[Show abstract][Hide abstract] ABSTRACT: We present a comprehensive and fully automated system for computer-aided detection and diagnosis of masses in mammograms. Novel methods for detection include: selection of suspicious focal areas based on analysis of the gradient vector field, rejection of oriented components of breast tissue using multidirectional Gabor filtering, and use of differential features for rejection of false positives (FPs) via clustering of the surrounding fibroglandular tissue. The diagnosis step is based on extraction of contour-independent features for characterization of lesions as benign or malignant from automatically detected circular and annular regions. A new unified 3D free-response receiver operating characteristic framework is introduced for global analysis of two binary categorization problems in cascade. In total, 3,080 suspicious focal areas were extracted from a set of 156 full-field digital mammograms, including 26 malignant tumors, 120 benign lesions, and 18 normal mammograms. The proposed system detected and diagnosed malignant tumors with a sensitivity of 0.96, 0.92, and 0.88 at, respectively, 1.83, 0.46, and 0.45 FPs/image, with two stages of stepwise logistic regression for selection of features, a cascade of Fisher linear discriminant analysis and an artificial neural network with radial basis functions, and leave-one-patient-out cross-validation.
[Show abstract][Hide abstract] ABSTRACT: In this paper, a novel approach for classification of breast masses is presented that quantifies the texture of masses without relying on accurate extraction of their contours. Two novel feature descriptors based on 2D extensions of the reverse arrangement (RA) and Mantel's tests were designed for this purpose. Measures of radial correlation and radial trend were extracted from the original gray-scale values as well as from the Gabor magnitude response of 146 regions of interest, including 120 benign masses and 26 malignant tumors. Four classifiers, Fisher-linear discriminant analysis, Bayesian, support vector machine, and an artificial neural network based on radial basis functions (ANN-RBF), were employed to predict the diagnosis, using stepwise logistic regression for feature selection and the leave-one-patient-out method for cross-validation. The ANN-RBF resulted in an area under the receiver operating characteristic curve of 0.93. The experimental results show the effectiveness of the proposed approach.
No preview · Article · Jul 2013 · Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
[Show abstract][Hide abstract] ABSTRACT: Automatic detection of the nipple in mammograms is an important step in computerized systems that combine multiview information for accurate detection and diagnosis of breast cancer. Locating the nipple is a difficult task owing to variations in image quality, presence of noise, and distortion and displacement of the breast tissue due to compression. In this work, we propose a novel Hessian-based method to locate automatically the nipple in screen-film and full-field digital mammograms (FFDMs). The method includes detection of a plausible nipple/retroareolar area in a mammogram using geometrical constraints, analysis of the gradient vector field by mean and Gaussian curvature measurements, and local shape-based conditions. The proposed procedure was tested on 566 mammographic images consisting of 372 randomly selected scanned films from two public databases (mini-MIAS and DDSM), and 194 digital mammograms acquired with a GE Senographe 2000D FFDM system. A radiologist independently marked the centers of the nipples for evaluation of the results. The average error obtained was 6.7 mm (22 pixels) with reference to the center of the nipple as identified by the radiologist. Only two out of the 566 detected nipples (0.35 %) had an error larger than 50 mm. The method was also directly compared with two other techniques for the detection of the nipple. The results indicate that the proposed method outperforms other algorithms presented in the literature and can be used to identify accurately the nipple on various types of mammographic images.
No preview · Article · Mar 2013 · Journal of Digital Imaging
[Show abstract][Hide abstract] ABSTRACT: We present new feature descriptors specifically designed to quantify angular nonstationarity and angular dependence of pixel values in sectors of mammographic lesions. A key novelty of this work is that the proposed measures characterize the texture of masses without relying on accurate determination of their contours. An artificial neural network based on radial basis functions was used to predict the diagnosis of 120 benign masses and 26 malignant tumors in a database of full-field digital mammograms. Features were selected using stepwise logistic regression and the leave-one-patient-out method was used for cross-validation of results. An area under the receiver operating characteristic curve of 0.9890 ± 0.0114 was obtained using randomly selected centroids and an expected size of the masses. Results indicate that the use of the proposed contour-independent features can be an effective approach for computer-aided classification of mammographic lesions.
