A Novel Multi-Scaled Deep Convolutional Structure for Punctilious Human Gait Authentication.

The need for non-interactive human recognition systems to ensure safe isolation between users and biometric equipment has been exposed by the COVID-19 pandemic. This study introduces a novel Multi-Scaled Deep Convolutional Structure for Punctilious Human Gait Authentication (MSDCS-PHGA). The proposed MSDCS-PHGA involves segmenting, preprocessing, and resizing silhouette images into three scales. Gait features are extracted from these multi-scale images using custom convolutional layers and fused to form an integrated feature set. This multi-scaled deep convolutional approach demonstrates its efficacy in gait recognition by significantly enhancing accuracy. The proposed convolutional neural network (CNN) architecture is assessed using three benchmark datasets: CASIA, OU-ISIR, and OU-MVLP. Moreover, the proposed model is evaluated against other pre-trained models using key performance metrics such as precision, accuracy, sensitivity, specificity, and training time. The results indicate that the proposed deep CNN model outperforms existing models focused on human gait. Notably, it achieves an accuracy of approximately 99.9% for both the CASIA and OU-ISIR datasets and 99.8% for the OU-MVLP dataset while maintaining a minimal training time of around 3 min.

ASD2-TL∗ GTO: Autism spectrum disorders detection via transfer learning with gorilla troops optimizer framework.

Autism Spectrum Disorder (ASD) treatment requires accurate diagnosis and effective rehabilitation. Artificial intelligence (AI) techniques in medical diagnosis and rehabilitation can aid doctors in detecting a wide range of diseases more effectively. Nevertheless, due to its highly heterogeneous symptoms and complicated nature, ASD diagnostics continues to be a challenge for researchers. This study introduces an intelligent system based on the Artificial Gorilla Troops Optimizer (GTO) metaheuristic optimizer to detect ASD using Deep Learning and Machine Learning. Kaggle and UCI ML Repository are the data sources used in this study. The first dataset is the Autistic Children Data Set, which contains 3,374 facial images of children divided into Autistic and Non-Autistic categories. The second dataset is a compilation of data from three numerical repositories: (1) Autism Screening Adults, (2) Autistic Spectrum Disorder Screening Data for Adolescents, and (3) Autistic Spectrum Disorder Screening Data for Children. When it comes to image dataset experiments, the most notable results are (1) a TF learning ratio greater than or equal to 50 is recommended, (2) all models recommend data augmentation, and (3) the DenseNet169 model reports the lowest loss value of 0.512. Concerning the numeric dataset, five experiments recommend standardization and the final five attributes are optional in the classification process. The performance metrics demonstrate the worthiness of the proposed feature selection technique using GTO more than counterparts in the literature review.

Revolutionizing Oral Cancer Detection: An Approach Using Aquila and Gorilla Algorithms Optimized Transfer Learning-Based CNNs.

The early detection of oral cancer is pivotal for improving patient survival rates. However, the high cost of manual initial screenings poses a challenge, especially in resource-limited settings. Deep learning offers an enticing solution by enabling automated and cost-effective screening. This study introduces a groundbreaking empirical framework designed to revolutionize the accurate and automatic classification of oral cancer using microscopic histopathology slide images. This innovative system capitalizes on the power of convolutional neural networks (CNNs), strengthened by the synergy of transfer learning (TL), and further fine-tuned using the novel Aquila Optimizer (AO) and Gorilla Troops Optimizer (GTO), two cutting-edge metaheuristic optimization algorithms. This integration is a novel approach, addressing bias and unpredictability issues commonly encountered in the preprocessing and optimization phases. In the experiments, the capabilities of well-established pre-trained TL models, including VGG19, VGG16, MobileNet, MobileNetV3Small, MobileNetV2, MobileNetV3Large, NASNetMobile, and DenseNet201, all initialized with 'ImageNet' weights, were harnessed. The experimental dataset consisted of the Histopathologic Oral Cancer Detection dataset, which includes a 'normal' class with 2494 images and an 'OSCC' (oral squamous cell carcinoma) class with 2698 images. The results reveal a remarkable performance distinction between the AO and GTO, with the AO consistently outperforming the GTO across all models except for the Xception model. The DenseNet201 model stands out as the most accurate, achieving an astounding average accuracy rate of 99.25% with the AO and 97.27% with the GTO. This innovative framework signifies a significant leap forward in automating oral cancer detection, showcasing the tremendous potential of applying optimized deep learning models in the realm of healthcare diagnostics. The integration of the AO and GTO in our CNN-based system not only pushes the boundaries of classification accuracy but also underscores the transformative impact of metaheuristic optimization techniques in the field of medical image analysis.

