S. Tamil Selvi

Computer-aided detection of breast cancer on mammograms

Breast cancer is the second leading cause of cancer death in women. Accurate early detection can effectively reduce the mortality rate caused by breast cancer. Masses and microcalcification clusters are an important early signs of breast cancer. However, it is often difficult to distinguish abnormalities from normal breast tissues because of their subtle appearance and ambiguous margins. Computer aided diagnosis (CAD) helps the radiologist in detecting the abnormalities in an efficient way. This paper investigates a new classification approach for detection of breast abnormalities in digital mammograms using Particle Swarm Optimized Wavelet Neural Network (PSOWNN). The proposed abnormality detection algorithm is based on extracting Laws Texture Energy Measures from the mammograms and classifying the suspicious regions by applying a pattern classifier. The method is applied to real clinical database of 216 mammograms collected from mammogram screening centers. The detection performance of the CAD system is analyzed using Receiver Operating Characteristic (ROC) curve. This curve indicates the trade-offs between sensitivity and specificity that is available from a diagnostic system, and thus describes the inherent discrimination capacity of the proposed system. The result shows that the area under the ROC curve of the proposed algorithm is 0.96853 with a sensitivity 94.167% of and specificity of 92.105%.

Class-specific multiple classifiers scheme to recognize emotions from speech signals

The emotion recognition performances of AR parameters of different orders are investigated.AR reflection coefficients recognize emotions better than LPC.A new class-specific multiple classifiers scheme is proposed for speech emotion recognition.The proposed method utilizes a feature vector and a classifier for each emotion.The class-specific multiple classifiers scheme improves the recognition accuracy. Automatic emotion recognition from speech signals is one of the important research areas, which adds value to machine intelligence. Pitch, duration, energy and Mel-frequency cepstral coefficients (MFCC) are the widely used features in the field of speech emotion recognition. A single classifier or a combination of classifiers is used to recognize emotions from the input features. The present work investigates the performance of the features of Autoregressive (AR) parameters, which include gain and reflection coefficients, in addition to the traditional linear prediction coefficients (LPC), to recognize emotions from speech signals. The classification performance of the features of AR parameters is studied using discriminant, k-nearest neighbor (KNN), Gaussian mixture model (GMM), back propagation artificial neural network (ANN) and support vector machine (SVM) classifiers and we find that the features of reflection coefficients recognize emotions better than the LPC. To improve the emotion recognition accuracy, we propose a class-specific multiple classifiers scheme, which is designed by multiple parallel classifiers, each of which is optimized to a class. Each classifier for an emotional class is built by a feature identified from a pool of features and a classifier identified from a pool of classifiers that optimize the recognition of the particular emotion. The outputs of the classifiers are combined by a decision level fusion technique. The experimental results show that the proposed scheme improves the emotion recognition accuracy. Further improvement in recognition accuracy is obtained when the scheme is built by including MFCC features in the pool of features.

A Swarm Optimized Neural Network System for Classification of Microcalcification in Mammograms

Early detection of microcalcification clusters in breast tissue will significantly increase the survival rate of the patients. Radiologists use mammography for breast cancer diagnosis at early stage. It is a very challenging and difficult task for radiologists to correctly classify the abnormal regions in the breast tissue, because mammograms are noisy images. To improve the accuracy rate of detection of breast cancer, a novel intelligent computer aided classifier is used, which detects the presence of microcalcification clusters. In this paper, an innovative approach for detection of microcalcification in digital mammograms using Swarm Optimization Neural Network (SONN) is used. Prior to classification Laws texture features are extracted from the image to capture descriptive texture information. These features are used to extract texture energy measures from the Region of Interest (ROI) containing microcalcification (MC). A feedforward neural network is used for detection of abnormal regions in breast tissue is optimally designed using Particle Swarm Optimization algorithm. The proposed intelligent classifier is evaluated based on the MIAS database where 51 malignant, 63 benign and 208 normal images are utilized. The approach has also been tested on 216 real time clinical images having abnormalities which showed that the results are statistically significant. With the proposed methodology, the area under the ROC curve (Az) reached 0.9761 for MIAS database and 0.9138 for real clinical images. The classification results prove that the proposed swarm optimally tuned neural network highly contribute to computer-aided diagnosis of breast cancer.

Classification of malignant and benign microcalcification using SVM classifier

Breast Cancer is one of the frequent and leading causes of mortality among woman, especially in developed countries. Woman within the age of 40–69 have more risk of breast cancer. Though breast cancer leads to death, early detection of breast cancer can increase the survival rate. Clustered Microcalcification (MC) in mammograms is the major indication for early detection of breast cancer. MC is quiet tiny bits of calcium, and may show up in clusters or in patterns and is associated with extra cell activity in breast tissue. Usually, the extra cell growth is not cancerous, but sometimes tight clusters of microcalcification can indicate early breast cancer. Individual clusters are difficult to detect, hence an intelligent Computer Aided Detection (CAD) will help the radiologists in detecting the MC clusters in an easy and efficient way. In this paper, we present a new classification approach using Support Vector Machines (SVM) for detection of microcalcification clusters in digital mammograms. Classifying data is a common task in machine learning. SVM is a linear classifier which constructs a hyperplane or set of hyperplanes in an infinite dimensional space. The MC detection is formulated as a supervised learning problem and we apply SVM as a classifier to determine at each pixel location in the mammogram if the MC is present or not. To improve the classification rate Laws texture energy measures are taken from the image Region of interest (ROI). Once the features are computed for each ROI, they can be used as input to the SVM classifier. The method was applied to 322 digitized mammographic images from the MIAS database. Results shows that the classification performance of the proposed approach is superior when compared with several other classification approach discussed in the literature.

