Common pediatric surgical conditions and associated health-seeking behaviors in Pakistan: An urban and rural comparative assessment.

Approximately five billion people do not have access to necessary surgical treatment globally and up to 85% of children in LMICs are affected with conditions requiring surgical care by the age of 15 years. It is crucial to identify common surgical conditions in children in Pakistan to inform healthcare professionals and policymakers for effective resource allocation. This representative cross-sectional household survey conducted on children aged 5-10 years assessed existing surgical diseases and healthcare-seeking behaviors in the two largest provinces (Sindh and Punjab) of Pakistan. The data was collected through a validated cross-sectional survey tool [Surgeons OverSeas Assessment of Surgical Need (SOSAS)]. Caregivers were asked about their child's recent and past surgical conditions in six distinct anatomical regions and pictures were taken of identified conditions after appropriate consent for further diagnosis. Health-seeking behaviors including the kind of treatment sought, the nature of care received, and the reasons for not receiving care were noted. 13.5% of children surveyed reported a surgical condition, with a similar distribution across urban (13.2%) and rural (13.7) areas and the most common cause was trauma. The greatest number of surgical conditions were found to be on the head and neck region (57.7%), while the back accounted for the least number of conditions (1.7%). Our results outline a need for organizing all entities (governmental, non-governmental, and private) involved in child health to ensure efficient resource allocation to cater to existing surgical problems.

Optimized efficient attention-based network for facial expressions analysis in neurological health care.

Facial Expression Analysis (FEA) plays a vital role in diagnosing and treating early-stage neurological disorders (NDs) like Alzheimer's and Parkinson's. Manual FEA is hindered by expertise, time, and training requirements, while automatic methods confront difficulties with real patient data unavailability, high computations, and irrelevant feature extraction. To address these challenges, this paper proposes a novel approach: an efficient, lightweight convolutional block attention module (CBAM) based deep learning network (DLN) to aid doctors in diagnosing ND patients. The method comprises two stages: data collection of real ND patients, and pre-processing, involving face detection and an attention-enhanced DLN for feature extraction and refinement. Extensive experiments with validation on real patient data showcase compelling performance, achieving an accuracy of up to 73.2%. Despite its efficacy, the proposed model is lightweight, occupying only 3MB, making it suitable for deployment on resource-constrained mobile healthcare devices. Moreover, the method exhibits significant advancements over existing FEA approaches, holding tremendous promise in effectively diagnosing and treating ND patients. By accurately recognizing emotions and extracting relevant features, this approach empowers medical professionals in early ND detection and management, overcoming the challenges of manual analysis and heavy models. In conclusion, this research presents a significant leap in FEA, promising to enhance ND diagnosis and care.The code and data used in this work are available at: https://github.com/munsif200/Neurological-Health-Care.

Efficient leukocytes detection and classification in microscopic blood images using convolutional neural network coupled with a dual attention network.

Leukocytes, also called White Blood Cells (WBCs) or leucocytes, are the cells that play a pivotal role in human health and are vital indicators of diseases such as malaria, leukemia, AIDS, and other viral infections. WBCs detection and classification in blood smears offers insights to pathologists, aiding diagnosis across medical conditions. Traditional techniques, including manual counting, detection, classification, and visual inspection of microscopic images by medical professionals, pose challenges due to their labor-intensive nature. However, traditional methods are time consuming and sometimes susceptible to errors. Here, we propose a high-performance convolutional neural network (CNN) coupled with a dual-attention network that efficiently detects and classifies WBCs in microscopic thick smear images. The main aim of this study was to enhance clinical hematology systems and expedite medical diagnostic processes. In the proposed technique, we utilized a deep convolutional generative adversarial network (DCGAN) to overcome the limitations imposed by limited training data and employed a dual attention mechanism to improve accuracy, efficiency, and generalization. The proposed technique achieved overall accuracy rates of 99.83%, 99.35%, and 99.60% for the peripheral blood cell (PBC), leukocyte images for segmentation and classification (LISC), and Raabin-WBC benchmark datasets, respectively. Our proposed approach outperforms state-of-the-art methods in terms of accuracy, highlighting the effectiveness of the strategies employed and their potential to enhance diagnostic capabilities and advance real-world healthcare practices and diagnostic systems.

Three-dimensional surface area analyses of developing maxillary second premolar root apices for age estimation using CBCT images.