Biliary fistula and late recurrence of liver hydatid cyst: Role of cysto-biliary communication: A prospective multicenter study.

BACKGROUND: Hydatid cyst disease (HCD) is common in certain locations. Surgery is associated with postoperative biliary fistula (POBF) and recurrence. The primary aim of this study was to identify whether occult cysto-biliary communication (CBC) can predict recurrent HCD. The secondary aim was to assess the role of cystic fluid bilirubin and alkaline phosphatase (ALP) levels in predicting POBF and recurrent HCD. AIM: To identify whether occult CBC can predict recurrent HCD. The secondary aim was to assess the role of cystic fluid bilirubin and ALP levels in predicting POBF and recurrent HCD. METHODS: From September 2010 to September 2016, a prospective multicenter study was undertaken involving 244 patients with solitary primary superficial stage cystic echinococcosis 2 and cystic echinococcosis 3b HCD who underwent laparoscopic partial cystectomy with omentoplasty. Univariable logistic regression analysis assessed independent factors determining biliary complications and recurrence. RESULTS: There was a highly statistically significant association (P ≤ 0.001) between cystic fluid biochemical indices and the development of biliary complications (of 16 patients with POBF, 15 patients had high cyst fluid bilirubin and ALP levels), where patients with high bilirubin-ALP levels were 3405 times more likely to have biliary complications. There was a highly statistically significant association (P ≤ 0.001) between biliary complications, biochemical indices, and the occurrence of recurrent HCD (of 30 patients with recurrent HCD, 15 patients had high cyst fluid bilirubin and ALP; all 16 patients who had POBF later developed recurrent HCD), where patients who developed biliary complications and high bilirubin-ALP were 244.6 and 214 times more likely to have recurrent hydatid cysts, respectively. CONCLUSION: Occult CBC can predict recurrent HCD. Elevated cyst fluid bilirubin and ALP levels predicted POBF and recurrent HCD.

A Pseudo-near isogenic F2 population strategy for rapid QTL cloning.

Near isogenic F2 (NIF2) population frequently developed by conventional backcross has dramatically contributed to QTL identification in plants. Developing such a NIF2 population is time-consuming. Thus, it is urgent to rapidly produce a NIF2 population for QTL cloning. Here, we proposed a rapid QTL cloning strategy by generating a Pseudo-near isogenic F2 population (Pseudo-NIF2), which segregates at the target QTL but is fixed at other QTLs for the target trait. Nineteen QTLs for GL, GW, and TGW were detected in the F2 population from the cross between Zhenshan 97 and Egy316. To verify the efficiency of Pseudo-NIF2 in QTL quick cloning, the novel moderate QTL qGL10.1 which explained 9.1% and 5.6% of grain length variation in F2 and F2:3 populations was taken as an example. An F2 plant (F2-120), which segregated at qGL10.1 but fixed at other 8 QTLs for grain length, was screened to generate a Pseudo-NIF2 population by selfing cross. In the Pseudo-NIF2 population, the segregation ratio of plants with long grains to short grains fits 3:1, indicating that one gene controlled the variation of grain length. Based on the Pseudo-NIF2 and its progeny, qGL10.1 was fine mapped to a 19.3-kb region, where a gene OsMADS56 was verified as the candidate by functional polymorphism between parental alleles. Pseudo-NIF2 strategy is a rapid way for QTL cloning, which saves 3 to 4 cropping seasons compared to the conventional way. Applying the method for cloning QTL with moderate or major effects is promising. Supplementary Information: The online version contains supplementary material available at 10.1007/s11032-023-01408-x.

A two-stage renal disease classification based on transfer learning with hyperparameters optimization.

