Harsa Amylia Mat Sakim

DNA ploidy and cell cycle distribution of breast cancer aspirate cells measured by image cytometry and analyzed by artificial neural networks for their prognostic significance

Chromosomal abnormalities are commonly associated with cancer, and their importance in the pathogenesis of the disease has been well recognized. Also recognized in recent years is the possibility that, together with chromosomal abnormalities, DNA ploidy of breast cancer aspirate cells, measured by image cytometric techniques, may correlate with prognosis of the disease. Here, we have examined the use of an artificial neural network to predict: 1) subclinical metastatic disease in the regional lymph nodes and 2) histological assessment, through the analysis of data obtained by image cytometric techniques of fine needle aspirates of breast tumors. The cellular features considered were: 1) DNA ploidy measured in terms of nuclear DNA content as well as by cell cycle distribution; 2) size of the S-phase fraction; and 3) nuclear pleomorphism. A further objective of the study was to analyze individual markers in terms of impact significance on predicting outcome in both cases. DNA ploidy, indicated by cell cycle distribution, was found markedly to influence the prediction of nodal spread of breast cancer, and nuclear pleomorphism to a lesser degree. Furthermore, a comparison between histological assessment and artificial neural network prediction shows a closer correlation between the neural approach and the development of further metastases as indicated in subsequent follow-up, than does histological assessment.

Medical image fusion scheme using complex contourlet transform based on PCA

We present an efficient method for the fusion of medical captured images using different modalities that enhances the original images and combines the complementary information of the various modalities. The contourlet transform has mainly been employed as a fusion technique for images obtained from equal or different modalities. The limitation of directional information of dual-tree complex wavelet (DT-CWT) is rectified in dual-tree complex contourlet transform (DT-CCT) by incorporating directional filter banks (DFB) into the DT-CWT. The DT-CCT produces images with improved contours and textures, while the property of shift invariance is retained. To improve the fused image quality, we propose a new method for fusion rules based on principle component analysis (PCA) which depend on frequency component of DT-CCT coefficients (contourlet domain). For low frequency components, PCA method is adopted and for high frequency components, the salient features are picked up based on local energy. The final fusion image is obtained by directly applying inverse dual tree complex contourlet transform (IDT-CCT) to the fused low and high frequency components. The experimental results showed that the proposed method produces fixed image with extensive features on multimodality.

An efficient medical image fusion method using contourlet transform based on PCM

An efficient medical image fusion method has been proposed based on contourlet transform and multi fusion rules. The multimodal medical images were first decomposed using the contourlet transform then fusion rules were applied to low frequency components and high frequency components of contourlet coefficients. For low frequency components principle component analysis (PCA) method was adopted. While for high frequency components region based contourlet contrast was adopted. The final fusion image is obtained by directly applying inverse contourlet transform to the fused low and high frequency components. Using four image quality indicators experimental results showed that the proposed method give extensive fused image on multimodality CT/MRI.

Density based breast segmentation for mammograms using graph cut techniques

In this work we explore the application of graph cuts techniques to the problem of finding the boundary of different breast tissue regions in mammograms. The goal of the segmentation algorithm is to see if graph cuts algorithm could separate different densities for the different breast patterns. The graph cut is applied with multi-selection of seeds label to provide the hard constraint, whereas the seeds labels are selected based on user defined. Graph cuts have been explored on images of various imaging modalities but not on mammograms just yet. Therefore, this project is mainly focused on using graph cut algorithm to perform segmentation to increase visibility of different breast densities in mammography images. Segmentation of the mammogram into different mammographic densities is useful for risk assessment and quantitative evaluation of density changes. Our proposed methodology for the segmentation of mammograms on the basis of their region into different densities based categories has been tested on MIAS database.

Computer Aided Detection of Breast Density and Mass, and Visualization of Other Breast Anatomical Regions on Mammograms Using Graph Cuts

Breast cancer mostly arises from the glandular (dense) region of the breast. Consequently, breast density has been found to be a strong indicator for breast cancer risk. Therefore, there is a need to develop a system which can segment or classify dense breast areas. In a dense breast, the sensitivity of mammography for the early detection of breast cancer is reduced. It is difficult to detect a mass in a breast that is dense. Therefore, a computerized method to separate the existence of a mass from the glandular tissues becomes an important task. Moreover, if the segmentation results provide more precise demarcation enabling the visualization of the breast anatomical regions, it could also assist in the detection of architectural distortion or asymmetry. This study attempts to segment the dense areas of the breast and the existence of a mass and to visualize other breast regions (skin-air interface, uncompressed fat, compressed fat, and glandular) in a system. The graph cuts (GC) segmentation technique is proposed. Multiselection of seed labels has been chosen to provide the hard constraint for segmentation of the different parts. The results are promising. A strong correlation (r = 0.93) was observed between the segmented dense breast areas detected and radiological ground truth.