Three-dimensional surface area analyses of developing root apices for age estimation in children and young adults have shown promising results. The current study aimed to apply this three-dimensional method to develop a regression model for estimating age in Malaysian children aged 7 to 14 using developing maxillary second premolars. A training sample of 155 cone-beam computed tomography scans (83 Malays and 72 Chinese) was analysed, and the formula was subsequently validated on an independent sample of 92 cone-beam computed tomography scans (45 Malays and 47 Chinese). The results showed a strong correlation (r = 94 %) between the chronological age as a dependent variable and the predictor variables, including root surface area of the apex, sex, ethnicity, and root development status (open/closed apices). For this model, the predictor variables accounted for 88.4 % of the variation in age except sex and ethnicity. A mean absolute error value of 0.42 indicated that this model can be reliably used for Malaysian children. In conclusion, this study recognises the method of three-dimensional surface area analyses as a valuable tool for age estimation in forensic and clinical practice. Further studies are highly recommended to assess its effectiveness across different demographic groups.

Revealing analgesic and anxiolytic potentials of synthetic benzimidazole analogues: An in-vivo and in-silico study.

Certain drugs have potential to affect and alter individual's behavior. On the other hand, pain is a complex phenomenon with various treatment options; analgesic medicines are the primary source. Therefore, this study was based on examining some of the benzimidazole analogues for their analgesic as well as behavioral potential following Tail immersion test and Open field test respectively. In addition, molecular docking was performed to find the interaction of these compounds with the active site using AutoDock Vina which was further visualized through Discovery Studio Visualizer. It was seen that the cyano-methyl benzimidazole derivatives (CMB1-CMB3) showed relief in pain as compared to benzimidazole derivatives (BI1-BI3), CMB2 demonstrated highly potent analgesic effect. Likewise, all structures except BI1 displayed increase locomotion during open field test and can be offered as anxiolytic compounds. Almost all derivatives showed improve binding energies for the tested proteins where the high analgesic action of CMB2 might be correlated to its high binding affinity and interaction at µOR. It was also noticed that all structures except BI showed possible binding interaction with GABAA receptor and hence possessed anxiolytic like potential. Thus, this study offered benzimidazole analogues for further drug development of analgesic and anxiolytic like compounds.

Bayesian AEWMA control chart under ranked set sampling with application to reliability engineering.

The article introduces a novel Bayesian AEWMA Control Chart that integrates different loss functions (LFs) like the square error loss function and Linex loss function under an informative prior for posterior and posterior predictive distributions, implemented across diverse ranked set sampling (RSS) designs. The main objective is to detect small to moderate shifts in the process mean, with the average run length and standard deviation of run length serving as performance measures. The study employs a hard bake process in semiconductor production to demonstrate the effectiveness of the proposed chart, comparing it with existing control charts through Monte Carlo simulations. The results underscore the superiority of the proposed approach, particularly under RSS designs compared to simple random sampling (SRS), in identifying out-of-control signals. Overall, this study contributes a comprehensive method integrating various LFs and RSS schemes, offering a more precise and efficient approach for detecting shifts in the process mean. Real-world applications highlight the heightened sensitivity of the suggested chart in identifying out-of-control signals compared to existing Bayesian charts using SRS.

In vitro and in vivo antioxidant therapeutic evaluation of phytochemicals from different parts of Dodonaea viscosa Jacq.

Introduction: Natural antioxidants are vital to promote health and treat critical disease conditions in the modern healthcare system. This work adds to the index of natural medicines by exploring the antioxidant potential of Dodonaea viscosa Jacq. (Plant-DV). Material and Methods: The aqueous extract of leaves and flower-containing seeds from plant-DV in freshly prepared phosphate buffer is evaluated for antioxidant potential. In vitro antioxidant potential of the nascent and oxidatively stressed extracts was analyzed through glutathione (GSH) assay, hydrogen peroxide (H2O2) scavenging effect, glutathione-S-transferase (GST) assay, and catalase (CAT) activity. In vivo therapeutic assessment is performed in Wistar Albino rats using vitamin C as a positive control. The livers and kidneys of individual animals are probed for glutathione, glutathione-S-transferase, and catalase activities. Results: flower-containing seeds have GSH contents (59.61 µM) and leaves (32.87 µM) in the fresh aqueous extracts. The hydrogen peroxide scavenging effect of leaves is superior to flower-containing seeds with 17.25% and 14.18% respectively after 30 min incubation. However, oxidatively stressed extracts with Ag(I) and Hg(II) show declining GSH and GST levels. The plant extracts are non-toxic in rats at 5000 mg/Kg body weight. Liver and kidneys homogenate reveal an increase in GSH, GST, and CAT levels after treatment with 150 ± 2 mg/kg and 300 ± 2 mg/kg body weight plant extract compared with normal saline-treated negative and vitamin C treated positive control. Discussion: The crude aqueous extracts of leaves and flower-containing seeds of plant-DV show promising antioxidant potential both in in vitro and in vivo evaluation.

A fuzzy logic based explicit declustering technique.