Renal diseases are common health problems that affect millions of people around the world. Among these diseases, kidney stones, which affect anywhere from 1 to 15% of the global population and thus; considered one of the leading causes of chronic kidney diseases (CKD). In addition to kidney stones, renal cancer is the tenth most prevalent type of cancer, accounting for 2.5% of all cancers. Artificial intelligence (AI) in medical systems can assist radiologists and other healthcare professionals in diagnosing different renal diseases (RD) with high reliability. This study proposes an AI-based transfer learning framework to detect RD at an early stage. The framework presented on CT scans and images from microscopic histopathological examinations will help automatically and accurately classify patients with RD using convolutional neural network (CNN), pre-trained models, and an optimization algorithm on images. This study used the pre-trained CNN models VGG16, VGG19, Xception, DenseNet201, MobileNet, MobileNetV2, MobileNetV3Large, and NASNetMobile. In addition, the Sparrow search algorithm (SpaSA) is used to enhance the pre-trained model's performance using the best configuration. Two datasets were used, the first dataset are four classes: cyst, normal, stone, and tumor. In case of the latter, there are five categories within the second dataset that relate to the severity of the tumor: Grade 0, Grade 1, Grade 2, Grade 3, and Grade 4. DenseNet201 and MobileNet pre-trained models are the best for the four-classes dataset compared to others. Besides, the SGD Nesterov parameters optimizer is recommended by three models, while two models only recommend AdaGrad and AdaMax. Among the pre-trained models for the five-class dataset, DenseNet201 and Xception are the best. Experimental results prove the superiority of the proposed framework over other state-of-the-art classification models. The proposed framework records an accuracy of 99.98% (four classes) and 100% (five classes).

Hepatobiliary manifestations following two-stages elective laparoscopic restorative proctocolectomy for patients with ulcerative colitis: A prospective observational study.

BACKGROUND: Hepatobiliary manifestations occur in ulcerative colitis (UC) patients. The effect of laparoscopic restorative proctocolectomy (LRP) with ileal pouch anal anastomosis (IPAA) on hepatobiliary manifestations is debated. AIM: To evaluate hepatobiliary changes after two-stages elective laparoscopic restorative proctocolectomy for patients with UC. METHODS: Between June 2013 and June 2018, 167 patients with hepatobiliary symptoms underwent two-stage elective LRP for UC in a prospective observational study. Patients with UC and having at least one hepatobiliary manifestation who underwent LRP with IPAA were included in the study. The patients were followed up for four years to assess the outcomes of hepatobiliary manifestations. RESULTS: The patients' mean age was 36 ± 8 years, and males predominated (67.1%). The most common hepatobiliary diagnostic method was liver biopsy (85.6%), followed by Magnetic resonance cholangiopancreatography (63.5%), Antineutrophil cytoplasmic antibodies (62.5%), abdominal ultrasonography (35.9%), and Endoscopic retrograde cholangiopancreatography (6%). The most common hepatobiliary symptom was Primary sclerosing cholangitis (PSC) (62.3%), followed by fatty liver (16.8%) and gallbladder stone (10.2%). 66.4% of patients showed a stable course after surgery. Progressive or regressive courses occurred in 16.8% of each. Mortality was 6%, and recurrence or progression of symptoms required surgery for 15%. Most PSC patients (87.5%) had a stable course, and only 12.5% became worse. Two-thirds (64.3%) of fatty liver patients showed a regressive course, while one-third (35.7%) showed a stable course. Survival rates were 98.8%, 97%, 95.8%, and 94% at 12 mo, 24 mo, 36 mo, and at the end of the follow-up. CONCLUSION: In patients with UC who had LRP, there is a positive impact on hepatobiliary disease. It caused an improvement in PSC and fatty liver disease. The most prevalent unchanged course was PSC, while the most common improvement was fatty liver disease.

Technique for facilitating closed reduction of difficult flexion type supracondylar humeral fracture in children.

The displaced flexion type supracondylar humeral fractures (SCHF) are inherently unstable and there is great intraoperative difficulty in obtaining and maintaining the fracture reduction by closed means. We introduced a technique for closed reduction and K-wires pinning of displaced flexion type SCHF. Fourteen patients with flexion-type SCHF (9 boys and 5 girls) underwent a reduction technique using a construct of three K-wires. The proximal wire was used for rotational control of the proximal fragment and the two distal wires were used for correction of the flexion and rotational deformity of the distal fragment. The patient's mean age was 7 (6-11) years. Results were evaluated by the anterior humeral line, Baumann's angle, carrying angle radiographically and Flynn's criteria clinically. The mean time for the union was 4.8 (4-6) weeks. The anterior humeral line passed through the middle one-third of the capitulum in 12 patients and the anterior third in two patients. The mean Baumann's angle was 19.60 ± 3.8 and the mean carrying angle was 14.21 ± 3.04. We reported no cases of failed closed reduction. The median operation time in this study was 30 (25-40) min. The mean number of C-arm images was 33.5 ± 5.23. According to Flynn's criteria; 10 cases (71.4%) were excellent and 4 (28.6%) were good. This technique can achieve the accurate reduction of flexion type SCHF and avoid the complications of both repeated closed reduction trials and open reduction. Level of Evidence: Level IV, case series.

