Volume (10) - Issue (I), ACSE-BIME ISSN: Print 1687-4811, Online 1687-482X &
CD-ROM 1687-4838
|
@ARTICLE |
{P1160934843, |
| AUTHOR = |
{Nandita Pradhan and A.K. Sinha}, |
| TITLE = |
{Development of a composite feature vector for the detection of pathological and healthy tissues in FLAIR MR images of brain}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2010}, |
| MONTH= |
{December}, |
| VOLUME = |
{10}, |
| ISSUE = |
{I}, |
| PAGES= |
{1-11}, |
| ABSTRACT= |
{This paper presents a technique for segmentation and detection of pathological tissues (Tumor and Edema), normal tissues (White Matter and Gray Matter) and fluid (Cerebrospinal Fluid) from Fluid Attenuated Inversion Recovery (FLAIR) magnetic resonance (MR) images of brain with the help of composite feature vectors comprising of wavelet and statistical parameters, in contrast to other researchers who developed feature vectors either using statistical parameter or using wavelet parameters. The main contributions of paper are (1) Segmentation of intra cranial brain image in five segments is done with k-mean algorithm, which is based on combined features of wavelet energy function, & statistical parameters that reflect texture properties and pixel value analysis, giving better result. (2) In addition to tumor, edema is also characterized as a separate class, which is critical for therapy planning, surgery, diagnosis and treatment of tumors. Block processing of image is done by extracting feature vectors from small blocks of 4×4 pixels of image corresponding to tissues of tumor, edema, white matter, gray matter and cerebrospinal fluid and artificial neural network is trained using back propagation algorithm}, |
| NOTE= |
{
FLAIR Magnetic Resonance Image, Segmentation , k-means algorithm, Edema, Wavelet Energy function }
} |
(Status: Accepted)
| @ARTICLE |
{P1161002964, |
| AUTHOR = |
{Alaa M. Elsayad}, |
| TITLE = |
{Diagnosis of Erythemato-Squamous Diseases using Ensemble of Data Mining Methods}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2010}, |
| MONTH= |
{December}, |
| VOLUME = |
{10}, |
| ISSUE = |
{I}, |
| PAGES= |
{13-23}, |
| ABSTRACT= |
{The differential diagnosis of erythemato-squamous diseases is a major challenge in dermatology. This group of diseases consists of six different categories: psoriasis, seboreic dermatitis, lichen planus, pityriasis rosea, chronic dermatitis and pityriasis rubra pilaris. They all share the clinical features of erythema and scaling with very little differences. This paper investigates three different data mining methods; multilayer perceptron neural network, C5.0 decision tree and linear discriminate analysis in order to build an ensemble model to the problem of differential diagnosis of these erythemato-squamous diseases. The dermatology dataset investigated in this study is taken from the University of California at Irvine (UCI) machine learning repository. Given a training set of such patterns, the individual model learned how to differentiate a new case in the domain. The proposed ensemble combined the models using a confidence-weighted voting scheme. The classification performance of the proposed system is presented using statistical accuracy, specificity and sensitivity}, |
| NOTE= |
{neural network, decision tree, discriminant analysis, ensemble of classifiers, Erythemato-squamous}
}
|
(Status: Accepted)
| @ARTICLE |
{P1160936856, |
| AUTHOR = |
{ Mohamed Abd elhamid Abbas}, |
| TITLE = |
{Analysis of Nucleotide Sequences relying on Logic Representation with a Focus on H1N1 Case of Study}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2010}, |
| MONTH= |
{December}, |
| VOLUME = |
{10}, |
| ISSUE = |
{I}, |
| PAGES= |
{25--34}, |
| ABSTRACT= |
{ Analysis of Nucleotide Sequences is an important field to predict the behavior of different genus. The main contribution of the paper is proposing an efficient and a simple representation of deoxyribonucleic acid (DNA) double helix structure in a typical case. The suggested representation is based on the logic concepts of digital computations. The suggested approach modifies the concept of DNA matrix representation for one strand to analyze the whole DNA double helix. This allows analyzing smoothly the structure of DNA presenting an efficient analysis for number of features such as DNA comparisons, determining the degree of similarity among DNA of different origins and the stability of the double helix. To verify the proposed work a case study about Influenza A virus H1N1, Swine Flu, is analyzed. A comparison is presented among the DNA of H1N1, and other types of Influenza A viruses based on Data collected from the online database GeneBank. The results of the case study using the proposed representation depict that HIN1 virus infects human is highly similar to H5N1 that infect avian. Another Study about the stability of the double helix of H1N1 virus is presented. This study depicts the ability of H1N1 virus to mutate over last seven years. These results are equivalent to results reported by WHO World Health Organization}, |
| NOTE= |
{DNA double helix, DNA comparison, double helix stability, matrix representation, H1N1 virus}
}
|
(Status: Accepted)
| @ARTICLE |
{P1160943906, |
| AUTHOR = |
{Prashant Bansod and U.B. Desai and S.N. Merchant and Nitin Burkule}, |
| TITLE = |
{Spatio-temporal Guided Local Search for Semiautomatic Endocardial Contour Estimation in Echocardiography Sequences}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2010}, |
| MONTH= |
{December}, |
| VOLUME = |
{10}, |
| ISSUE = |
{I}, |
| PAGES= |
{35-46}, |
| ABSTRACT= |
