Fatemeh Saki

Classification of benign and malignant masses based on Zernike moments

In mammography diagnosis systems, high False Negative Rate (FNR) has always been a significant problem since a false negative answer may lead to a patients death. This paper is directed towards the development of a novel Computer-aided Diagnosis (CADx) system for the diagnosis of breast masses. It aims at intensifying the performance of CADx algorithms as well as reducing the FNR by utilizing Zernike moments as descriptors of shape and margin characteristics. The input Regions of Interest (ROIs) are segmented manually and further subjected to a number of preprocessing stages. The outcomes of preprocessing stage are two processed images containing co-scaled translated masses. Besides, one of these images represents the shape characteristics of the mass, while the other describes the margin characteristics. Two groups of Zernike moments have been extracted from the preprocessed images and applied to the feature selection stage. Each group includes 32 moments with different orders and iterations. Considering the performance of the overall CADx system, the most effective moments have been chosen and applied to a Multi-layer Perceptron (MLP) classifier, employing both generic Back Propagation (BP) and Opposition-based Learning (OBL) algorithms. The Receiver Operational Characteristics (ROC) curve and the performance of resulting CADx systems are analyzed for each group of features. The designed systems yield Az=0.976, representing fair sensitivity, and Az=0.975 demonstrating fair specificity. The best achieved FNR and FPR are 0.0% and 5.5%, respectively.

Fast opposite weight learning rules with application in breast cancer diagnosis

Classification of breast abnormalities such as masses is a challenging task for radiologists. Computer-aided Diagnosis (CADx) technology may enhance the performance of radiologists by assisting them in classifying patterns into benign and malignant categories. Although Neural Networks (NN) such as Multilayer Perceptron (MLP) have drawbacks, namely long training times, a considerable number of CADx systems employ NN-based classifiers. The reason being that they provide high accuracy when they are appropriately trained. In this paper, we introduce three novel learning rules called Opposite Weight Back Propagation per Pattern (OWBPP), Opposite Weight Back Propagation per Epoch (OWBPE), and Opposite Weight Back Propagation per Pattern in Initialization (OWBPI) to accelerate the training procedure of an MLP classifier. We then develop CADx systems for the diagnosis of breast masses employing the traditional Back Propagation (BP), OWBPP, OWBPE and OWBPI algorithms on MLP classifiers. We quantitatively analyze the accuracy and convergence rate of each system. The results suggest that the convergence rate of the proposed OWBPE algorithm is more than 4 times faster than that of the traditional BP. Moreover, the CADx systems which use OWBPE classifier on average yield an area under Receiver Operating Characteristic (ROC), i.e. Az, of 0.928, a False Negative Rate (FNR) of 9.9% and a False Positive Rate (FPR) of 11.94%.

A novel opposition-based classifier for mass diagnosis in mammography images

In this paper, a novel opposition-based classifier has been developed which classifies breast masses into benign and malignant categories. An MLP network with a novel learning rule, called Opposite Weighted Back Propagation (OWBP), has been utilized as the classifier. The objective is increasing the convergence rate of MLP learning rules as well as improving the mass diagnostic performance. The input ROI, which is a suspected part of mammogram, is segmented manually by expert radiologists and subjected to some preprocessing stages such as histogram equalization, translation and scaling. Then, a group of features which are appropriate descriptors of mass shape, margin and density have been extracted from the preprocessed ROIs. The proposed features include circularity, Zernike moments, contrast, average gray level, NRL derivatives and SP. The proposed classifier has been trained with both traditional BP and OWBP learning rules and the performance have been evaluated. The system which utilizes OWPB learning rule yields a significantly faster training time than BP algorithm while the Az of the resulting CADx system is 0.944.

Mass diagnosis in mammography images using novel FTRD features

In this paper, a novel group of features have been introduced for diagnosing the masses in mammography images. The goal is increasing the performance of CADx algorithms as well as decreasing computational complexity. The proposed features are proper descriptors of mass margin which are called Fourier Transform of Radial Distance (FTRD). The input ROI has been segmented manually by expert radiologists and subjected to some preprocessing stages. In order to extract the proposed features, the Radial Distance (RD) vectors of masses have been extracted. In addition, the zero padding method has been utilized to equalize the length of the RD vectors. Then, the resulting vectors are transformed to the frequency domain. It is shown that the magnitude response of FTRD vectors can be appropriate descriptors of the mass margin. Furthermore, in order to make a trade-off between the computational complexity and performance of the overall system, several groups of FTRD features with different lengths have been chosen and applied to an MLP classifier. Finally, the ROC curves have been plotted for each group of features and the performances have been evaluated. The most effective system yields an Az which is equal to 0.98. Moreover, the best achieved FPR is 5.56%.

