Mammographic Image Analysis Society Research Articles

An Optimized Feature Selection Method For Breast Cancer Diagnosis in Digital Mammogram using Multiresolution Representation

This paper introduces a method for feature extraction from multiresolution representations (wavelet,curvelet) for classification of digital mammograms. The proposed method selects the fe atures according to its capability to distinguish between different classes. The method starts with both performing wavelet and curvelet transform over mammogram images. The resulting coefficients of each image are used to construct a matrix. Each row in the matrix corresponds to an image.The most significant features, in terms of capabilities of differentiating classes,are selected. The method uses threshold values to select the columns that will maximize the difference between the different classes'representa tives. The proposed method is applied to the mammographic image analysis society (MIAS) dataset. The results calculated using 2x5-folds cross validation show that the proposed method is able to find an appropriate feature set that lead to significant improvement in c lassification accuracy.The obtained results were satisfactory and the performances of both wavelet and curvelet are presented and compared.

Fuzzy technique for microcalcifications clustering in digital mammograms.

BackgroundMammography has established itself as the most efficient technique for the identification of the pathological breast lesions. Among the various types of lesions, microcalcifications are the most difficult to identify since they are quite small (0.1-1.0 mm) and often poorly contrasted against an images background. Within this context, the Computer Aided Detection (CAD) systems could turn out to be very useful in breast cancer control.MethodsIn this paper we present a potentially powerful microcalcifications cluster enhancement method applicable to digital mammograms. The segmentation phase employs a form filter, obtained from LoG filter, to overcome the dependence from target dimensions and to optimize the recognition efficiency. A clustering method, based on a Fuzzy C-means (FCM), has been developed. The described method, Fuzzy C-means with Features (FCM-WF), was tested on simulated clusters of microcalcifications, implying that the location of the cluster within the breast and the exact number of microcalcifications are known.The proposed method has been also tested on a set of images from the mini-Mammographic database provided by Mammographic Image Analysis Society (MIAS) publicly available.ResultsThe comparison between FCM-WF and standard FCM algorithms, applied on both databases, shows that the former produces better microcalcifications associations for clustering than the latter: with respect to the private and the public database we had a performance improvement of 10% and 5% with regard to the Merit Figure and a 22% and a 10% of reduction of false positives potentially identified in the images, both to the benefit of the FCM-WF. The method was also evaluated in terms of Sensitivity (93% and 82%), Accuracy (95% and 94%), FP/image (4% for both database) and Precision (62% and 65%).ConclusionsThanks to the private database and to the informations contained in it regarding every single microcalcification, we tested the developed clustering method with great accuracy. In particular we verified that 70% of the injected clusters of the private database remained unaffected if the reconstruction is performed with the FCM-WF. Testing the method on the MIAS databases allowed also to verify the segmentation properties of the algorithm, showing that 80% of pathological clusters remained unaffected.

Pectoral Muscle Segmentation in Mammograms Based on Anatomic Features

In this paper, an anatomic features-based method is proposed to segment the pectoral muscle region according to texture feature and shape feature. Firstly, spectral clustering combined with edge information is presented and used to segment the pectoral muscle, leading to an over-segmented result. Afterwards, a region merging algorithm is proposed on the basis of the intensity distribution of regions and the characteristic of triangle shape. Finally, the pectoral muscle is identified from the over-segmented result according to region merging. The proposed method is evaluated on 322 mammograms from the mammographic image analysis society (mini-MIAS) database and 50 mammograms from the Breast Center of Peking University People s Hospital (BCPKUPH). The results show that the proposed method works well for pectoral muscles of different sizes, shapes and intensities.