Density Based Breast Segmentation for Mammograms Using Graph Cut and Seed Based Region Growing Techniques

In this work we explore the application of graph cuts and seed based region growing (SBRG) techniques to segment and detect the boundary of different breast tissue regions in mammograms. The graph cut (GC) is applied with multiselection of seed labels to provide the hard constraint, whereas the seeds labels are selected based on user defined. The region growing is applied with multi-selection of threshold and the threshold values are selected based upon histogram. To enhance the representation of each tissue type, pseudocolouring is used. The main goal of this study is to evaluate the graph cut techniques in the segmentation of different breast tissue regions, which correspond to the density in mammograms. Segmentation of the mammogram into different mammographic densities is useful for risk assessment and quantitative evaluation of density changes. Our proposed methodology has been tested on MIAS database.

MR image monomodal registration based on the nonsubsampled contourlet transform and mutual information

Image registration methods based on mutual information criteria have been widely used in multimodal medical image registration and have shown hopeful results. Although they are also used in monomodal image registration, their performance is not as excellent as that in multimodal registration. In general, the majority of registration methods consist of the following four steps: feature extraction, feature matching, transformation of the models and, finally, resampling the image. It was noted that the accuracy of the registration process depends on matching a feature and control points (CP) detection. Therefore in this paper has been to rely on this feature for magnetic resonance image (MRI) monomodal registration. We have proposed to extract the salient edges and extracted a CP of medical images by using efficiency of multiresolution representation of data nonsubsampled contourlet transform (NSCT). The MR images were first decomposed using the NSCT, and then Edge and CP were extracted from bandpass directional subband of NSCT coefficients and some proposed rules. After edge and CP extraction, mutual information (MI) was adopted for the registration of feature points and translation parameters are calculated by using particle swarm optimization (PSO). We implement experiments to evaluate the performance of the NTSC and MI similarity measures for 2-D monomodal registration. The experimental results showed that the proposed method produces totally accurate performance for MR image monomodal registration.

Neural Network Inputs Selection for Breast Cancer Cells Classification

Neural networks have been employed in many medical applications including breast cancer classification. Innovation in diagnostic features of tumours may play a central role in development of new treatment methods for earliest stage of breast cancer detection. Feature selection of neural network inputs is important for an accurate diagnosis application. Therefore, this study proposes elimination method for inputs feature selection of neural network to classify breast cancer cells. Morphological features were used as the inputs to several neural networks. The elimination method was employed on Hybrid Multilayer Perceptron (HMLP) network to investigate the diagnostic capability of features in combination and individually. Based on network performance resulted, the method was found practical for neural network inputs selection. Training the network with combination of dominant morphological features increased diagnosis capabilities and gave highest accuracy of 96%.

Normalization and rectification method for online hindi digit recognition with partial alignment algorithm

Research in data entry using light pen and other devices has always been of major interest over the past two decades. This is very helpful especially to those who are unable to use the keyboard fast enough. In this work, a new normalization and rectification method has been used, along with partial sequence alignment algorithm for online digit recognition. The normalization and rectification method was applied to obtain a unique sharp digit structure. A hybrid partial local-global sequence alignment is used to obtain the best matched digit DNA from the database as a two stage recognition process. The proposed method used stored data base samples for comparison purposes and then tested on 18 persons of different range in age with various writing styles. The normalization and rectification method was compared to smoothing method to determine the algorithm performance. The algorithm achieved 98.68% recognition accuracy when subjected with a normalization factor and thresholds adjusted to fixed values.

Evaluation of Morphological Features for Breast Cells Classification Using Neural Networks

Rapid technology advancement has contributed towards achievements in medical applications. Cancer detection in its earliest stage is definitely very important for effective treatments. Innovation in diagnostic features of tumours may play a central role in development of new treatment methods. Thus, the purpose of this study is to evaluate proposed morphological features to classify breast cancer cells. In this paper, the morphological features were evaluated using neural networks. The features were presented to several neural networks architecture to investigate the most suitable neural network type for classifying the features effectively. The performance of the networks was compared based on resulted mean squared error, accuracy, false positive, false negative, sensitivity and specificity. The optimum network for classification of breast cancer cells was found using Hybrid Multilayer Perceptron (HMLP) network. The HMLP network was then employed to investigate the diagnostic capability of the features individually and in combination. The features were found to have important diagnostic capabilities. Training the network with a larger number of dominant morphological features was found to significantly increase the diagnostic capabilities. A combination of the proposed features gave the highest accuracy of 96%.