[Show abstract][Hide abstract] ABSTRACT: In this work we propose a joint two-side masking procedure for automatic analysis of mammographic images. The primary objective is the improvement of computerized systems capability in revealing additional findings, as the asymmetrical changes of the breast parenchyma. The method allows the proper comparison of the left and right breast by progressive selection of paired small areas on the mammogram, primarily the so-called "forbidden areas", zones that need special attention in mammographic interpretation. The masking of specific areas of the mammogram requires the identification of two anatomical structures of the breast: the pectoral muscle and the nipple used, together with the breast skin line, to find paired matching points on the images for comparison. With this purpose, specific algorithms have been developed. In particular, a new method for nipple extraction will be presented and validated by expert radiologists, by the use of a proprietary program developed by the authors. Finally, an application example of the automatic Tabar masking procedure will be shown, in order to point out the potential of this method in detection of suspicious areas in mammograms.
[Show abstract][Hide abstract] ABSTRACT: In this paper, we propose a novel approach for the automatic breast boundary segmentation using spatial fuzzy c-means clustering and active contours models. We will evaluate the performance of the approach on screen film mammographic images digitized by specific scanner devices and full-field digital mammographic images at different spatial and pixel resolutions. Expert radiologists have supplied the reference boundary for the massive lesions along with the biopsy proven pathology assessment. A performance assessment procedure will be developed considering metrics such as precision, recall, F-measure, and accuracy of the segmentation results. A Montecarlo simulation will be also implemented to evaluate the sensitivity of the boundary extracted on the initial settings and on the image noise.
[Show abstract][Hide abstract] ABSTRACT: This study sought to evaluate the accuracy of vacuum-assisted biopsy (VAB) in the diagnosis of atypical ductal hyperplasia (ADH) by determining the rate of VAB underestimation compared with definitive histology. In addition, an attempt was made to identify parameters that could help determine the most appropriate patient management.
We retrospectively reviewed 1,776 VAB procedures performed between November 1999 and January 2008 for suspicious subclinical breast lesions visible only at mammography. A total of 177 patients with a VAB diagnosis of pure ADH were studied. Patients with a diagnosis of ADH associated with other lesions (lobular intraepithelial neoplasia, papilloma), atypical lobular hyperplasia, lobular carcinoma in situ and any lesions with a microhistological diagnosis other than ADH were excluded. Mammographic appearance of lesions was as follows: 152 mostly clustered microcalcifications (86%); five opacities with microcalcifications (3%); 12 single opacities (3%); and eight parenchymal distortions (4%), of which five were without and three were with microcalcifications. In cases underestimated by VAB, we evaluated the extent of ADH within ducts and lobules. Based on results, patients were subdivided into two groups: ≤2 ADH foci; >2 ADH foci. Patients were subdivided into two groups: one was referred for surgery and the other for follow-up care. The decision to either perform or not perform surgery was based on combined analysis of the following parameters: patient age; risk factors in the patient's history; mammographic extent of microcalcifications; complete excision of microcalcifications at VAB; and final Breast Imaging Reporting and Data System (BI-RADS) assessment.
In the first group (n=98), comparison of microhistology with final histology revealed that 19 cases of ADH had been underestimated by VAB. In the second group (n=79), six cases of ADH showed progression of the mammographic abnormality, which was subsequently confirmed by surgical biopsy.
The most relevant parameters affecting the decision to proceed to surgical excision were lesion diameter >7 mm on mammography, >2 ADH foci, incomplete removal of the calcifications and a family and/or personal history of breast cancer. Although there are no definite mammographic predictors of malignancy, a radiological assessment of suspicious lesion in the presence of an additional equivocal parameter always warrants surgical management.
No preview · Article · Mar 2011 · La radiologia medica
[Show abstract][Hide abstract] ABSTRACT: We report on a morphological study of 192 breast masses as seen in mammograms, with the aim of discrimination between benign masses and malignant tumors. From the contour of each mass, we computed the fractal dimension (FD) and a few shape factors, including compactness, fractional concavity, and spiculation index. We calculated FD using four different methods: the ruler and box-counting methods applied to each 2-dimensional (2D) contour and its 1-dimensional signature. The ANOVA test indicated statistically significant differences in the values of the various shape features between benign masses and malignant tumors. Analysis using receiver operating characteristics indicated the area under the curve, A(z), of up to 0.92 with the individual shape features. The combination of compactness, FD with the 2D ruler method, and the spiculation index resulted in the highest A(z) value of 0.93.
No preview · Article · Aug 2010 · Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference