Wan Azani Wan Mustafa
Thumbnail Image
Preferred name
Wan Azani Wan Mustafa
Official Name
Wan Azani, Wan Mustafa
Alternative Name
Mustafa, W.
Azani Mustafa, Wan
Mustaffa, Wan Azani
Wan Mustafa, Wan Azani
Main Affiliation
Scopus Author ID
57219421621
Researcher ID
J-4603-2014

Research Output

Filters

39
13
Reset filters

Settings
Now showing 1 - 10 of 44
  • Publication
    Nucleus Region Detection of Cervical Cytology Using Image Channel Conversion Techniques
    ( 2024-05-10)
    Alquran H.
    ;
    Badarneh A.
    ;
    Alsalatie M.
    ;
    Wan Azani Wan Mustafa
    ;
    Alquraan B.
    Cervical cancer is a form of cancer that develops in the cells of the cervix, which links the uterus to the vagina. Cervical cancer can often be prevented by attending the cervical screening, which aims to find and treat changes to cells before they turn into cancer. Pap smear images are a more popular technique for screening cervical cancer. The nucleus and cytoplasm are present in the smear cell images. The spread of cancer is determined by the shape and structure of the nucleus. Thus, nucleus segmentation is an important step in cancer detection. However, overlapping, poor contrast, uneven staining, and other factors make cervical nucleus segmentation difficult. This paper proposes a new segmentation method for the cervical nucleus using digital image processing. In our proposed method, image processing techniques are employed to segment the nucleus. This method mainly compared the performance of using Red Green Blue (RGB) channels and Hue, Saturation, and Value (HSV). The best two channels from each two-colored image representation are compared, where the V channel is the best among H and S channels. On the other hand, G chancel is the best among the G and B channels. Therefore, the best two channels are compared, and the segmentation using the G channel is the best among all, with a sensitivity of 94.3%, specificity of 94.6% and precision of 88.3%. The main impact of this paper will be to assist doctors in diagnosing cervical cancer-based segmentation of the nucleus in Pap smear images.
  • Publication
    Nucleus segmentation in pap smear images using image processing techniques
    ( 2024-03-07)
    Alslatie M.
    ;
    Alquran H.
    ;
    Wan Azani Wan Mustafa
    ;
    Naser M.M.
    ;
    Yacob Y.M.
    Cervical cancer is caused by the growth of abnormal cells in the cervix's lining. Human papillomavirus (HPV), a sexually transmitted infection, plays a role in most cervical cancers. Therefore, cervical cancer can be avoided by having regular screenings and being vaccinated against HPV infection. The term pap-smear refers to human cell samples stained using the Papanicolaou method. The Papanicolaou method is used to detect precancerous cell changes before they become invasive cancer. The smear cell image is composed of a nucleus and cytoplasm. Cancer prevalence is determined by the shape and structure of the nucleus. Therefore, the segmentation of the nucleus is an essential step in detecting cancer. However, overlapping, poor contrast, uneven staining, and other factors make cervical nucleus segmentation difficult. This paper proposes a new segmentation method for the cervical nucleus using digital image processing. Our proposed method used a median filter to remove noise and a non-linear contrast stretching to enhance the Pap smear images. Then, we used Bradley thresholding for the segmented cervical nucleus. The main impact of this paper will assist doctors in diagnosing cervical cancer based on Pap smear images and increase the accuracy percentages compared to the conventional method.
  • Publication
    Cervical Cancer Classification Using Combined Machine Learning and Deep Learning Approach
    ( 2022-01-01)
    Alquran H.
    ;
    Wan Azani Wan Mustafa
    ;
    Qasmieh I.A.
    ;
    Yacob Y.M.
    ;
    Alsalatie M.
    ;
    Al-Issa Y.
    ;
    Alqudah A.M.
