P. Palanisamy

Analysis of nuclei textures of fine needle aspirated cytology images for breast cancer diagnosis using complex Daubechies wavelets

Breast cancer is the most frequent cause of cancer induced death among women in the world. Diagnosis of this cancer can be done through radiological, surgical, and pathological assessments of breas ...

Two-dimensional DOA estimation of coherent signals using acoustic vector sensor array

In this paper, we present two new methods for estimating two-dimensional (2-D) direction-of-arrival (DOA) of narrowband coherent (or highly correlated) signals using an L-shaped array of acoustic vector sensors. We decorrelate the coherency of the signals and reconstruct the signal subspace using cross-correlation matrix, and then the ESPRIT and propagator methods are applied to estimate the azimuth and elevation angles. The ESPRIT technique is based on the shift invariance property of array geometry and the propagator method is based on partitioning of the cross-correlation matrix. The propagator method is computationally efficient and requires only linear operations. Moreover, it does not require any eigendecomposition or singular-value decomposition as for the ESPRIT method. These two techniques are direct methods which do not require any 2-D iterative search for estimating the azimuth and the elevation angles. Simulation results are presented to demonstrate the performance of the proposed methods.

Wavelet based feature extraction method for breast cancer cytology images

Cancer of the breast is the most common cancer among women. Testing for detection of this cancer involves visual microscopic test of cytology samples such as Fine Needle Aspiration Cytology (FNAC). The result of analysis on this sample by Cyto-pathologist is crucial for breast cancer patient. In this paper, Complex wavelets are employed for multiscale image analysis to extract feature set for the description of Chromatin texture in the cytological diagnosis of invasive breast cancer. Finally, the obtained feature sets are used for training a k-nearest neighbor classifier so that it can classify malignant samples from benign, when given to it in the form of a feature set. The developed automatic classifier has been tested on FNAC samples of benign and malignant cases database and on an average 93.33% successful classification rate has been achieved.

An Expert Support System for Breast Cancer Diagnosis using Color Wavelet Features

Breast cancer diagnosis can be done through the pathologic assessments of breast tissue samples such as core needle biopsy technique. The result of analysis on this sample by pathologist is crucial for breast cancer patient. In this paper, nucleus of tissue samples are investigated after decomposition by means of the Log-Gabor wavelet on HSV color domain and an algorithm is developed to compute the color wavelet features. These features are used for breast cancer diagnosis using Support Vector Machine (SVM) classifier algorithm. The ability of properly trained SVM is to correctly classify patterns and make them particularly suitable for use in an expert system that aids in the diagnosis of cancer tissue samples. The results are compared with other multivariate classifiers such as Naïves Bayes classifier and Artificial Neural Network. The overall accuracy of the proposed method using SVM classifier will be further useful for automation in cancer diagnosis.

Detection and removal of Salt and Pepper noise in images by improved median filter

A methodology based on median filters for the removal of Salt and Pepper noise by its detection followed by filtering in both binary and gray level images has been proposed in this paper. Linear and nonlinear filters have been proposed earlier for the removal of impulse noise; however the removal of impulse noise often brings about blurring which results in edges being distorted and poor quality. Therefore the necessity to preserve the edges and fine details during filtering is the challenge faced by researchers today. The proposed method consists of noise detection followed by the removal of detected noise by median filter using selective pixels that are not noise themselves. The noise detection is based on simple thresholding of pixels. Computer simulations were carried out to analyse the performance of the proposed method and the results obtained were compared to that of conventional median filter and center weighted median (CWM) filter.