Computer‐aided classification of breast masses in mammogram images based on spherical wavelet transform and support vector machines

AbstractBreast cancer can be effectively detected and diagnosed using the technology of digital mammography. However, although this technology has been rapidly developing recently, suspicious regions cannot be detected in some cases by radiologists, because of the noise or inappropriate mammogram contrast. This study presents a classification of segmented region of interests (ROIs) as either benign or malignant to serve as a second eye of the radiologists. Our study consists of three steps. In the first step, spherical wavelet transform (SWT) is applied to the original ROIs. In the second step, shape, boundary and grey level based features of wavelet (detail) and scaling (approximation) coefficients are extracted. Finally, in the third step, malignant/benign classification of the masses is implemented by giving the feature matrices to a support vector machine system. The proposed system achieves 91.4% and 90.1% classification accuracy using the dataset acquired from the hospital of Istanbul University in Turkey and the free Mammographic Image Analysis Society, respectively. Furthermore, discrete wavelet transform, which produces 83.3% classification accuracy, is applied to the coefficients to make a comparison with the SWT method.

A novel automatic suspicious mass regions identification using Havrda & Charvat entropy and Otsu's N thresholding

Mass detection is a very important process for breast cancer diagnosis and computer aided systems. It can be very complex when the mass is small or invisible because of dense breast tissue. Therefore, the extraction of suspicious mass region can be very challenging. This paper proposes a novel segmentation algorithm to identify mass candidate regions in mammograms. The proposed system includes three parts: breast region and pectoral muscle segmentation, image enhancement and suspicious mass regions identification. The first two parts have been examined in previous studies. In this study, we focused on suspicious mass regions identification using a combination of Havrda & Charvat entropy method and Otsu's N thresholding method. An open access Mammographic Image Analysis Society (MIAS) database, which contains 59 masses, was used for the study. The proposed system obtained a 93% sensitivity rate for suspicious mass regions identification in 56 abnormal and 40 normal images.

A fast and simple method for the visual enhancement of microcalcifications in digital mammograms based on mathematical morphology

A fast and simple method for the visual enhancement of small bright details in digital mam- mograms based on mathematical morphology is proposed. By a proper choice of the shape and size of the structuring element, an algorithm for a particular processing task - in this case, for the visual enhancement of microcalcifications in digital mammograms - was designed. The efficiency of the proposed algorithm was tested on publicly available mammograms from the mammographic image analysis society database. In all tested cases (23 mammograms), the proposed method successfully segmented and enhanced the existing microcalcifications, in- dependently verified by medical experts. The proposed procedure may be used both as a visual aid in clinical mammogram analysis or as a preprocessing step for further processing, such as segmentation, classification and detection of microcalcifications. Moreover, the algorithm is very fast and robust, thus applicable to real-time mammogram processing.

Performance evaluation of the wave atom algorithm to classify mammographic images

The most common type of cancer seen in women is breast cancer. To enable recovery from this severe disease, monitoring and early detection must be provided, and related precautions must be taken as a first step. During diagnosis, some cases may be overlooked due to fatigue and eyestrain, because the determination of abnormalities is a repetitive procedure. In this study, a computer-aided diagnosis (CAD) system, using the wave atom transform (WAT) algorithm and support vector machine (SVM), is proposed to evaluate mammography images. During the process, the region of interest (ROI) is defined before applying the method. The system includes a feature extraction approach based on the WAT algorithm. In terms of classification, the process has 2 main stages: the classification of normal/abnormal regions and malignant/benign ones. The proposed system also uses principle component analysis (PCA) for further dimensional reduction and feature selection. A dataset from the Mammographic Image Analysis Society database is employed for testing and measuring the performance of the proposed system. The best success rates in this work are obtained using the coefficients at scales of 1, 2, and 3, by employing SVM with PCA. The maximum classification success rate to define the regions of interest as normal/abnormal is 100%. The success rate of malignant/benign classification is also achieved as 100% in the tests. According to the results, it is observed that these features ensure important support for more comprehensive clinical investigations and the results are very encouraging when mammograms are categorized via WAT, PCA, and SVM.

A mass classification and image retrieval model for mammograms

In this paper, a breast tissue density classification and image retrieval model is studied and a model for the data reduction is presented. This model is based on two-directional two-dimensional principal component analysis ((2D)2PCA) technique, and a support vector machine (SVM) with the radial basis function (RBF) for mammographic images classification and retrieval. The model is formed based on breast density, according to the categories defined by the breast imaging-reporting and data system (BIRADS) which is a standard on the assessment of mammographic images and is tested on the Mammographic Image Analysis Society (MIAS) database. The five-fold cross-validation has been used for the parameters selection in SVM to avoid the over-fitting error in the data classification. The average precision rates of the model are in the range from 87·34% to 99·12%.

