Proceedings ArticleDOI
A neural-genetic algorithm for feature selection and breast abnormality classification in digital mammography
Ping Zhang,Brijesh Verma,Kuldeep Kumar +2 more
- Vol. 3, pp 2303-2308
Reads0
Chats0
TLDR
This work proposes a neural-genetic algorithm for feature selection in conjunction with neural network based classifier and combined the computer-extracted statistical features from the mammogram with the human-extraction features for classifying different types of small breast abnormalities.Abstract:
Digital mammography is one of the most suitable methods for early detection of breast cancer. In uses digital mammograms to find suspicious areas. However, it is very difficult to distinguish benign and malignant cases, especially for the small size lesions in the early stage of cancer. This is reflected in the high percentage of unnecessary biopsies that are performed and many deaths caused by late detection or misdiagnosis. A computer based feature selection and classification system can provide a second opinion to the radiologists. This work proposes a neural-genetic algorithm for feature selection in conjunction with neural network based classifier. It also combined the computer-extracted statistical features from the mammogram with the human-extracted features for classifying different types of small breast abnormalities. It obtained 90.5% accuracy rate for calcification cases and 87.2% for mass cases with difference feature subsets. The obtained results show that different types of breast abnormality should use different features for classification.read more
Citations
More filters
Journal ArticleDOI
Performing Feature Selection With Multilayer Perceptrons
E. Romero,J.M. Sopena +1 more
TL;DR: Experimental results indicate that the increase in the computational cost associated with retraining the network with every feature temporarily removed before computing the saliency is rewarded with a significant performance improvement, suggesting that forcing overtraining may be as useful as early stopping.
Journal ArticleDOI
Improving the Mann-Whitney statistical test for feature selection: An approach in breast cancer diagnosis on mammography
TL;DR: The experimental results indicated that uFilter method statistically outperformed the U-test method and it demonstrated similar, but not superior, performance than traditional feature selection methods (CHI2 discretization, IG, 1Rule and Relief).
Journal ArticleDOI
Novel network architecture and learning algorithm for the classification of mass abnormalities in digitized mammograms
TL;DR: The proposed approach has outperformed existing classification approaches in terms of classification accuracy, generalization and memorization abilities, number of iterations, and guaranteed training on a benchmark database.
Proceedings ArticleDOI
Bacteria Foraging Based Independent Component Analysis
TL;DR: It is observed that the proposed BFOICA algorithm overcomes the long standing permutation ambiguity and recovers the independent components in a fixed order which depends on the statistical characteristics of the signals to be estimated.
Journal ArticleDOI
Neural–Genetic Synthesis for State-Space Controllers Based on Linear Quadratic Regulator Design for Eigenstructure Assignment
TL;DR: A neural-genetic model based on the linear quadratic regulator design for the eigenstructure assignment of multivariable dynamic systems is presented, which represents a fusion of a genetic algorithm and a recurrent neural network to perform the selection of the weighting matrices and the Riccati equation solution.
References
More filters
Book ChapterDOI
Current Status of the Digital Database for Screening Mammography
Michael D. Heath,Kevin W. Bowyer,Daniel B. Kopans,W. Philip Kegelmeyer,Richard H. Moore,K.I. Chang,S. Munishkumaran +6 more
TL;DR: The Digital Database for Screening Mammography is a resource for use by researchers investigating mammogram image analysis, focused on the context of image analysis to aid in screening for breast cancer.
Proceedings Article
Feature subset selection using the wrapper method: overfltting and dynamic search space topology
Ron Kohavi,Dan Sommerfield +1 more
TL;DR: This work introduces compound operators that dynamically change the topology of the search space to better utilize the information available from the evaluation of feature subsets and shows that compound operators unify previous approaches that deal with relevant and irrelevant features.
Proceedings Article
Application of data mining techniques for medical image classification
TL;DR: This paper investigates the use of different data mining techniques, neural networks and association rule mining, for anomaly detection and classification, and shows that the two approaches performed well, obtaining a classification accuracy reaching over 70% percent for both techniques.
Journal ArticleDOI
Application of shape analysis to mammographic calcifications
TL;DR: A set of shape factors to measure the roughness of contours of calcifications in mammograms and for use in their classification as malignant or benign as well as for classification as benign or benign are developed.
Journal Article
Malignant and benign clustered microcalcifications : automated feature analysis and classification. authors' reply
G. A. P. De Kort,David Beijerinck,Jan J. M. Deurenberg,Yulei Jiang,Robert M. Nishikawa,Dulcy E. Wolverton,Robert A. Schmidt,Carl J. Vyborny +7 more
TL;DR: In this article, the authors developed a method for differentiating malignant from benign clustered microcifications in which image features are both extracted and analyzed by a computer, and the accuracy of computer analysis was statistically significantly better than that of five radiologists.
Related Papers (5)
Computer-aided detection and classification of microcalcifications in mammograms: a survey
A CAD system for the automatic detection of clustered microcalcifications in digitized mammogram films
Songyang Yu,Ling Guan +1 more