Speckle reduction in medical ultrasound images using an unbiased non-local means method

Abstract Enhancement of ultrasound (US) images is required for proper visual inspection and further pre-processing since US images are generally corrupted with speckle. In this paper, a new approach based on non-local means (NLM) method is proposed to remove the speckle noise in the US images. Since the interpolated final Cartesian image produced from uncompressed ultrasound data contaminated with fully developed speckle can be represented by a Gamma distribution, a Gamma model is incorporated in the proposed denoising procedure. In addition, the scale and shape parameters of the Gamma distribution are estimated using the maximum likelihood (ML) method. Bias due to speckle noise is expressed using these parameters and is removed from the NLM filtered output. The experiments on phantom images and real 2D ultrasound datasets show that the proposed method outperforms other related well-accepted methods, both in terms of objective and subjective evaluations. The results demonstrate that the proposed method has a better performance in both speckle reduction and preservation of structural features.

Enhancement and bias removal of optical coherence tomography images

Optical coherence tomography (OCT) has continually evolved and expanded as one of the most valuable routine tests in ophthalmology. However, noise (speckle) in the acquired images causes quality degradation of OCT images and makes it difficult to analyze the acquired images. In this paper, an iterative approach based on bilateral filtering is proposed for speckle reduction in multiframe OCT data. Gamma noise model is assumed for the observed OCT image. First, the adaptive version of the conventional bilateral filter is applied to enhance the multiframe OCT data and then the bias due to noise is reduced from each of the filtered frames. These unbiased filtered frames are then refined using an iterative approach. Finally, these refined frames are averaged to produce the denoised OCT image. Experimental results on phantom images and real OCT retinal images demonstrate the effectiveness of the proposed filter.

DIRECTION OF ARRIVAL ESTIMATION BASED ON FOURTH-ORDER CUMULANT USING PROPAGATOR METHOD

In this paper direction-of-arrival estimation (DOA) of multiple narrow-band sources, based on higher-order statistics using propagator, is presented. This technique uses fourth-order cumulants of the received array data instead of second-order statistics (auto- covariance) and then the so-called propagator approach is used to estimate the DOA of the sources. The propagator is a linear operator which only depends on the array steering vectors and which can be easily extracted from the received array data. But it does not require any eigendecomposition of the cumulant matrix of the received data like MUSIC algorithm. Computer simulations are carried out to compare the performance of the proposed method to those of methods based on auto-covariance using MUSIC and propagator algorithms.

Log-gabor wavelets based breast carcinoma classification using least square support vector machine

Breast cancer diagnosis can be done through the pathologic assessments of breast tissue samples such as core needle biopsy technique. Testing for detection of this cancer involves visual microscopic test of breast tissue samples. The result of analysis on this sample by pathologist is crucial for breast cancer patient. In this paper, nucleus of core needle biopsy samples are investigated after decomposition by means of the log-gabor wavelet transform and a novel method is developed to compute the complex color wavelet features based on the color textural information. These color textural features are used for breast cancer diagnosis using least square support vector machine (LS-SVM) classifier algorithm. The ability of properly trained least square support vector machine (LS-SVM) is to correctly classify patterns makes them particularly suitable for use in an expert system that aids in the diagnosis of cancer tissue samples. The overall accuracy of the proposed using LS-SVM classifier shows better result, which will be useful for automation in cancer diagnosis.

Complex wavelet as nucleus descriptors for automated cancer cytology classifier system using ANN

Breast cancer is the most frequent cancer and the most frequent cause of cancer induced death in women in the world. Diagnosis and prognosis of this cancer can be done through the radiological, surgical, and pathologic assessments of breast tissue samples. In developing countries, testing for detection of this cancer involves visual microscopic test of cytology samples such as Fine Needle Aspiration Cytology (FNAC) taken from the patients breast. The result of analysis on this sample by cyto-pathologist is crucial for breast cancer patient. In this paper, nucleus clusters of cells in the sub-band images of FNAC samples are investigated after decomposition by means of the complex discrete wavelet transform. From this a novel scheme is developed to compute the wavelet features based on the first and second order textural information of each color band. The ability of properly trained artificial neural networks to correctly classify and recognize patterns makes them particularly suitable for use in an expert system that aids in the diagnosis of cancer cytology images. Hence the extracted features are fed in to the artificial neural network as input for its classification task. The overall accuracy of classification of the proposed approach is 82.21%. The results of the analysis are found to be better than the previous study.