MASS CLASSIFICATION IN DIGITAL MAMMOGRAMS BASED ON DISCRETE SHEARLET TRANSFORM

The most significant health problem in the world is breast cancer and early detection is the key to predict it. Mammography is the most reliable method to diagnose breast cancer at the earliest. The classification of the two most findings in the digital mammograms, micro calcifications and mass are valuable for early detection. Since, the appearance of the masses are similar to the surrounding parenchyma, the classification is not an easy task. In this study, an efficient approach to classify masses in the Mammography Image Analysis Society (MIAS) database mammogram images is presented. The key features used for the classification is the energies of shearlet decomposed image. These features are fed into SVM classifier to classify mass/non mass images and also benign/malignant. The results demonstrate that the proposed shearlet energy features outperforms the wavelet energy features in terms of accuracy.

Texture feature extraction using gray level statistical matrix for content-based mammogram retrieval

Texture is one of the visual contents of an image used in content-based image retrieval (CBIR) to represent and index the image. Statistical textural representation methods characterize texture by the statistical distribution of the image intensity. This paper proposes a gray level statistical matrix from which four statistical texture features are estimated for the retrieval of mammograms from mammographic image analysis society (MIAS) database. The mammograms comprising architectural distortion, asymmetry, calcification, circumscribed, ill-defined, spiculated and normal classes are used in the experimentation. Precision, recall, retrieval rate, normalized average rank, average matching fraction, storage requirement and retrieval time are the performance measures used for the evaluation of retrieval performance. Using the proposed method, the highest mean precision rate obtained is 85.1 %. The results show that the proposed method outperforms the state-of-the-art texture feature extraction methods in mammogram retrieval problem.

Detection of Breast Cancer Cells by Using Texture Analysis

In Brief Breast cancer is a serious public health problem worldwide. This study presents a texture analysis approach to detect cancer on mammograms. Fifty-five regions of interest (ROIs) containing abnormal breast tissue and 192 ROIs containing normal breast tissue were extracted from digital mammograms obtained from the Mammographic Image Analysis Society database. Haralick texture features derived from spatial grey-level dependence matrix were calculated for each ROI. The importance of each feature in distinguishing abnormal from normal tissues was determined by stepwise linear discriminant analysis. The methodology obtained 92.7% of accuracy for the detection of abnormal tissue (cancer) on digitalized mammograms. Breast cancer is a serious public health problem worldwide. This study presents a texture analysis approach to detect cancer on mammograms.

Mammographical mass detection and classification using Local Seed Region Growing–Spherical Wavelet Transform (LSRG–SWT) hybrid scheme

The purpose of this study is to implement accurate methods of detection and classification of benign and malignant breast masses in mammograms. Our new proposed method, which can be used as a diagnostic tool, is denoted Local Seed Region Growing–Spherical Wavelet Transform (LSRG–SWT), and consists of four steps. The first step is homomorphic filtering for enhancement, and the second is detection of the region of interests (ROIs) using a Local Seed Region Growing (LSRG) algorithm, which we developed. The third step incoporates Spherical Wavelet Transform (SWT) and feature extraction. Finally the fourth step is classification, which consists of two sequential components: the 1st classification distinguishes the ROIs as either mass or non-mass and the 2nd classification distinguishes the masses as either benign or malignant using a Support Vector Machine (SVM). The mammograms used in this study were acquired from the hospital of Istanbul University (I.U.) in Turkey and the Mammographic Image Analysis Society (MIAS). The results demonstrate that the proposed scheme LSRG–SWT achieves 96% and 93.59% accuracy in mass/non-mass classification (1st component) and benign/malignant classification (2nd component) respectively when using the I.U. database with k-fold cross validation. The system achieves 94% and 91.67% accuracy in mass/non-mass classification and benign/malignant classification respectively when using the I.U. database as a training set and the MIAS database as a test set with external validation.