    Cervical cancer is screened by pap smear methodology for detection and classification purposes. Pap smear images of the cervical region are employed to detect and classify the abnormality of cervical tissues. In this paper, we proposed the first system that it ables to classify the pap smear images into a seven classes problem. Pap smear images are exploited to design a computer-aided diagnoses system to classify the abnormality in cervical images cells. Automated features that have been extracted using ResNet101 are employed to discriminate seven classes of images in Support Vector Machine (SVM) classifier. The success of this proposed system in distinguishing between the levels of normal cases with 100% accuracy and 100% sensitivity. On top of that, it can distinguish between normal and abnormal cases with an accuracy of 100%. The high level of abnormality is then studied and classified with a high accuracy. On the other hand, the low level of abnormality is studied separately and classified into two classes, mild and moderate dysplasia, with ∼ 92% accuracy. The proposed system is a built-in cascading manner with five models of polynomial (SVM) classifier. The overall accuracy in training for all cases is 100%, while the overall test for all seven classes is around 92% in the test phase and overall accuracy reaches 97.3%. The proposed system facilitates the process of detection and classification of cervical cells in pap smear images and leads to early diagnosis of cervical cancer, which may lead to an increase in the survival rate in women.
  • Publication
    Automated Heart Diseases Detection Using Machine Learning Approach
    ( 2023-01-01)
    Aburayya R.A.
    ;
    Alomar R.A.
    ;
    Alnajjar D.K.
    ;
    Athamnah S.
    ;
    Alquran H.
    ;
    Wan Azani Wan Mustafa
    ;
    Al-Dolaimy F.
    ;
    Alkhayyat A.
    An extensive number of people might be affected by heart disease (HD), a major health issue that can occur anywhere in the world. Therefore, early diagnosis of cardiac disease is advantageous for treatment. A technology that can easily diagnose heart disease must be developed because the number of people with the condition is rising quickly. In addition, the patient's smoking history affects whether a problem is present or not. The HD system can define the most crucial cardiovascular patient characteristics and identify high-risk patients, but it can also model these characteristics to make it simple and clear to distinguish between them. Age, chest discomfort, blood pressure (BP), gender, cholesterol, and heartbeat are a few examples of factors that are taken into account while applying and comparing machine learning algorithms. The major goal of this article is to create a fundamental machine learning model to enhance accurate cardiac disease diagnosis. In our study, we used a HD dataset to construct a machine-learning-based diagnosis method for heart disease prediction (Logistic Regression, K-Nearest Neighbor (K-NN), Decision Tree, Naive Bayes, Random Forest, and Support Vector Machine (SVM)). To evaluate the performance of classifiers, we employed cross-validation, feature selection techniques, and well-known machine learning metrics like classification accuracy, specificity, and sensitivity. The suggested system makes it simple to distinguish between those who have cardiac disease and those who are healthy. Additionally, each classifier's receiver optimistic curves and area under the curves were calculated. All of the classifiers, feature selection algorithms, preprocessing techniques, validation techniques, and metrics for measuring the performance of the classifiers utilized in this study have been covered. A smaller collection of features and the complete set of features have both been used to validate the performance of the suggested system.
  • Publication
    Automated Diagnosis of Heart-Lung Diseases in Chest X-ray Images
    ( 2022-01-01)
    Alslatie M.
    ;
    Alquran H.
    ;
    Wan Azani Wan Mustafa
    ;
    Abu-Qasmieh I.
    ;
    Alqudah A.M.
    ;
    Alkhayyat A.
    The state of the art of artificial intelligence (AI) for various medical imaging applications leads to enhanced accuracy, analysis, visualization, and interpretation of chest Xray (CXR) images for diagnosis. Many diseases are diagnosed based on CXR images. In this paper, two types of abnormalities are diagnosed based on AI techniques. The two classes are atelectasis and cardiomegaly. The acquired images are segmented to localize the chest region and then enhanced using gray-level transformation methods. The enhanced images are passed to two pretrained convolutional neural networks (CNNs): shuffle and mobile net. The transfer learning approach is utilized in this stage. The automated features are extracted from the last fully connected layer. Each CNN deserves to have the two most representative features for the two classes. These four features are passed to support the vector machine classifier. The training accuracy reached 100% and the test accuracy was 96.7%. The proposed method can be extended to be a milestone in the classification of all heart-lung diseases that can be diagnosed using chest X-ray images.
