Rizuana Iqbal Hussain

Clinical evaluation of the anterior translation of glenohumeral joint using ultrasonography: an intra- and inter-rater reliability study.

OBJECTIVE The aim of this study was to investigate the intra- and inter-rater reliability of ultrasonography (US) to measure anterior translation of the humeral head (ATHH) among healthy subjects and patients with sacroiliac joint dysfunction. METHODS The study included a total of 22 shoulder joints from 11 subjects. Six subjects were healthy and 5 had sacroiliac joint dysfunction. Anterior translation of the humeral head was measured twice using US by two different investigators. Intraclass correlation coefficient (ICC3,1), standard error of measurements (SEMs), coefficient of variations (CVs) and Bland-Altman plot were used as analytical tests to investigate intra- and inter-rater reliability, amount of error and agreeability of the measurements between investigators. RESULTS Intraclass correlation coefficient was 0.94, showing a high level of intra-rater reliability of the first investigator with SEMs (0.01 cm) and CV (5.1%) in measuring ATHH. Intra-rater reliability of the second investigator was 0.84 with SEMs (0.03 cms) and CV (9.6%), indicating a high level of reliability. Inter-rater reliability was high, with an ICC value of 0.92 with SEMs (0.02 cms) and CV (5.9%). CONCLUSION The use of US as a measurement of ATHH has good levels of intra- and inter-rater reliability in clinical practice.

Brain imaging classification based On Learning Vector Quantization

The performance accuracy of the Artificial Neural Network (ANN) is highly dependent on the class distribution. Data multi-randomization before classification is proposed in this paper in order to obtain a proper classification model, which guaranties well performance of the classifiers. Multi randomization aims to allocate the best class distribution by re-ordering the input dataset randomly. In this paper, Learning Vector Quantization (LVQ) which is a supervised ANN, Multilayer perceptron (MLP), unsupervised Self organizing Map (SOM) and Radial Base Function (RBF) are used to classify multi randomized brain Magnetic Resonance Imaging (MRI) dataset. The proposed method showed significant improvement in the stability of the classifiers.

Breast cancer mass localization based on machine learning

According to Breast Cancer Institute (BCI), Breast cancer is one of the most dangerous types of cancer that affects women all around the world. Based on clinical guidelines, the use of mammogram for an early detection of this cancer is an important step in reducing its danger. Thus, computer aided detection using image processing techniques in analyzing mammogram images and localizing abnormalities such as mass has been used. A False Positive (FP) rate is considered a challenge in localizing mass in mammogram images. Hence, in this paper, the rejection model based on the Support Vector Machine (SVM) has been used in reducing the FP rate of segmented mammogram images using the Chan-Vese method, initialized by the Marker Controller Watershed (MCWS) algorithm. Firstly, a mammogram image is segmented using the MCWS algorithm. Then, the segmentation is refined using Chan-Vese. After that, the SVM rejection model is built and is used in rejecting the non-correct segmented nodules. The dataset which consists of 16 nodules and 28 non-nodules has been obtained from the UKM Medical Centre. The experiment has shown the effectiveness of the SVM rejection model in reducing the FP rate compared to the result without the use of the SVM rejection model.

Hexagonal microstrip antenna simulation for breast cancer detection

As an emerging technology, UltraWide Band (UWB) wireless communications provides a very different approach to the antenna technology compared to narrow band systems, which has been a very attractive choice for medical antenna development. In this paper presents the design and simulation of a hexagonal microstrip antenna along with a breast phantom simulation. The antenna is simulated by introducing a hexagon slot in the center of the patch an impedance bandwidth nearly 5 GHz is achieved. The presented antenna has been designed and simulated successfully. The simulation analysis of designed antenna is carried out using HFSS software. The obtained results with this antenna make it a suitable antenna for UWB systems and portable applications.

Round Randomized Learning Vector Quantization for Brain Tumor Imaging

Brain magnetic resonance imaging (MRI) classification into normal and abnormal is a critical and challenging task. Owing to that, several medical imaging classification techniques have been devised in which Learning Vector Quantization (LVQ) is amongst the potential. The main goal of this paper is to enhance the performance of LVQ technique in order to gain higher accuracy detection for brain tumor in MRIs. The classical way of selecting the winner code vector in LVQ is to measure the distance between the input vector and the codebook vectors using Euclidean distance function. In order to improve the winner selection technique, round off function is employed along with the Euclidean distance function. Moreover, in competitive learning classifiers, the fitting model is highly dependent on the class distribution. Therefore this paper proposed a multiresampling technique for which better class distribution can be achieved. This multiresampling is executed by using random selection via preclassification. The test data sample used are the brain tumor magnetic resonance images collected from Universiti Kebangsaan Malaysia Medical Center and UCI benchmark data sets. Comparative studies showed that the proposed methods with promising results are LVQ1, Multipass LVQ, Hierarchical LVQ, Multilayer Perceptron, and Radial Basis Function.

Brain Tumor Treatment Advisory System

The process of brain tumor diagnoses involved many medical expert and large number of rules and regulation. For public, it is important to recognise the symptoms. Medical expert need the system to assist in decision making. This paper presents a brain tumor treatment advisory system (BTTAS) for public and medical experts. The aims of the system are: to educate public on brain tumor, to assist medical expert in diagnosing process, and suggested treatment. The rules for the treatment advisory system are developed with assistance of medical experts from Universiti Kebangsaan Malaysia Medical Center (UKMMC). Based on user testing evaluations, most experts have given acceptable satisfaction rate towards this application.

Mamdani-Fuzzy Expert System for BIRADS Breast Cancer Determination Based on Mammogram Images

Breast cancer is considered as a dangerous disease attack women all over the world. A Mamdani-Fuzzy expert system is built to detect the disease in early stage by using mammogram images and data report for calcification and ultrasound data for mass size. Two input and one output which are size of mass and distribution of calcification (input) and class of BIRADS (output) have been used to develop the model. The model is able to classify 84.04 % mammogram images into the actual BIRADS. 13 images which are 13.83% wrongly classify and 2 images which are 2.13% unable to classify because of some limitation as stated in discussion.