Mammographic Microcalcifications Detection using Discrete Wavelet Transform

cancer can be diagnosed with an early training course by detecting the presence of microcalcifications in screening mammograms. The multiresolution analysis using discrete wavelet transform presents characteristics which can be exploited to develop tools for detection of microcalcifications. The objective of this work is to study the best type of wavelet and the optimal level of decomposition for a better detection. The approach is divided into two phases. The first phase of the algorithm consists on multiresolution analysis based on 1-D discrete wavelet transform over profiles of microcalcifications extracted from mammographic images. This analysis is carried out with several families of wavelets. The second phase of the algorithm is interested in the validation of the results of the first. In this stage, we apply 2-D discrete wavelet transform in analysis and synthesis on screening mammograms extracted from the mini-MIAS database (Mammographic Image Analysis Society) in order to detect the microcalcifications.

Automated Abnormal Mass Detection in the Mammogram Images Using Chebyshev Moments

Breast cancer is the second leading cause of cancer mortality among women after lung cancer. Early diagnosis of this disease has a major role in its treatment. Thus the use of computer systems as a detection tool could be viewed as essential to helping with this disease. In this study a new system for automated mass detection in mammography images is presented as being more accurate and valid. After optimization of the image and extracting a better picture of the breast tissue from the image and applying log-polar transformation, Chebyshev moments can be calculated in all areas of breast tissue. Then after extracting effective features in the diagnosis of mammography images, abnormal masses, which are important for the physician and specialists, can be determined with applying the appropriate threshold. To check the system performance, images in the MIAS (Mammographic Image Analysis Society) mammogram database have been used and the results allowed us to draw a FROC (Free Response Receiver Operating Characteristic) curve. When compared the FROC curve with similar systems experts, the high ability of our system was confirmed. In this system, images of different thresholds, specifically 445, 450, 455 are processed and then put through a sensitivity analysis. The process garnered good results 100, 92 and 84%, respectively and a false positive rate per image 2.56, 0.86, 0.26, respectively have been calculated. Comparing other automatic mass detection systems, the proposed method has a few advantages over prior systems: Our process allows us to determine the amount of false positives and/or sensitivity parameters within the system. This can be determined by the importance of the detection work being done. The proposed system achieves 100% sensitivity and 2.56 false positive for every image.

Textural Feature Extraction and Classification of Mammogram Images using CCCM and PNN

This work presents and investigates the discriminatory capability of contourlet coefficient co- occurrence matrix features in the analysis of mammogram images and its classification. It has been revealed that contourlet transform has a remarkable potential for analysis of images representing smooth contours and fine geometrical structures, thus suitable for textural details. Initially the ROI (Region of Interest) is cropped from the original image and its contrast is enhanced using histogram equalization. The ROI is decomposed using contourlet transform and the co-occurrence matrices are generated for four different directions (θ=0°, 45°, 90° and 135°) and distance (d= 1 pixel). For each co-occurrence matrix a variety of second order statistical texture features are extracted and the dimensionality of the features is reduced using Sequential Floating Forward Selection (SFFS) algorithm. A PNN is used for the purpose of classification. For experimental evaluation, 200 images are taken from mini MIAS (Mammographic Image Analysis Society) database. Experimental results show that the proposed methodology is more efficient and maximum classification accuracy of 92.5% is achieved. The results prove that contourlet coefficient co-occurrence matrix texture features can be successfully applied for the classification of mammogram images. Keywords-Contourlet Transform, Mammogram, SFFS, PNN, ROI, MIAS

Detection of microcalcification clusters in digitized X-ray mammograms using unsharp masking and image statistics

A fully automated method for detecting microcalcification (MC) clusters in regions of interest (ROIs) extracted from digitized X-ray mammograms is proposed. In the first stage, an unsharp masking is used to perform the contrast enhancement of the MCs. In the second stage, the ROIs are decomposed into a 2-level contourlet representation and the reconstruction is obtained by eliminating the low-frequency subband in the second level. In the third stage, statistical textural features are extracted from the ROIs and they are classified using support vector machines. To test the performance of the method, 57 ROIs selected from the Mammographic Image Analysis Society's MiniMammogram database are used. The true positive and false positive rates are used to evaluate the performance of the classification, and the results are compared with those from other studies presented in the literature. The results show that the classification method of unsharp masking and low-band eliminated image statistics is convenient for MC cluster detection. In particular, a true positive rate of about 94% is achieved at the rate of 0.06 false positives per image.