  • Publication
    Contrast enhancement on pap smear cell images: A comparison
    ( 2023-06-12)
    Hameed M.S.S.
    ;
    Wan Azani Wan Mustafa
    ;
    Syed Zulkarnain Syed Idrus
    ;
    Mohd Aminudin Jamlos
    ;
    Alquran H.
    Cervical cancer is a common disease that can be carried by women. It is the 3rd leading cause of female cancer in Malaysia and the 4th most common type of cancer for women globally. Referring to the HPV Information Centre in 2018, it is estimated that 1682 women are diagnosed and 944 die from having cervical cells. In 2018, 569, 847 of the 18,078,957 cases were categorised as cervical cancer, which is 3.2%. With the advancement in science and technology, cervical cancer can be detected at an early stage by conducting a Pap smear test. This test will filter abnormal cervical cells and detect precancerous changes in cervical cells based on the colour and shape properties of their nuclei and cytoplasm. The problem is that performing the procedure manually can be time-consuming and cause inconsistencies and errors even further because the cervical cell itself does not show an obvious difference in texture and colour from normal cells. This paper will focus on colour contrast enhancement of the cervical cell using a few methods such as Contrast Stretching (CS), CLAHE, Histogram Equalization (HE), Image Adjustment, and Multi Scale Retinex (MSR). From this research, the cervical cell colour contrast can be enhanced to a better level and the detection of cervical cells can happen faster and more accurately. Hence, the errors in detecting can be reduced again so they can be treated soon.
  • Publication
    Diagnosis of Liver Tumors in Human CT Images Based on the LiverNet Approach
    ( 2022-06-01)
    Alawneh K.
    ;
    Alquran H.
    ;
    Alsalatie M.
    ;
    Wan Azani Wan Mustafa
    ;
    Al-Issa Y.
    ;
    Alqudah A.
    ;
    Badarneh A.
    Liver cancer contributes to the increasing mortality rate in the world. Therefore, early detection may lead to a decrease in morbidity and increase the chance of survival rate. This research offers a computer-aided diagnosis system, which uses computed tomography scans to categorize hepatic tumors as benign or malignant. The 3D segmented liver from the LiTS17 dataset is passed through a Convolutional Neural Network (CNN) to detect and classify the existing tumors as benign or malignant. In this work, we propose a novel light CNN with eight layers and just one conventional layer to classify the segmented liver. This proposed model is utilized in two different tracks; the first track uses deep learning classification and achieves a 95.6% accuracy. Meanwhile, the second track uses the automatically extracted features together with a Support Vector Machine (SVM) classifier and achieves 100% accuracy. The proposed network is light, fast, reliable, and accurate. It can be exploited by an oncological specialist, which will make the diagnosis a simple task. Furthermore, the proposed network achieves high accuracy without the curation of images, which will reduce time and cost.
  • Publication
    Liver Tumor Decision Support System on Human Magnetic Resonance Images: A Comparative Study
    ( 2023-01-01)
    Alquran H.
    ;
    Al-Issa Y.
    ;
    Alslatie M.
    ;
    Abu-Qasmieh I.
    ;
    Alqudah A.
    ;
    Wan Azani Wan Mustafa
    ;
    Yacob Y.M.