An optimized deep learning approach for suicide detection through Arabic tweets.

Many people worldwide suffer from mental illnesses such as major depressive disorder (MDD), which affect their thoughts, behavior, and quality of life. Suicide is regarded as the second leading cause of death among teenagers when treatment is not received. Twitter is a platform for expressing their emotions and thoughts about many subjects. Many studies, including this one, suggest using social media data to track depression and other mental illnesses. Even though Arabic is widely spoken and has a complex syntax, depressive detection methods have not been applied to the language. The Arabic tweets dataset should be scraped and annotated first. Then, a complete framework for categorizing tweet inputs into two classes (such as Normal or Suicide) is suggested in this study. The article also proposes an Arabic tweet preprocessing algorithm that contrasts lemmatization, stemming, and various lexical analysis methods. Experiments are conducted using Twitter data scraped from the Internet. Five different annotators have annotated the data. Performance metrics are reported on the suggested dataset using the latest Bidirectional Encoder Representations from Transformers (BERT) and Universal Sentence Encoder (USE) models. The measured performance metrics are balanced accuracy, specificity, F1-score, IoU, ROC, Youden Index, NPV, and weighted sum metric (WSM). Regarding USE models, the best-weighted sum metric (WSM) is 80.2%, and with regards to Arabic BERT models, the best WSM is 95.26%.

Classification of breast cancer using a manta-ray foraging optimized transfer learning framework.

Due to its high prevalence and wide dissemination, breast cancer is a particularly dangerous disease. Breast cancer survival chances can be improved by early detection and diagnosis. For medical image analyzers, diagnosing is tough, time-consuming, routine, and repetitive. Medical image analysis could be a useful method for detecting such a disease. Recently, artificial intelligence technology has been utilized to help radiologists identify breast cancer more rapidly and reliably. Convolutional neural networks, among other technologies, are promising medical image recognition and classification tools. This study proposes a framework for automatic and reliable breast cancer classification based on histological and ultrasound data. The system is built on CNN and employs transfer learning technology and metaheuristic optimization. The Manta Ray Foraging Optimization (MRFO) approach is deployed to improve the framework's adaptability. Using the Breast Cancer Dataset (two classes) and the Breast Ultrasound Dataset (three-classes), eight modern pre-trained CNN architectures are examined to apply the transfer learning technique. The framework uses MRFO to improve the performance of CNN architectures by optimizing their hyperparameters. Extensive experiments have recorded performance parameters, including accuracy, AUC, precision, F1-score, sensitivity, dice, recall, IoU, and cosine similarity. The proposed framework scored 97.73% on histopathological data and 99.01% on ultrasound data in terms of accuracy. The experimental results show that the proposed framework is superior to other state-of-the-art approaches in the literature review.

A3C-TL-GTO: Alzheimer Automatic Accurate Classification Using Transfer Learning and Artificial Gorilla Troops Optimizer.

Alzheimer's disease (AD) is a chronic disease that affects the elderly. There are many different types of dementia, but Alzheimer's disease is one of the leading causes of death. AD is a chronic brain disorder that leads to problems with language, disorientation, mood swings, bodily functions, memory loss, cognitive decline, mood or personality changes, and ultimately death due to dementia. Unfortunately, no cure has yet been developed for it, and it has no known causes. Clinically, imaging tools can aid in the diagnosis, and deep learning has recently emerged as an important component of these tools. Deep learning requires little or no image preprocessing and can infer an optimal data representation from raw images without prior feature selection. As a result, they produce a more objective and less biased process. The performance of a convolutional neural network (CNN) is primarily affected by the hyperparameters chosen and the dataset used. A deep learning model for classifying Alzheimer's patients has been developed using transfer learning and optimized by Gorilla Troops for early diagnosis. This study proposes the A3C-TL-GTO framework for MRI image classification and AD detection. The A3C-TL-GTO is an empirical quantitative framework for accurate and automatic AD classification, developed and evaluated with the Alzheimer's Dataset (four classes of images) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). The proposed framework reduces the bias and variability of preprocessing steps and hyperparameters optimization to the classifier model and dataset used. Our strategy, evaluated on MRIs, is easily adaptable to other imaging methods. According to our findings, the proposed framework was an excellent instrument for this task, with a significant potential advantage for patient care. The ADNI dataset, an online dataset on Alzheimer's disease, was used to obtain magnetic resonance imaging (MR) brain images. The experimental results demonstrate that the proposed framework achieves 96.65% accuracy for the Alzheimer's Dataset and 96.25% accuracy for the ADNI dataset. Moreover, a better performance in terms of accuracy is demonstrated over other state-of-the-art approaches.