A ROBUST APPROACH TO CLASSIFY MICROCALCIFICATION IN DIGITAL MAMMOGRAMS USING CONTOURLET TRANSFORM AND SUPPORT VECTOR MACHINE

Mammogram is the best available radiographic method to detect breast cancer in the early stage. However detecting a microcalcification clusters in the early stage is a tough task for the radiologist. Herein we present a novel approach for classifying microcalcification in digital mammograms using Nonsubsampled Contourlet Transform (NSCT) and Support Vector Machine (SVM). The classification of microcalcification is achieved by extracting the microcalcification features from the Contourlet coefficients of the image and the outcomes are used as an input to the SVM for classification. The system classifies the mammogram images as normal or abnormal and the abnormal severity as benign or malignant. The evaluation of the system is carried on using Mammography Image Analysis Society (MIAS) database. The experimental result shows that the proposed method provides improved classification rate.

Mammogram tumour classification using modified segmentation techniques

Sophisticated technologies in the field of medical electronics have helped to improve the lives of patients. In this work, an intelligent system for the identification of micro-calcification clusters in digitised mammograms is proposed. The proposed intelligent system consists of two stages: segmentation algorithm and a neural network/kernel system. The system was tested for mammogram images for the Mammographic Image Analysis Society and Digital Database for Screening Mammographic Databases. Different classifiers such as support vector machines, learning vector quantiser, radial basis function and back propagation neural network are used and tested. Support vector machine classifier outperforms other classifiers. The proposed system incorporates improved segmentation and better classification. The proposed intelligent system gives a better accuracy. The execution time is considerably low-befitting real-time applications. The application of the system can be used to identify tumours as benign or malignant.

A computer-aided diagnosis system for breast cancer detection by using a curvelet transform

The most common type of cancer among women worldwide is breast cancer. Early detection of breast cancer is very important to reduce the fatality rate. For the hundreds of mammographic images scanned by a radiologist, only a few are cancerous. While detecting abnormalities, some of them may be missed, as the detection of suspicious and abnormal images is a recurrent mission that causes fatigue and eyestrain. In this paper, a computer-aided diagnosis system using the curvelet transform (CT) algorithm is proposed for interpreting mammograms to improve the decision making. The purpose of this study is to develop a method for the characterization of the mammography as both normal and abnormal regions, and to determine its diagnostic performance to differentiate between malignant and benign ones. The multiresolution CT that was recently derived is used to differentiate among 200 mammograms: 50 malignant, 50 benign, and 100 normal. A support vector machine and the k-nearest neighbor algorithm are used as classifiers to build the diagnostic model and are also used for the principal component analysis and linear discriminant analysis for further dimensional reduction and feature selection. A dataset from the Mammographic Image Analysis Society database is used for testing the method.

Feature extraction method for breast cancer diagnosis in digital mammograms using multi-resolution transformations and SVM-fuzzy logic classifier

The paper comprises a pattern to study digital mammogram images, which is mainly oriented to the recognition of the malignant/benign masses, skin thickening and micro calcifications. Image processing algorithms, like multi-resolution transformations, are implemented to obtain vector coefficients; wherein, a matrix is obtained on the basis of wavelet coefficients. Texture features are extracted from the wavelet coefficients. Dynamic thresholds are applied to optimise the number of features, and achieve maximum classification accuracy rate. The SVM-fuzzy method is used to classify between normal and abnormal tissues. The fuzzy classifier is used for extracting geometrical features. Due to lack of generalisations, the neuro-fuzzy rule is integrated with a kernel SVM to form a support vector based on the neural network in handling the uncertainty information. We use the Mammographic Image Analysis Society MIAS standard data set for the study and training-set purpose. We obtain classification accuracy rates of about 93.9%, demonstrating the proposed method for contribution towards a successful diagnosis pattern for breast cancer.