During the spatial estimation of geoscience resource variables, the quantity or quality of minerals and hydrocarbons can be represented by a broad range of properties, including geochemical, geotechnical, or other physical measures. Preferential sampling within the region of interest causes biased global parameters due to clustered sampling patterns. Unbiased sample distribution is essential for conducting conditional simulations to model uncertainty of spatially distributed attributes, e.g. geochemical content of metal or porosity. Therefore, declustering procedures are applied during resource estimation to estimate an unbiased statistical distribution of the measured variables. Traditional techniques such as cell declustering do not consider grade clustering, i.e., the similarity of measured variables within a spatially clustered neighbourhood. This paper presents a declustering technique that explicitly accounts for spatial clustering and the similarity of measured samples' attributes within these spatially clustered samples. In the proposed method, samples were first classified explicitly into spatial and geochemical (grade) clusters using the Fuzzy c-means algorithm. Declustering weights were derived using the Mamdani based Fuzzy Inference System using various T-norm operations. The technique was applied to the publicly available GSLib and Walker Lake datasets. It was shown that the proposed scheme produced more accurate results than those obtained with the traditional declustering technique.

Species composition, seasonal abundance and population dynamics of predatory spiders from cotton field plots of irrigated and semi-arid regions of Punjab, Pakistan.

The purpose of the current study was to document the variety of predatory spider species present in the cotton fields of two major cotton-producing districts in Punjab, Pakistan, as well as the population dynamics of those spiders. The research was carried out between May and October 2018 and 2019. Manual picking, visual counting, pitfall traps, and sweep netting were the procedures used to collect samples on a biweekly basis. A total of 10,684 spiders comprising 39 species, 28 genera, and 12 families were documented. Araneidae and Lycosidae families contributed a major share to the overall catch of spiders, accounting for 58.55 percent of the total. The Araneidae family's Neoscona theisi ) was the most dominating species, accounting for 12.80% of the total catch and being the dominant species. The estimated spider species diversity was 95%. Their densities were changed over time in the study, but they were highest in the second half of September and the first half of October of both years. The cluster analysis distinguished the two districts and the sites chosen. There was a relationship between humidity and rainfall and the active density of spiders; however, this association was not statistically significant. It is possible to increase the population of spiders in an area by reducing the number of activities detrimental to spiders and other useful arachnids. Spiders are considered effective agents of biological control throughout the world. The findings of the current study will help in the formulation of pest management techniques that can be implemented in cotton growing regions all over the world.

Modelling Electricity Consumption During the COVID19 Pandemic: Datasets, Models, Results and a Research Agenda.

The COVID19 pandemic has impacted the global economy, social activities, and Electricity Consumption (EC), affecting the performance of historical data-based Electricity Load Forecasting (ELF) algorithms. This study thoroughly analyses the pandemic's impact on these models and develop a hybrid model with better prediction accuracy using COVID19 data. Existing datasets are reviewed, and their limited generalization potential for the COVID19 period is highlighted. A dataset of 96 residential customers, comprising 36 and six months before and after the pandemic, is collected, posing significant challenges for current models. The proposed model employs convolutional layers for feature extraction, gated recurrent nets for temporal feature learning, and a self-attention module for feature selection, leading to better generalization for predicting EC patterns. Our proposed model outperforms existing models, as demonstrated by a detailed ablation study using our dataset. For instance, it achieves an average reduction of 0.56% & 3.46% in MSE, 1.5% & 5.07% in RMSE, and 11.81% & 13.19% in MAPE over the pre- and post-pandemic data, respectively. However, further research is required to address the varied nature of the data. These findings have significant implications for improving ELF algorithms during pandemics and other significant events that disrupt historical data patterns.

Health behaviors and care seeking practices for childhood diarrhea and pneumonia in a rural district of Pakistan: A qualitative study.

Diarrhea and pneumonia are the leading causes of morbidity and mortality in children under five, and Pakistan is amongst the countries with the highest burden and low rates of related treatment coverage. We conducted a qualitative study as part of the formative phase to inform the design of the Community Mobilization and Community Incentivization (CoMIC) cluster randomized control trial (NCT03594279) in a rural district of Pakistan. We conducted in-dept interviews and focused group discussions with key stakeholders using a semi-structured study guide. Data underwent rigorous thematic analysis and major themes identified included socio-cultural dynamics, community mobilization and incentives, behavioral patterns and care seeking practices for childhood diarrhea and pneumonia, infant and young child feeding practices (IYCF), immunization, water sanitation and hygiene (WASH) and access to healthcare. This study highlights shortcomings in knowledge, health practices and health systems. There was to a certain extent awareness of the importance of hygiene, immunization, nutrition, and care-seeking, but the practices were poor due to various reasons. Poverty and lifestyle were considered prime factors for poor health behaviors, while health system inefficiencies added to these as rural facilities lack equipment and supplies, resources, and funding. The community identified that intensive inclusive community engagement and demand creation strategies tied to conditioned short term tangible incentives could help foster behavior change.

