Ali M. Hasan

Bio: Ali M. Hasan is an academic researcher from Nahrain University. The author has contributed to research in topics: Segmentation & Vinyl chloride. The author has an hindex of 9, co-authored 22 publications receiving 293 citations. Previous affiliations of Ali M. Hasan include University of Salford.

Classification of Covid-19 coronavirus, pneumonia and healthy lungs in CT scans using Q-deformed entropy and deep learning features

Abstract: Many health systems over the world have collapsed due to limited capacity and a dramatic increase of suspected COVID-19 cases. What has emerged is the need for finding an efficient, quick and accurate method to mitigate the overloading of radiologists' efforts to diagnose the suspected cases. This study presents the combination of deep learning of extracted features with the Q-deformed entropy handcrafted features for discriminating between COVID-19 coronavirus, pneumonia and healthy computed tomography (CT) lung scans. In this study, pre-processing is used to reduce the effect of intensity variations between CT slices. Then histogram thresholding is used to isolate the background of the CT lung scan. Each CT lung scan undergoes a feature extraction which involves deep learning and a Q-deformed entropy algorithm. The obtained features are classified using a long short-term memory (LSTM) neural network classifier. Subsequently, combining all extracted features significantly improves the performance of the LSTM network to precisely discriminate between COVID-19, pneumonia and healthy cases. The maximum achieved accuracy for classifying the collected dataset comprising 321 patients is 99.68%.

Combining Deep and Handcrafted Image Features for MRI Brain Scan Classification

Abstract: Progresses in the areas of artificial intelligence, machine learning, and medical imaging technologies have allowed the development of the medical image processing field with some astonishing results in the last two decades. These innovations enabled the clinicians to view the human body in high-resolution or three-dimensional cross-sectional slices, which resulted in an increase in the accuracy of the diagnosis and the examination of patients in a non-invasive manner. The fundamental step for magnetic resonance imaging (MRI) brain scans classifiers is their ability to extract meaningful features. As a result, many works have proposed different methods for features extraction to classify the abnormal growths in the brain MRI scans. More recently, the application of deep learning algorithms to medical imaging leads to impressive performance enhancements in classifying and diagnosing complicated pathologies, such as brain tumors. In this paper, a deep learning feature extraction algorithm is proposed to extract the relevant features from MRI brain scans. In parallel, handcrafted features are extracted using the modified gray level co-occurrence matrix (MGLCM) method. Subsequently, the extracted relevant features are combined with handcrafted features to improve the classification process of MRI brain scans with support vector machine (SVM) used as the classifier. The obtained results proved that the combination of the deep learning approach and the handcrafted features extracted by MGLCM improves the accuracy of classification of the SVM classifier up to 99.30%.

Segmentation of brain tumors in MRI images using three-dimensional active contour without edge

Abstract: Brain tumor segmentation in magnetic resonance imaging (MRI) is considered a complex procedure because of the variability of tumor shapes and the complexity of determining the tumor location, size, and texture. Manual tumor segmentation is a time-consuming task highly prone to human error. Hence, this study proposes an automated method that can identify tumor slices and segment the tumor across all image slices in volumetric MRI brain scans. First, a set of algorithms in the pre-processing stage is used to clean and standardize the collected data. A modified gray-level co-occurrence matrix and Analysis of Variance (ANOVA) are employed for feature extraction and feature selection, respectively. A multi-layer perceptron neural network is adopted as a classifier, and a bounding 3D-box-based genetic algorithm is used to identify the location of pathological tissues in the MRI slices. Finally, the 3D active contour without edge is applied to segment the brain tumors in volumetric MRI scans. The experimental dataset consists of 165 patient images collected from the MRI Unit of Al-Kadhimiya Teaching Hospital in Iraq. Results of the tumor segmentation achieved an accuracy of 89% ± 4.7% compared with manual processes.

Spectroscopic, Physical and Topography of Photochemical Process of PVC Films in the Presence of Schiff Base Metal Complexes

Abstract: The photostability of poly(vinyl chloride), PVC, containing various Schiff base metal complexes (0.5% by weight) was investigated. Various indices corresponding to a number of functional groups were monitored with irradiation of polymeric films to determine their photostabilization activities. The quantum yield of the chain scission (Φcs) of modified polymeric films was found to be (1.15⁻4.65) × 10⁶. The surface morphology of a PVC sample was investigated by the use of atomic force microscope (AFM). The photostability of PVC films in the presence of Schiff base additives was found to follow the following order: PVC < PVC + CuL₂ < PVC + CdL₂ < PVC + ZnL₂ < PVC + SnL₂ < PVC + NiL₂. Various mechanisms for PVC films photostability containing the Schiff base additives have been suggested.

Image Processing

Abstract: MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

Brain Tumor Classification Using Convolutional Neural Network

Abstract: Misdiagnosis of brain tumor types will prevent effective response to medical intervention and decrease the chance of survival among patients. One conventional method to differentiate brain tumors is by inspecting the MRI images of the patient’s brain. For large amount of data and different specific types of brain tumors, this method is time consuming and prone to human errors. In this study, we attempted to train a Convolutional Neural Network (CNN) to recognize the three most common types of brain tumors, i.e. the Glioma, Meningioma, and Pituitary. We implemented the simplest possible architecture of CNN; i.e. one each of convolution, max-pooling, and flattening layers, followed by a full connection from one hidden layer. The CNN was trained on a brain tumor dataset consisting of 3064 T-1 weighted CE-MRI images publicly available via figshare Cheng (Brain Tumor Dataset, 2017 [1]). Using our simple architecture and without any prior region-based segmentation, we could achieve a training accuracy of 98.51% and validation accuracy of 84.19% at best. These figures are comparable to the performance of more complicated region-based segmentation algorithms, which accuracies ranged between 71.39 and 94.68% on identical dataset Cheng (Brain Tumor Dataset, 2017 [1], Cheng et al. (PLoS One 11, 2017 [2]).

A Combined Deep CNN-LSTM Network for the Detection of Novel Coronavirus (COVID-19) Using X-ray Images

Abstract: Nowadays automatic disease detection has become a crucial issue in medical science with the rapid growth of population. Coronavirus (COVID-19) has become one of the most severe and acute diseases in very recent times that has been spread globally. Automatic disease detection framework assists the doctors in the diagnosis of disease and provides exact, consistent, and fast reply as well as reduces the death rate. Therefore, an automated detection system should be implemented as the fastest way of diagnostic option to impede COVID-19 from spreading. This paper aims to introduce a deep learning technique based on the combination of a convolutional neural network (CNN) and long short-term memory (LSTM) to diagnose COVID-19 automatically from X-ray images. In this system, CNN is used for deep feature extraction and LSTM is used for detection using the extracted feature. A collection of 421 X-ray images including 141 images of COVID-19 is used as a dataset in this system. The experimental results show that our proposed system has achieved 97% accuracy, 91% specificity, and 100% sensitivity. The system achieved desired results on a small dataset which can be further improved when more COVID-19 images become available. The proposed system can assist doctors to diagnose and treatment the COVID-19 patients easily.