    Liver cancer is the second leading cause of cancer death worldwide. Early tumor detection may help identify suitable treatment and increase the survival rate. Medical imaging is a non-invasive tool that can help uncover abnormalities in human organs. Magnetic Resonance Imaging (MRI), in particular, uses magnetic fields and radio waves to differentiate internal human organs tissue. However, the interpretation of medical images requires the subjective expertise of a radiologist and oncologist. Thus, building an automated diagnosis computer-based system can help specialists reduce incorrect diagnoses. This paper proposes a hybrid automated system to compare the performance of 3D features and 2D features in classifying magnetic resonance liver tumor images. This paper proposed two models; the first one employed the 3D features while the second exploited the 2D features. The first system uses 3D texture attributes, 3D shape features, and 3D graphical deep descriptors beside an ensemble classifier to differentiate between four 3D tumor categories. On top of that, the proposed method is applied to 2D slices for comparison purposes. The proposed approach attained 100% accuracy in discriminating between all types of tumors, 100% Area Under the Curve (AUC), 100% sensitivity, and 100% specificity and precision as well in 3D liver tumors. On the other hand, the performance is lower in 2D classification. The maximum accuracy reached 96.4% for two classes and 92.1% for four classes. The top-class performance of the proposed system can be attributed to the exploitation of various types of feature selection methods besides utilizing the ReliefF features selection technique to choose the most relevant features associated with different classes. The novelty of this work appeared in building a highly accurate system under specific circumstances without any processing for the images and human input, besides comparing the performance between 2D and 3D classification. In the future, the presented work can be extended to be used in the huge dataset. Then, it can be a reliable, efficient Computer Aided Diagnosis (CAD) system employed in hospitals in rural areas.
  • Publication
    Intelligent Diagnosis and Classification of Keratitis
    ( 2022-06-01)
    Alquran H.
    ;
    Al-Issa Y.
    ;
    Alsalatie M.
    ;
    Wan Azani Wan Mustafa
    ;
    Qasmieh I.A.
    ;
    Zyout A.
    A corneal ulcer is an open sore that forms on the cornea; it is usually caused by an infection or injury and can result in ocular morbidity. Early detection and discrimination between different ulcer diseases reduces the chances of visual disability. Traditional clinical methods that use slit-lamp images can be tiresome, expensive, and time-consuming. Instead, this paper proposes a deep learning approach to diagnose corneal ulcers, enabling better, improved treatment. This paper sug-gests two modes to classify corneal images using manual and automatic deep learning feature ex-traction. Different dimensionality reduction techniques are utilized to uncover the most significant features that give the best results. Experimental results show that manual and automatic feature extraction techniques succeeded in discriminating ulcers from a general grading perspective, with ~93% accuracy using the 30 most significant features extracted using various dimensionality reduction techniques. On the other hand, automatic deep learning feature extraction discriminated severity grading with a higher accuracy than type grading regardless of the number of features used. To the best of our knowledge, this is the first report to ever attempt to distinguish corneal ulcers based on their grade grading, type grading, ulcer shape, and distribution. Identifying corneal ulcers at an early stage is a preventive measure that reduces aggravation and helps track the efficacy of adapted medical treatment, improving the general public health in remote, underserved areas.
  • Publication
    Pap Smear Image Analysis Based on Nucleus Segmentation and Deep Learning – A Recent Review
    ( 2023-02-01)
    Alias N.A.
    ;
    Wan Azani Wan Mustafa
    ;
    Mohd Aminudin Jamlos
    ;
    Ismail S.
    ;
    Alquran H.
    ;
    Mohamad Nur Khairul Hafizi Rohani
    Cervical cancer refers to a dangerous and common illness that impacts women worldwide. Moreover, this cancer affects over 300,000 people each year, with one woman diagnosed every minute. It affects over 0.5 million women annually, leading to over 0.3 million deaths. Recently, considerable literature has grown around developing technologies to detect cervical cancer cells in women. Previously, a cervical cancer diagnosis was made manually, which may result in a false positive or negative. Automated detection of cervical cancer and analysis method of the Papanicolaou (Pap) smear images are still debated among researchers. Thus, this paper reviewed several studies related to the detection method of Pap smear images focusing on Nuclei Segmentation and Deep Learning (DL) from the publication year of 2020, 2021, and 2022. Training, validation, and testing stages have all been the subject of study. However, there are still inadequacies in the current methodologies that have caused limitations to the proposed approaches by researchers. This study may inspire other researchers to view the proposed methods' potential and provide a decent foundation for developing and implementing new solutions.