Lidocaine vs. tramadol vs. placebo wound infiltration for post-cesarean section pain relief: a randomized controlled trial.

OBJECTIVES: In low-income settings, postoperative pain relief could be challenging as a high patient/nurse ratio limits pain assessment and adequate analgesics administration. The multi-center prospective double-blinded parallel randomized controlled trial was done to compare lidocaine, tramadol, and placebo (saline) intraoperative wound infiltration to relieve post-cesarean section wound pain during the first 24 h. METHODS: Ninety-nine cases were equally randomized into three groups, each containing 33 pregnant women undergoing cesarean section under general anesthesia. During operation, the wound was infiltrated subcutaneously with 20 mL of 2% lidocaine solution in the first group, 2 mg/kg tramadol in the second group, and saline in the third group. The primary outcome was to assess the postoperative pain at 2, 4, 6, 12, and 24 h by the Yes-No-Don't Know (YNDK) Scale, while the secondary outcome was to assess the need for further postoperative analgesia. RESULTS: Wound infiltration with lidocaine or tramadol was effective in pain relief, and both were superior to placebo. Wound infiltration with tramadol was superior to lidocaine in pain relief at 2 h and up to 24 h. CONCLUSIONS: Wound infiltration with tramadol has a more prolonged pain relief effect than lidocaine in post-cesarean section pain relief in patients performing cesarean section under general anesthesia lasting up to 24 h, and both are superior to placebo in pain relief.

The impact of virtual reality on pain management during normal labor: A systematic review and meta-analysis of randomized controlled trials.

OBJECTIVE: To evaluate the impact of virtual reality on pain management during normal labor. METHODS: A systematic search was performed in September 2021 through PubMed, Cochrane Library, Scopus, and ISI web of science. We selected randomized clinical trials (RCTs) that compared virtual reality in the intervention group versus placebo or no intervention in the control group among laboring women during their normal delivery. Revman software was used for performing our meta-analysis. Our primary outcome was the pain score evaluated during the labor process by the Visual Analog Scale (VAS). Our secondary outcomes were anxiety and satisfaction scores during childbirth in addition to the duration of the first and second stages of labor. RESULTS: Eight RCTs met our inclusion criteria with a total number of 466 patients. We found virtual reality was linked to a significant reduction in the VAS pain score during labor compared to the control group (MD = -1.40, 95% CI [-1.83, -0.96], p < 0.001). The anxiety score during labor was significantly reduced among the virtual reality group (SMD = -1.15, 95% CI [-2.18, -0.12], p = 0.03). Moreover, virtual reality significantly improved the satisfaction score during labor (MD = 15.58, 95% CI [4.93, 26.22], p = 0.004). However, there were no significant differences between virtual reality and control groups regarding the duration of the first and second stages of labor. CONCLUSIONS: Virtual reality is an effective technique for reducing anxiety, increasing satisfaction, and improving pain management during normal labor.

An automated diagnosis and classification of COVID-19 from chest CT images using a transfer learning-based convolutional neural network.

