<span lang="EN-US">Stroke is the second-leading cause of death globally; therefore, it needs immediate treatment to prevent the brain from damage. Neuroimaging technique for stroke detection such as computed tomography (CT) has been widely used for emergency setting that can provide precise information on an obvious difference between white and gray matter. CT is the comprehensively utilized medical imaging technology for bone, soft tissue, and blood vessels imaging. A fully automatic segmentation became a significant contribution to help neuroradiologists achieve fast and accurate interpretation based on the region of interest (ROI). This review paper aims to identify, critically appraise, and summarize the evidence of the relevant studies needed by researchers. Systematic literature review (SLR) is the most efficient way to obtain reliable and valid conclusions as well as to reduce mistakes. Throughout the entire review process, it has been observed that the segmentation techniques such as fuzzy C-mean, thresholding, region growing, k-means, and watershed segmentation techniques were regularly used by researchers to segment CT scan images. This review is also impactful in identifying the best automated segmentation technique to evaluate brain stroke and is expected to contribute new information in the area of stroke research.</span>

Stroke is a “brain attack” that often causes paralysis, resulted from either bleeding in the brain (hemorrhagic) or the blockage of blood flow to the brain (ischemic). It posed a big challenge to Malaysian healthcare services with at least 32 deaths per day, while survivors were burdened with multiple problems. Conventionally, the diagnosis is performed manually by neuroradiologists during a highly subjective and time consuming tasks. Therefore, this paper intends to diagnose and classify stroke by investigating diffusion- weighted imaging (DWI) of brain stroke images using Bagged Tree classification. Stroke is classified into three main types which are acute stroke, chronic stroke and hemorrhage stroke. The performance of the proposed method is then verified using accuracy and Area Under the Curve (AUC). Based on the results, the overall accuracy for the classification is 96.7%. The AUC of each type of stroke for acute stroke, chronic stroke and hemorrhage stroke is 97%, 100% and 99%, respectively. This outcome could serve as an insight to improve the healthcare of the community by providing better solutions using such intelligent system.

<span>Defect inspection emerged as an important role for product quality monitoring process since it is a requirement of International Organization for Standardization (ISO) 9001. The used of manual inspection is impractical because of time consuming, human error, tiredness, repetitive and low productivity. Small and medium enterprises (SMEs) are industries that having problems in maintaining the quality of their products due to small capital provided. Therefore, automatic inspection is a promising approach to maintain product quality as well as to resolve the existing problems related to delay outputs and cost burden. This article presents a computerized analysis to detect color concentration defects that occur in beverage production based on texture information provided by gray level co-occurrence matrix (GLCM).</span><span> Based on the texture information, GLCM cross-section is computed to extract the parameters for features of color concentration. The distance value between two colors is then computed using co-occurrence histogram. The defect results either pass or reject is determined using Euclidean distance and rule-based classification. The experimental results show 100% accuracy which makes the proposed technique can implimented for beverage manufacturing inspection process.</span>

<span lang="EN-US">Treatment of stroke patients can be effectively carried out with the help of collateral circulation performance. Collateral circulation scoring as it is now used is dependent on visual inspection, which can lead to an inter- and <br /> intra-rater discrepancy. In this study, a collateral circulation classification using the ResNet50 was analyzed by using cone beam computed tomography (CBCT) images for the ischemic stroke patient. The remarkable performance of deep learning classification helps neuroradiologists with fast image classification. A pre-trained deep network ResNet50 was applied to extract robust features and learn the structure of CBCT images in their convolutional layers. Next, the classification layer of the ResNet50 was performed into binary classification as “good” and “poor” classes. The images were divided by 80:20 for training and testing. The empirical results support the claim that the application of ResNet50 offers consistent accuracy, sensitivity, and specificity values. The performance value of the classification accuracy was 76.79%. The deep learning approach was employed to unveil how biological image analysis could generate incredibly dependable and repeatable outcomes. The experiments performed on CBCT images evidenced that the proposed ResNet50 using convolutional neural network (CNN) architecture is indeed effective in classifying collateral circulation.</span>

No abstract