{We propose a Spatio-Temporal Guided Local Search (STGLS) algorithm for the detection of endocardial contours in short axis and long axis views of echo cardiographic image sequences. The proposed algorithm requires minimal user intervention at the end diastolic and end systolic frames of the image sequence for specifying the candidate points of the contour. The region of interest and left ventricle center are approximated by tting an ellipse through the points marked by the expert in end diastolic frame. Contours in other frames of the sequence over a cardiac cycle are detected by use of the proposed algorithm in spatio-temporal frame work. GLS with features and constraints for solution space along with penalty terms overcome the optimization in contour detection being trapped in local minima. The spatio-temporal frame work incorporates the important temporal information from the adjacent frames during optimization to overcome dropouts. The proposed algorithm was applied to 20 data sets over a full cardiac cycle and the results were validated by comparing computer generated boundaries to those manually outlined by two experts using Hausdor distance (HD) measure, radial mean square error (rmse) and contour similarity index (CSI). For short axis views, the rmse was 1.83 mm with a HD of 6.13 1.96 mm. For long axis view, the rmse was 1.91 mm with a HD of 7.12 2.23 mm. We have also compared our results with two existing approaches, level set and optical ow. The results indicate an improvement when compared with ground truth due to incorporation of temporal clues. The STGLS algorithm oers an e cient semiautomatic segmentation of heart chambers in two dimensional (2D) echocardiography sequences for accurate assessment of global left ventricular function to guide therapy and staging of the cardiovascular diseases.}, |
| NOTE= |
{ Spatio-temporal, Guided local search, Echocardiography, Endocardial, Segmentation.}
}
|
(Status: Accepted)
| @ARTICLE |
{P1160949925, |
| AUTHOR = |
{H.B.Kekre and Saylee Gharge and Tanuja K. Sarode}, |
| TITLE = |
{Performance Evaluation of KFCG and LBG Algorithms in Tumor Demarcation of Mammograms}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2010}, |
| MONTH= |
{December}, |
| VOLUME = |
{10}, |
| ISSUE = |
{I}, |
| PAGES= |
{47--56}, |
| ABSTRACT= |
{X-ray mammography is the most effective and economical breast imaging modality. Segmenting a mammographic images into homogeneous texture regions representing disparate tissue types is often a useful preprocessing step in the computer-assisted detection of breast cancer. That is why we proposed new algorithm to detect cancer in mammogram breast cancer images. In this paper we proposed segmentation using vector quantization technique. Here we used Kekre's Fast Codebook Generation algorithm (KFCG) for segmentation of mammographic images. Initially a codebook of size 128 was generated for mammographic images. These code vectors were further clustered in 8 clusters using same KFCG algorithm. These 8 images were displayed as a result. This approach does not leads to over segmentation or under segmentation. For the comparison purpose we displayed results of Equalized Entropy using Gray Level Co-occurrence Matrix, watershed segmentation and Linde Buzo Gray(LBG) algorithm along with this method }, |
| NOTE= |
{Mammography, segmentation, tumor detection, LBG,KFCG}
}
|
| @ARTICLE |
{P1160952954, |
| AUTHOR = |
{V.Ashok and A.Nirmal kumar and T.Balakumaran and P.Ravikumar}, |
| TITLE = |
{Laser Doppler Based Blood Glucose Diagnosis in Real Time by Noninvasive Technique}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2010}, |
| MONTH= |
{December}, |
| VOLUME = |
{10}, |
| ISSUE = |
{I}, |
| PAGES= |
{57--66}, |
| ABSTRACT= |
{A method provides for the design of Fast Haar wavelet with the supervised neural network for diagnosis of diabetes mellitus with nearer accuracy with in short time application non-invasively is proposed. Our proposed work consists of two parts. First, analysis bank of haar wavelet is modified by using polyphase structure. Second, supervised back propagation neural network in the diagnosis of diabetes mellitus with the output of fast haar wavelet as its input is formulated. Finally, a fast haar wavelet based neural network is designed and it satisfies alias free and gives perfect nearer blood glucose value non-invasively which correlates the value of 99.69% of clinical diagnosis. Number of arithmetic calculations (convolution and addition) is reduced in fast haar wavelet transform with neural network. This makes the less computational complexity and less power consumption by reducing in time. Wavelet based supervised back propagation network is used for diagnosing blood glucose which extract from the blood flow doppler signals non-invasively}, |
| NOTE= |
{Artificial Neural Network, Haar wavelet, polyphase components, Quardrature mirror filter, Blood Glucose}
}
|
(Status: Accepted)
| @ARTICLE |
{P1161027164, |
| AUTHOR = |
{S.Santhosh Baboo and S.K.Mahendran}, |
| TITLE = |
{AN ADAPTIVE PREPROCESSING TECHNIQUE FOR X-RAY IMAGE}, |
| JOURNAL = |
{ICGST International Journal on Bioinformatics and Medical Engineering, BIME}, |
| YEAR = |
{2010}, |
| MONTH= |
{December}, |
| VOLUME = |
{10}, |
| ISSUE = |
{I}, |
| PAGES= |
{67--73}, |
| ABSTRACT= |
{This paper describes a human bone X-ray radiographic images preprocessing, and applied in Contrast Limited Adaptive Histogram Equalization. The Image preprocessing algorithms are improving the image quality before edge detection. In Medical image any changes will affect the entire diagnosis. In preprocessing first we applied it in the anisotropic filtering and median filtering to the X-ray image to improve the image quality. The two different method results are compared in PSNR. The best PSNR output image is applied in CLAHE for the image enhancing are better contrast, sharpness of detail and visibility of features enhancement}, |
| NOTE= |
{Image preprocessing, Histogram Equalization, X-ray images, PSNR, MSE}
}
|
(Status: Accepted)
|
