Pattern classification and cross-validation -- 5.8.4 Results and discussion -- 5.9 Method 2: analysis of spatial correlation -- 5.9.1 Computation of measures of spatial correlation -- 5.9.2 Pattern classification and cross-validation -- 5.9.3 Results and discussion -- 5.10 Method 3: analysis of structural similarity -- 5.10.1 Spherical semivariogram descriptors -- 5.10.2 Correlation-based structural similarity -- 5.10.3 Classification of mammograms as asymmetric or normal pairs -- 5.10.4 Results and discussion -- 5.11 Remarks --

6. Design of contour-independent features for classification of masses -- 6.1 Motivation -- 6.2 State of the art -- 6.3 Overview of the design studies -- 6.4 Study 1: design and performance analysis of radial features -- 6.4.1 Experimental setup -- 6.4.2 Methods -- 6.4.3 Results and discussion -- 6.5 Study 2: design and performance analysis of angular features -- 6.5.1 Experimental setup -- 6.5.2 Methods -- 6.5.3 Results and discussion -- 6.6 Remarks --

7. Integrated CADe/CADx of mammographic lesions -- 7.1 Motivation -- 7.2 State of the art -- 7.3 Overview of the integrated CADe/CADx system -- 7.4 Datasets and experimental setup -- 7.5 Methods -- 7.5.1 Preprocessing -- 7.5.2 Detection of suspicious focal areas -- 7.5.3 Extraction of directional components -- 7.5.4 Extraction of circular ROIs -- 7.5.5 Extraction of features for detection of lesions -- 7.5.6 Extraction of features for classification of lesions -- 7.5.7 Pattern classification and cross-validation -- 7.5.8 Performance evaluation -- 7.5.9 3D FROC framework -- 7.6 Results and comparative analysis -- 7.6.1 Initial performance assessment -- 7.6.2 Performance of classification -- 7.6.3 Comparative analysis -- 7.7 Discussion -- 7.8 Remarks --

Concluding remarks -- References -- Authors' biographies

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 TabĐar 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

Nur in Feld suchen:

Zuletzt gesuchte Begriffe: