Computerized detection of breast masses in digitized mammograms

Varela, Celia; Tahoces, Pablo G.; Méndez, Adriana; Souto, Miguel Abel; Vidal, José Martı́nez

doi:10.1016/j.compbiomed.2005.12.006

Cited by 108 publications

(42 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With SVM classifier sensitivity increases up to moments of order 20, but decreases with high-order moments. Table 3 compares [46] Gray level, BPN Private 94 % Sensitivity contour-related, and morphological Polakowski et al [36] Size, shape, MLP Private 92 % TPR/FPR and texture the classification rates of both the classifiers with different orders of Zernike moments on the two datasets. All results of k-NN classifier are generated with k = 10.…”

Section: Experiments Resultsmentioning

confidence: 99%

Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

Sharma

Khanna

2014

J Digit Imaging

View full text Add to dashboard Cite

This work is directed toward the development of a computer-aided diagnosis (CAD) system to detect abnormalities or suspicious areas in digital mammograms and classify them as malignant or nonmalignant. Original mammogram is preprocessed to separate the breast region from its background. To work on the suspicious area of the breast, region of interest (ROI) patches of a fixed size of 128 × 128 are extracted from the original large-sized digital mammograms. For training, patches are extracted manually from a preprocessed mammogram. For testing, patches are extracted from a highly dense area identified by clustering technique. For all extracted patches corresponding to a mammogram, Zernike moments of different orders are computed and stored as a feature vector. A support vector machine (SVM) is used to classify extracted ROI patches. The experimental study shows that the use of Zernike moments with order 20 and SVM classifier gives better results among other studies. The proposed system is tested on Image Retrieval In Medical Application (IRMA) reference dataset and Digital Database for Screening Mammography (DDSM) mammogram database. On IRMA reference dataset, it attains 99 % sensitivity and 99 % specificity, and on DDSM mammogram database, it obtained 97 % sensitivity and 96 % specificity. To verify the applicability of Zernike moments as a fitting texture descriptor, the performance of the proposed CAD system is compared with the S. Sharma · P. Khanna ( ) Pandit Dwarka Prasad Mishra Indian Institute of Information Technology, Design and Manufacturing Jabalpur, Dumna Airport Road, P.O.: Khamaria, Jabalpur, Madhya Pradesh 482 005, India e-mail: pkhanna@iiitdmj.ac.in S. Sharma e-mail: shubhi.sharma@iiitdmj.ac.in other well-known texture descriptors namely gray-level cooccurrence matrix (GLCM) and discrete cosine transform (DCT).

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

Sharma

Khanna

2014

J Digit Imaging

View full text Add to dashboard Cite

show abstract

“…The features extracted give the property of the texture, and are keep in knowledge base. [1]. the extracted features are compare with the unknown sample means the…”

Section: Feature Extractionmentioning

confidence: 99%

WACO for Mammogram Classification

Kumari¹,

Sowrya²

2016

IJCA

View full text Add to dashboard Cite

Breast cancer is one of the ruinous diseases causing more number of deaths in women. Many efforts are being made to develop efficient techniques to identify the breast cancer at early stage. This paper implements weaver ant colony optimization (WACO) for classifying mammograms. The behavior of weaver ants' to bind the neurons between the layer to make the path to find the output of Neural Network(NN). The unique nest building behavior of Weaver ants' made a considerable remark, NN have proved to be one of the best methods for classification & WACO is used for optimized pathfinding. Each layer of NN is considered as one leaf and the leaves are divided into as many portions equal to the number of neurons,& let ants connect portion of leaf from one layer to another, makes the weight connection in the NN. The task is accomplished by using a NN with a back propagation technique (BPT). To determine the usefulness of WACO based Neural Network (NN)closed nests building behavior made us change the architecture of BPN. Weaver ants show indirect message between ants to find the shortest path between their nest and food sources. These ants ability is to construct nests by weaving together leaves using larval silk .Local Binary Pattern is a method which can be used extract the features for identifying the breast cancer abnormality by mammogram. Multilayer perceptron (MLP) and support vector machine for mammogram classification and mammogram images are preprocessed to reduce noise and detect the background of the mammogram to extract the required features. This paper implements WACO for classifying mammograms. Here we used MIAS database which describes the mammogram is in which stage benign or normal stage

show abstract

“…The over-sampling ratio is set to 200%. For the other three comparative methods, five types of features (a total of 20 features) are extracted for each ROI: iris filter descriptors, gray level descriptors, texture descriptors, contour-related descriptors, and morphological descriptors [15].…”

Section: Evaluating the Ssrbm For Few Labeled Mass Candidatesmentioning

confidence: 99%

Restricted Boltzmann machines based oversampling and semi-supervised learning for false positive reduction in breast CAD

Cao

Liu

Bao

et al. 2015

BME

View full text Add to dashboard Cite

Abstract. The false-positive reduction (FPR) is a crucial step in the computer aided detection system for the breast. The issues of imbalanced data distribution and the limitation of labeled samples complicate the classification procedure. To overcome these challenges, we propose oversampling and semi-supervised learning methods based on the restricted Boltzmann machines (RBMs) to solve the classification of imbalanced data with a few labeled samples. To evaluate the proposed method, we conducted a comprehensive performance study and compared its results with the commonly used techniques. Experiments on benchmark dataset of DDSM demonstrate the effectiveness of the RBMs based oversampling and semi-supervised learning method in terms of geometric mean (G-mean) for false positive reduction in Breast CAD.

show abstract

Computerized detection of breast masses in digitized mammograms

Cited by 108 publications

References 23 publications

Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

Computer-Aided Diagnosis of Malignant Mammograms using Zernike Moments and SVM

WACO for Mammogram Classification

Restricted Boltzmann machines based oversampling and semi-supervised learning for false positive reduction in breast CAD

Contact Info

Product

Resources

About