An Improved Decision Support System for Detection of Lesions in Mammograms Using Differential Evolution Optimized Wavelet Neural Network

In this paper, a computerized scheme for automatic detection of cancerous lesion in mammograms is examined. Breast lesions in mammograms are an area with an abnormality or alteration in the breast tissues. Diagnosis of these lesions at the early stage is a very difficult task as the cancerous lesions are embedded in normal breast tissue structures. This paper proposes a supervised machine learning algorithm – Differential Evolution Optimized Wavelet Neural Network (DEOWNN) for detection of tumor masses in mammograms. Differential Evolution (DE) is a population based optimization algorithm based on the principle of natural evolution, which optimizes real parameters and real valued functions. By utilizing the DE algorithm, the parameters of the Wavelet Neural Network (WNN) are optimized. To increase the detection accuracy a feature extraction methodology is used to extract the texture features of the abnormal breast tissues and normal breast tissues prior to classification. Then DEOWNN classifier is applied at the end to determine whether the given input data is normal or abnormal. The performance of the computerized decision support system is evaluated using a mini database from Mammographic Image Analysis Society (MIAS). The detection performance is evaluated using Receiver Operating Characteristic (ROC) curves. The result shows that the proposed algorithm has a sensitivity of 96.9% and specificity of 92.9%.

Development of Energy Efficient Clustering Protocol in Wireless Sensor Network Using Neuro-Fuzzy Approach.

Wireless sensor networks (WSNs) consist of sensor nodes with limited processing capability and limited nonrechargeable battery power. Energy consumption in WSN is a significant issue in networks for improving network lifetime. It is essential to develop an energy aware clustering protocol in WSN to reduce energy consumption for increasing network lifetime. In this paper, a neuro-fuzzy energy aware clustering scheme (NFEACS) is proposed to form optimum and energy aware clusters. NFEACS consists of two parts: fuzzy subsystem and neural network system that achieved energy efficiency in forming clusters and cluster heads in WSN. NFEACS used neural network that provides effective training set related to energy and received signal strength of all nodes to estimate the expected energy for tentative cluster heads. Sensor nodes with higher energy are trained with center location of base station to select energy aware cluster heads. Fuzzy rule is used in fuzzy logic part that inputs to form clusters. NFEACS is designed for WSN handling mobility of node. The proposed scheme NFEACS is compared with related clustering schemes, cluster-head election mechanism using fuzzy logic, and energy aware fuzzy unequal clustering. The experiment results show that NFEACS performs better than the other related schemes.

A CAD system for breast cancer diagnosis using modified genetic algorithm optimized artificial neural network

In this paper, a computerized scheme for automatic detection of cancerous tumors in mammograms has been examined. Diagnosis of breast tumors at the early stage is a very difficult task as the cancerous tumors are embedded in normal breast tissue structures. This paper proposes a supervised machine learning algorithm --- Modified Genetic Algorithm (MGA) tuned Artificial Neural Network for detection of tumors in mammograms. Genetic Algorithm is a population based optimization algorithm based on the principle of natural evolution. By utilizing the MGA, the parameters of the Artificial Neural Network (ANN) are optimized. To increase the detection accuracy a feature extraction methodology is used to extract the texture features of the cancerous tissues and normal tissues prior to classification. Then Modified Genetic Algorithm (MGA) tuned Artificial Neural Network classifier is applied at the end to determine whether a given input data is suspicious for tumor or not. The performance of our computerized scheme is evaluated using a database of 322 mammograms originated from MIAS databases. The result shows that the proposed algorithm has a recognition score of 97.8%.

Combined texture and shape features for content based image retrieval

Image retrieval refers to extracting desired images from a large database. The retrieval may be of text based or content based. Here content based image retrieval (CBIR) is performed. CBIR is a long standing research topic in the field of multimedia. Here features such as texture & shape are analyzed. Gabor filter is used to extract texture features from images. Morphological closing operation combined with Gabor filter gives better retrieval accuracy. The parameters considered are scale and orientation. After applying Gabor filter on the image, texture features such as mean and standard deviations are calculated. This forms the feature vector. Shape feature is extracted by using Fourier Descriptor and the centroid distance. In order to improve the retrieval performance, combined texture and shape features are utilized, because many features provide more information than the single feature. The images are extracted based on their Euclidean distance. The performance is evaluated using precision-recall graph.

Bio Inspired Swarm Algorithm for Tumor Detection in Digital Mammogram

Microcalcification clusters in mammograms is the significant early sign of breast cancer. Individual clusters are difficult to detect and hence an automatic computer aided mechanism will help the radiologist in detecting the microcalcification clusters in an easy and efficient way. This paper presents a new classification approach for detection of microcalcification in digital mammogram using particle swarm optimization algorithm (PSO) based clustering technique. Fuzzy C-means clustering technique, well defined for clustering data sets are used in combination with the PSO. We adopt the particle swarm optimization to search the cluster center in the arbitrary data set automatically. PSO can search the best solution from the probability option of the Social-only model and Cognition-only model. This method is quite simple and valid, and it can avoid the minimum local value. The proposed classification approach is applied to a database of 322 dense mammographic images, originating from the MIAS database. Results shows that the proposed PSO-FCM approach gives better detection performance compared to conventional approaches.

Reduction of four-wave mixing effect in WDM systems using hybrid modulation techniques

Four-wave mixing (FWM) effect has become a major problem in wavelength division multiplexing (WDM) systems which is due to the non-linear effects in the fiber. In this paper, Hybrid Modulation techniques are proposed for minimizing the FWM effect. The combination of different modulator is used and the performance is analyzed in a 32-channel wdm system based on Q-factor and Bit Error Rate and FWM product power. The simulation results show that MZ-DDMZ-AM reduction technique is more efficient.