Researchers have developed more intelligent, highly responsive, and efficient detection methods owing to the COVID-19 demands for more widespread diagnosis. The work done deals with developing an AI-based framework that can help radiologists and other healthcare professionals diagnose COVID-19 cases at a high level of accuracy. However, in the absence of publicly available CT datasets, the development of such AI tools can prove challenging. Therefore, an algorithm for performing automatic and accurate COVID-19 classification using Convolutional Neural Network (CNN), pre-trained model, and Sparrow search algorithm (SSA) on CT lung images was proposed. The pre-trained CNN models used are SeresNext50, SeresNext101, SeNet154, MobileNet, MobileNetV2, MobileNetV3Small, and MobileNetV3Large. In addition, the SSA will be used to optimize the different CNN and transfer learning(TL) hyperparameters to find the best configuration for the pre-trained model used and enhance its performance. Two datasets are used in the experiments. There are two classes in the first dataset, while three in the second. The authors combined two publicly available COVID-19 datasets as the first dataset, namely the COVID-19 Lung CT Scans and COVID-19 CT Scan Dataset. In total, 14,486 images were included in this study. The authors analyzed the Large COVID-19 CT scan slice dataset in the second dataset, which utilized 17,104 images. Compared to other pre-trained models on both classes datasets, MobileNetV3Large pre-trained is the best model. As far as the three-classes dataset is concerned, a model trained on SeNet154 is the best available. Results show that, when compared to other CNN models like LeNet-5 CNN, COVID faster R-CNN, Light CNN, Fuzzy + CNN, Dynamic CNN, CNN and Optimized CNN, the proposed Framework achieves the best accuracy of 99.74% (two classes) and 98% (three classes).

Value of intrauterine platelet-rich concentrates in patients with intrauterine adhesions after hysteroscopy: A systematic review and meta-analysis of randomized controlled trials.

OBJECTIVE: To evaluate the value of intrauterine platelet-rich concentrates among patients with intrauterine adhesions (IUAs) after hysteroscopic adhesiolysis. METHODS: Four different databases (PubMed, Cochrane Library, Scopus, and ISI web of science) were searched for the available studies from inception to November 2021. We selected randomized clinical trials (RCTs) that compared platelet-rich concentrates in the intervention group versus no injection of platelet-rich concentrates in the control group among women with intrauterine adhesions after operative hysteroscopy. Revman software was utilized for performing our meta-analysis. Our primary outcomes were the adhesion score and incidence of recurrence of severe intrauterine adhesions postoperatively. Our secondary outcomes were the clinical pregnancy rate, menstrual flow duration in days, and menstrual flow amount (number of pads). RESULTS: Five RCTs met our inclusion criteria with a total number of 329 patients. We found that platelet-rich concentrates were linked to a significant reduction in the postoperative adhesion score (MD = -1.00, 95% CI [-1.68, -0.32], p = 0.004). Moreover, there was a significant reduction in the incidence of severe IUAs recurrence among the platelet-rich concentrates group (7.6%) compared to the control group (23.4%) after hysteroscopy (p = 0.001). The clinical pregnancy rate was significantly increased among the platelet-rich concentrates group (37.1%) in comparison with the control group (20.7%) after hysteroscopic adhesiolysis (p = 0.008). There were significant improvements in the menstrual flow duration and amount among the platelet-rich concentrates group (p < 0.001). CONCLUSIONS: Intrauterine placement of platelet-rich concentrates is an effective method for the treatment of intrauterine adhesions after hysteroscopy.

Accurate detection of Covid-19 patients based on Feature Correlated Naïve Bayes (FCNB) classification strategy.

The outbreak of Coronavirus (COVID-19) has spread between people around the world at a rapid rate so that the number of infected people and deaths is increasing quickly every day. Accordingly, it is a vital process to detect positive cases at an early stage for treatment and controlling the disease from spreading. Several medical tests had been applied for COVID-19 detection in certain injuries, but with limited efficiency. In this study, a new COVID-19 diagnosis strategy called Feature Correlated Naïve Bayes (FCNB) has been introduced. The FCNB consists of four phases, which are; Feature Selection Phase (FSP), Feature Clustering Phase (FCP), Master Feature Weighting Phase (MFWP), and Feature Correlated Naïve Bayes Phase (FCNBP). The FSP selects only the most effective features among the extracted features from laboratory tests for both COVID-19 patients and non-COVID-19 people by using the Genetic Algorithm as a wrapper method. The FCP constructs many clusters of features based on the selected features from FSP by using a novel clustering technique. These clusters of features are called Master Features (MFs) in which each MF contains a set of dependent features. The MFWP assigns a weight value to each MF by using a new weight calculation method. The FCNBP is used to classify patients based on the weighted Naïve Bayes algorithm with many modifications as the correlation between features. The proposed FCNB strategy has been compared to recent competitive techniques. Experimental results have proven the effectiveness of the FCNB strategy in which it outperforms recent competitive techniques because it achieves the maximum (99%) detection accuracy.

Deep Learning Approach for Early Detection of Alzheimer's Disease.

