Journal ArticleDOI
Mammogram segmentation by contour searching and massive lesion classification with neural network
Donato Cascio,Francesco Fauci,R. Magro,Giuseppe Raso,Roberto Bellotti,F. De Carlo,Sabina Tangaro,G. De Nunzio,Maurizio Quarta,G. Forni,A. Lauria,Maria Evelina Fantacci,Alessandra Retico,Giovanni Luca Masala,Pietro Oliva,S. Bagnasco,S.C. Cheran,E. L. Torres +17 more
- Vol. 53, Iss: 5, pp 2827-2833
TLDR
An algorithm for detecting masses in mammographic images acquired in several hospitals belonging to the MAGIC-5 collaboration by means of a ROI Hunter algorithm, without loss of meaningful information is presented.Abstract:
The mammography is the most effective procedure for an early diagnosis of the breast cancer. In this paper, an algorithm for detecting masses in mammographic images will be presented. The database consists of 3762 digital images acquired in several hospitals belonging to the MAGIC-5 collaboration (Medical Applications on a Grid Infrastructure Connection). A reduction of the whole image's area under investigation is achieved through a segmentation process, by means of a ROI Hunter algorithm, without loss of meaningful information. In the following classification step, feature extraction plays a fundamental role: some features give geometrical information, other ones provide shape parameters. Once the features are computed for each ROI, they are used as inputs to a supervised neural network with momentum. The output neuron provides the probability that the ROI is pathological or not. Results are provided in terms of ROC and FROC curves: the area under the ROC curve was found to be AZ=0.862plusmn0.007, and we get a 2.8 FP/Image at a sensitivity of 82%. This software is included in the CAD station actually working in the hospitals belonging to the MAGIC-5 Collaborationread more
Citations
More filters
Journal ArticleDOI
A review of automatic mass detection and segmentation in mammographic images.
Arnau Oliver,Jordi Freixenet,Joan Martí,Elsa Pérez,Josep Pont,Erika R. E. Denton,Reyer Zwiggelaar +6 more
TL;DR: The aim of this paper is to review existing approaches to the automatic detection and segmentation of masses in mammographic images, highlighting the key-points and main differences between the used strategies.
Journal ArticleDOI
A hybrid intelligent system for medical data classification
Manjeevan Seera,Chee Peng Lim +1 more
TL;DR: A hybrid intelligent system that consists of the Fuzzy Min-Max neural network, the Classification and Regression Tree, and the Random Forest model is proposed, and its efficacy as a decision support tool for medical data classification is examined.
Journal ArticleDOI
Automatic detection of lung nodules in CT datasets based on stable 3D mass-spring models
TL;DR: An advanced computerized method for the automatic detection of internal and juxtapleural nodules on low-dose and thin-slice lung CT scan and the use of the 3D AC model and the feature analysis based FPs reduction process constitutes an accurate approach to the segmentation and the classification of lung nodules.
Journal ArticleDOI
Detection of Suspicious Lesions by Adaptive Thresholding Based on Multiresolution Analysis in Mammograms
Kai Hu,Xieping Gao,Fei Li +2 more
TL;DR: A novel algorithm to detect suspicious lesions in mammograms that utilizes the combination of adaptive global thresholding segmentation and adaptive local thresholded segmentation on a multiresolution representation of the original mammogram is developed.
Journal ArticleDOI
A CAD system for nodule detection in low-dose lung CTs based on region growing and a new active contour model
Roberto Bellotti,F. De Carlo,G. Gargano,Sabina Tangaro,Donato Cascio,Ezio Catanzariti,P. Cerello,Sc Cheran,Pasquale Delogu,I. De Mitri,C. Fulcheri,Daniele Grosso,Alessandra Retico,Sandro Squarcia,E. Tommasi,Bruno Golosio +15 more
TL;DR: A computer-aided detection system for the selection of lung nodules in computer tomography (CT) images is presented, based on region growing (RG) algorithms and a new active contour model (ACM), able to draw the correct contour of the lung parenchyma and to include the pleural nodules.
References
More filters
Book
Neural Networks: A Comprehensive Foundation
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
Journal ArticleDOI
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
TL;DR: A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented and it is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a random chosen non-diseased subject.
Journal ArticleDOI
A method of comparing the areas under receiver operating characteristic curves derived from the same cases.
TL;DR: This paper refines the statistical comparison of the areas under two ROC curves derived from the same set of patients by taking into account the correlation between the areas that is induced by the paired nature of the data.
Journal ArticleDOI
REDUCTION IN MORTALITY FROM BREAST CANCER AFTER MASS SCREENING WITH MAMMOGRAPHY: Randomised Trial from the Breast Cancer Screening Working Group of the Swedish National Board of Health and Welfare
Laszlo Tabar,Laszlo Tabar,Laszlo Tabar,Adel Gad,Adel Gad,Adel Gad,L. H. Holmberg,L. H. Holmberg,L. H. Holmberg,U. Ljungquist,U. Ljungquist,U. Ljungquist,C.J.G Fagerberg,C.J.G Fagerberg,C.J.G Fagerberg,L. Baldetorp,L. Baldetorp,L. Baldetorp,O Gröntoft,O Gröntoft,O Gröntoft,B. Lundström,B. Lundström,B. Lundström,J. C. Månson,J. C. Månson,J. C. Månson,Gunnar Eklund,Gunnar Eklund,Gunnar Eklund,N.E Day,N.E Day,N.E Day,F. Pettersson,F. Pettersson,F. Pettersson +35 more
TL;DR: 7 years after the start of the study the excess of stage I cancers in the study group largely outweighs the deficit of advanced cancers, and the results to the end of 1984 show a 31% reduction in mortality from breast cancer and a 25% reduced in the rate of stage II or more advanced breast cancers.
Journal ArticleDOI
Analysis of cancers missed at screening mammography.
TL;DR: Analysis of 320 cancers found in a screened population between August 1985 and May 1990 revealed 77 cancers that were "missed" at screening mammography, which occurred in women with denser breasts, were less likely to demonstrate malignant microcalcifications, and were more likely to demonstrating a developing opacity as an indication of cancer.