Background noise classification using random forest tree classifier for cochlear implant applications

This paper presents improvements made to the previously developed noise classification path of the environment-adaptive cochlear implant speech processing pipeline. These improvements consist of the utilization of subband noise features together with a random forest tree classifier. Three commonly encountered noise environments of babble, street, and machinery are considered. The results using actual noise signals indicate that this classification method provides 10% improvement in the overall classification rate compared to the previously developed classification while maintaining the real-time implementation aspect of the entire speech processing pipeline.

A novel breast mass diagnosis system based on Zernike moments as shape and density descriptors

In this paper, a novel Computer-aided Diagnosis (CADx) system has been proposed for mass diagnosis in mammography images. Zernike moments are utilized as descriptors of shape and density characteristics in order to improve the overall accuracy. The input Regions of Interest (ROI) are segmented and subjected to some preprocessing stages. The outcome of preprocessing stage is a gray-scale image containing co-scaled translated mass which contains both shape and density characteristics of the mass. Two groups of Zernike moments have been extracted from the preprocessed images. Considering the performance of the overall system the most effective moments have been chosen and applied to a Multi-layer Perceptron (MLP) classifier. The Receiver Operational Characteristics (ROC) plot and the performance of overall CADx system are analyzed for each group of features. The average achieved area under ROC curve (Az) and False Positive Rate (FPR) for high-order moments are 0.872 and 18.34%, respectively. Besides, for low-order moments those are equal to 0.824 and 15.44%, respectively.

An effective breast mass diagnosis system using Zernike moments

In this paper, a novel CADx system has been proposed for the diagnosis of masses in mammography images. The objective is intensifying the performance of CADx algorithms as well as reducing the false positive rate by utilizing Zernike moments as descriptors of shape and margin characteristics. The input ROI is segmented manually by expert radiologists. Then, it is subjected to some preprocessing stages such as histogram equalization, translation, and NRL scaling. The outcome of preprocessing stage is two processed images containing co-scaled translated masses. Besides, one of these images represents the shape characteristics of the mass, while the other describes the margin characteristics. Two groups of Zernike moments have been extracted from the preprocessed images and proceeded to the feature selection stage. Each group includes 32 moments with different orders and iterations. Considering the performance of the overall CADx system, the most effective 32 moments have been chosen and applied to a multi-layer Perceptron classifier. The ROC plot and the performance of overall CADx system are analyzed for each group of features. The designed systems yield Az = 0.976 and 0.975 which represent fair sensitivity and fair specificity, respectively. The best achieved FPR is 5.5%.

Online frame-based clustering with unknown number of clusters

This paper presents an online frame-based clustering algorithm (OFC) for unsupervised classification applications in which data are received in a streaming manner as time passes by with the number of clusters being unknown. This algorithm consists of a number of steps including density-based outlier removal, new cluster generation, and cluster update. It is designed for applications when data samples are received in an online manner in frames. Such frames are first passed through an outlier removal step to generate denoised frames with consistent data samples during transitions times between clusters. A classification step is then applied to find whether frames belong to any of existing clusters. When frames do not get matched to any of existing clusters and certain criteria are met, a new cluster is created in real time and in an on-the-fly manner by using support vector domain descriptors. Experiments involving four synthetic and two real datasets are conducted to show the performance of the introduced clustering algorithm in terms of cluster purity and normalized mutual information. Comparison results with similar clustering algorithms designed for streaming data are also reported exhibiting the effectiveness of the introduced online frame-based clustering algorithm. Online frame-based clustering algorithm without having any knowledge of number of clusters.For applications when samples of a class appear in streaming frames.Superior to existing algorithms applicable to online frame-based clustering.

Real-Time Unsupervised Classification of Environmental Noise Signals

This paper presents a real-time unsupervised classification of environmental noise signals without knowing the number of noise classes or clusters. A previously developed online frame-based clustering algorithm is modified by adding feature extraction, a smoothing step and a fading step. The developed unsupervised classification or clustering is examined in terms of purity of clusters and normalized mutual information. The results obtained for actual noise signals exhibit the effectiveness of the introduced unsupervised classification in terms of both classification outcome and computational efficiency.

Smartphone-based real-time classification of noise signals using subband features and random forest classifier

This paper presents the real-time implementation and field testing of an app running on smartphones for classifying noise signals involving subband features and a random forest classifier. This app is compared to a previously developed app utilizing mel-frequency cepstral coefficients features and a Gaussian mixture model classifier. The real-time implementation has been carried out on both the Android and iOS smartphones. The field testing results indicate the superiority of this newly developed app over the previously developed app in terms of classification rates.