Alzheimer's disease (AD) is a chronic, irreversible brain disorder, no effective cure for it till now. However, available medicines can delay its progress. Therefore, the early detection of AD plays a crucial role in preventing and controlling its progression. The main objective is to design an end-to-end framework for early detection of Alzheimer's disease and medical image classification for various AD stages. A deep learning approach, specifically convolutional neural networks (CNN), is used in this work. Four stages of the AD spectrum are multi-classified. Furthermore, separate binary medical image classifications are implemented between each two-pair class of AD stages. Two methods are used to classify the medical images and detect AD. The first method uses simple CNN architectures that deal with 2D and 3D structural brain scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset based on 2D and 3D convolution. The second method applies the transfer learning principle to take advantage of the pre-trained models for medical image classifications, such as the VGG19 model. Due to the COVID-19 pandemic, it is difficult for people to go to hospitals periodically to avoid gatherings and infections. As a result, Alzheimer's checking web application is proposed using the final qualified proposed architectures. It helps doctors and patients to check AD remotely. It also determines the AD stage of the patient based on the AD spectrum and advises the patient according to its AD stage. Nine performance metrics are used in the evaluation and the comparison between the two methods. The experimental results prove that the CNN architectures for the first method have the following characteristics: suitable simple structures that reduce computational complexity, memory requirements, overfitting, and provide manageable time. Besides, they achieve very promising accuracies, 93.61% and 95.17% for 2D and 3D multi-class AD stage classifications. The VGG19 pre-trained model is fine-tuned and achieved an accuracy of 97% for multi-class AD stage classifications.

Ambient Healthcare Approach with Hybrid Whale Optimization Algorithm and Naïve Bayes Classifier.

There is a crucial need to process patient's data immediately to make a sound decision rapidly; this data has a very large size and excessive features. Recently, many cloud-based IoT healthcare systems are proposed in the literature. However, there are still several challenges associated with the processing time and overall system efficiency concerning big healthcare data. This paper introduces a novel approach for processing healthcare data and predicts useful information with the support of the use of minimum computational cost. The main objective is to accept several types of data and improve accuracy and reduce the processing time. The proposed approach uses a hybrid algorithm which will consist of two phases. The first phase aims to minimize the number of features for big data by using the Whale Optimization Algorithm as a feature selection technique. After that, the second phase performs real-time data classification by using Naïve Bayes Classifier. The proposed approach is based on fog Computing for better business agility, better security, deeper insights with privacy, and reduced operation cost. The experimental results demonstrate that the proposed approach can reduce the number of datasets features, improve the accuracy and reduce the processing time. Accuracy enhanced by average rate: 3.6% (3.34 for Diabetes, 2.94 for Heart disease, 3.77 for Heart attack prediction, and 4.15 for Sonar). Besides, it enhances the processing speed by reducing the processing time by an average rate: 8.7% (28.96 for Diabetes, 1.07 for Heart disease, 3.31 for Heart attack prediction, and 1.4 for Sonar).

An optimized transfer learning-based approach for automatic diagnosis of COVID-19 from chest x-ray images.

Accurate and fast detection of COVID-19 patients is crucial to control this pandemic. Due to the scarcity of COVID-19 testing kits, especially in developing countries, there is a crucial need to rely on alternative diagnosis methods. Deep learning architectures built on image modalities can speed up the COVID-19 pneumonia classification from other types of pneumonia. The transfer learning approach is better suited to automatically detect COVID-19 cases due to the limited availability of medical images. This paper introduces an Optimized Transfer Learning-based Approach for Automatic Detection of COVID-19 (OTLD-COVID-19) that applies an optimization algorithm to twelve CNN architectures to diagnose COVID-19 cases using chest x-ray images. The OTLD-COVID-19 approach adapts Manta-Ray Foraging Optimization (MRFO) algorithm to optimize the network hyperparameters' values of the CNN architectures to improve their classification performance. The proposed dataset is collected from eight different public datasets to classify 4-class cases (COVID-19, pneumonia bacterial, pneumonia viral, and normal). The experimental result showed that DenseNet121 optimized architecture achieves the best performance. The evaluation results based on Loss, Accuracy, F1-score, Precision, Recall, Specificity, AUC, Sensitivity, IoU, and Dice values reached 0.0523, 98.47%, 0.9849, 98.50%, 98.47%, 99.50%, 0.9983, 0.9847, 0.9860, and 0.9879 respectively.