Design of a High-Accuracy Classifier Based on Fisher Discriminant Analysis: Application to Computer-Aided Diagnosis of Microcalcifications

Hamdi, Nezha; Auhmani, Khalid; Hassani, Moha M’Rabet

doi:10.1109/iccsa.2008.43

Cited by 7 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, many researchers have contributed in the development and the growth of CAD systems. The researchers who have explored the area to distinguish malignant and benign microcalcifications have either used only the texture features [10][11][12][13][14][15][16][17], or a combination of texture and shape features [4,[18][19][20]. For extracting the shape-based features, some researchers have worked to extract shape and topology of individual microcalcifications [21,22].…”

Section: Literature Reviewmentioning

confidence: 99%

“…To distinguish benign and malignant microcalcifications, various researchers have proposed different approaches to compute texture features extracted from a region that contains microcalcifications. The most commonly used texture features are GLCM-based texture features [10,13,19], SGLD-based texture features [11], GLRLMbased texture features [10], LBP-based texture features [15], Gabor texture features [9,14] and wavelet-based texture features [19,20].…”

Section: 3bmentioning

confidence: 99%

See 1 more Smart Citation

An approach for classification of malignant and benign microcalcification clusters

Singh

Kaur

2018

Sādhanā

View full text Add to dashboard Cite

The only reliable and successful treatment of breast cancer is its detection through mammography at initial stage. Clusters of microcalcifications are important signs of breast cancer. Manual interpretation of mammographic images, in which the suspicious regions are indicated as areas of varying intensities, is not error free due to a number of reasons. These errors can be reduced by using computer-aided diagnosis systems that result in reduction of either false positives or true negatives. The purpose of the study in this paper is to develop a methodology for distinguishing malignant microcalcification clusters from benign microcalcification clusters. The proposed approach first enhances the region of interest by using morphological operations. Then, two types of features, cluster shape features and cluster texture features, are extracted. A Support Vector Machine is used for classification. A new set of shape features based on the recursive subsampling method is added to the feature set, which improves the classification accuracy of the system. It has been found that these features are capable of differentiating malignant and benign tissue regions. To investigate the performance of the proposed approach, mammogram images are taken from Digital Database for Screening Mammography database and an accuracy of 94.25% has been achieved. The experiments have shown that the proposed classification system minimizes the classification errors and is more efficient in correct diagnosis.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: 3bmentioning

confidence: 99%

An approach for classification of malignant and benign microcalcification clusters

Singh

Kaur

2018

Sādhanā

View full text Add to dashboard Cite

show abstract

“…The underlying principle of preprocessing is to enlarge the intensity difference between objects and background and to produce reliable representations of breast tissue structures. More details of the proposed preprocessing method can be found in [17,18].…”

Section: Frameworkmentioning

confidence: 99%

A New Approach Based on Quantum Clustering and Wavelet Transform for Breast Cancer Classification: Comparative Study

Hamdi

Auhmani

Hassani

2015

IJECE

Self Cite

View full text Add to dashboard Cite

Feature selection involves identifying a subset of the most useful features that produce the same results as the original set of features. In this paper, we present a new approach for improving classification accuracy. This approach is based on quantum clustering for feature subset selection and wavelet transform for features extraction. The feature selection is performed in three steps. First the mammographic image undergoes a wavelet transform then some features are extracted. In the second step the original feature space is partitioned in clusters in order to group similar features. This operation is performed using the Quantum Clustering algorithm. The third step deals with the selection of a representative feature for each cluster. This selection is based on similarity measures such as the correlation coefficient (CC) and the mutual information (MI). The feature which maximizes this information (CC or MI) is chosen by the algorithm. This approach is applied for breast cancer classification. The K-nearest neighbors (KNN) classifier is used to achieve the classification. We have presented classification accuracy versus feature type, wavelet transform and K neighbors in the KNN classifier. An accuracy of 100% was reached in some cases.

show abstract

“…al [7] combined shape, spectral, and GLCM features to classify microcalcifications using kernelbased support vector machine classifiers. Hamdi et al [8] classified MC clusters from MIAS database using GLCM and spectral features, feature selection using Fisher discriminate analysis (FDA), and a KNN classifier. Other studies [9], [10] demonstrated that it is not the texture of MCs objects but it the texture of breast tissue surrounding microcalcifications that can be useful for cancer diagnosis.…”

mentioning

confidence: 99%

Classification of Microcalcification Clusters via PSOKNN Heuristic Parameter Selection and GLCM Features

Zyout¹,

Abdel‐Qader²

2011

IJCA

View full text Add to dashboard Cite

Texture-based computer-aided diagnosis (CADx) of microcalcification clusters is more robust than the state-of-art shape-based CADx because the performance of shape-based approach heavily depends on the effectiveness of microcalcification (MC) segmentation. This paper presents a texture-based CADx that consists of two stages. The first one characterizes MC clusters using texture features from gray-level co-occurrence matrix (GLCM). In the second stage, an embedded feature selection based on particle swarm optimization and a knearest neighbor (KNN) classifier, called PSO-KNN, is applied to simultaneously determine the most discriminative GLCM features and to find the best k value for a KNN classifier. Testing the proposed CADx using 25 MC clusters from mini-MIAS dataset produced classification accuracy of 88% that obtained using 2 GLCM features.

show abstract

Design of a High-Accuracy Classifier Based on Fisher Discriminant Analysis: Application to Computer-Aided Diagnosis of Microcalcifications

Cited by 7 publications

References 32 publications

An approach for classification of malignant and benign microcalcification clusters

An approach for classification of malignant and benign microcalcification clusters

A New Approach Based on Quantum Clustering and Wavelet Transform for Breast Cancer Classification: Comparative Study

Classification of Microcalcification Clusters via PSOKNN Heuristic Parameter Selection and GLCM Features

Contact Info

Product

Resources

About