SSR identification and phylogenetic analysis in four plant species based on complete chloroplast genome sequences.

The effective utilization of traditional Chinese medicine (TCM) has been challenged by the difficulty to accurately distinguish between similar plant varieties. The stability and conservation of the chloroplast genome can aid in resolving genotypes. Previous studies using nuclear sequences and molecular markers have not effectively differentiated the species from related taxa, such as Machilus leptophylla, Hanceola exserta, Rubus bambusarum, and Rubus henryi. This study aimed to characterize the chloroplast genomes of these four plant species, and analyze their simple sequence repeats (SSRs) and phylogenetic positions. The results demonstrated the four chloroplast genomes consisted of 152.624 kb, 153.296 kb, 156.309 kb, and 158.953 kb in length, involving 124, 130, 129, and 131 genes, respectively. They also contained four specific regions with mononucleotide being the class with the most members. Moreover, these repeating types of SSR were various in individual class. Phylogenetic analysis showed that M. leptophylla was clustered with M. yunnanensis, and H. exserta was confirmed as belonging to the family Ocimeae. Additionally, R. bambusarum and R. henryi were grouped together but differed in their SSR features, indicating that they were not the same species. This research provides evidence for resolving species and contributes new genetic information for further studies.

Effect of varying thickness properties of the slow release fertilizer films on morphology, biodegradability, urea release, soil health, and plant growth.

Green biomass is a renewable and biodegradable material that has the potential use to trap urea to develop a high-efficiency urea fertilizer for crops' better performance. Current work examined the morphology, chemical composition, biodegradability, urea release, soil health, and plant growth effects of the SRF films subjected to changes in the thickness of 0.27, 0.54, and 1.03 mm. The morphology was examined by Scanning Electron Microscopy, chemical composition was analyzed by Infrared Spectroscopy, and biodegradability was assessed through evolved CO2 and CH4 quantified through Gas Chromatography. The chloroform fumigation technique was used for microbial growth assessment in the soil. The soil pH and redox potential were also measured using a specific probe. CHNS analyzer was used to calculate the total carbon and total nitrogen of the soil. A plant growth experiment was conducted on the Wheat plant (Triticum sativum). The thinner the films, the more they supported the growth and penetration of the soil's microorganisms mainly the species of fungus possibly due to the presence of lignin in films. The fingerprint regions of the infrared spectrum of SRF films showed all films in soil changed in their chemical composition due to biodegradation but the increase in the thickness possibly provides resistance to the films' losses. The higher thickness of the film delayed the rate and time for biodegradation and the release of methane gas in the soil. The 1.03 mm film (47% in 56 days) and 0.54 mm film (35% in 91 days) showed the slowest biodegradability as compared to the 0.27 mm film with the highest losses (60% in 35 days). The slow urea release is more affected by the increase in thickness. The Korsymer Pappas model with release exponent value of < 0.5 explained the release from the SRF films followed the quasi-fickian diffusion and also reduced the diffusion coefficient for urea. An increase in the pH and decrease in the redox potential of the soil is correlated with higher total organic content and total nitrogen in the soil in response to amending SRF films with variable thickness. Growth of the wheat plant showed the highest average plant length, leaf area index and grain per plant in response to the increase in the film's thickness. This work developed an important knowledge to enhance the efficiency of film encapsulated urea that can better slow the urea release if the thickness is optimized.

ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans.

Automated diagnostic techniques based on computed tomography (CT) scans of the chest for the coronavirus disease (COVID-19) help physicians detect suspected cases rapidly and precisely, which is critical in providing timely medical treatment and preventing the spread of epidemic outbreaks. Existing capsule networks have played a significant role in automatic COVID-19 detection systems based on small datasets. However, extracting key slices is difficult because CT scans typically show many scattered lesion sections. In addition, existing max pooling sampling methods cannot effectively fuse the features from multiple regions. Therefore, in this study, we propose an attention capsule sampling network (ACSN) to detect COVID-19 based on chest CT scans. A key slices enhancement method is used to obtain critical information from a large number of slices by applying attention enhancement to key slices. Then, the lost active and background features are retained by integrating two types of sampling. The results of experiments on an open dataset of 35,000 slices show that the proposed ACSN achieve high performance compared with state-of-the-art models and exhibits 96.3% accuracy, 98.8% sensitivity, 93.8% specificity, and 98.3% area under the receiver operating characteristic curve.

A reference-grade genome assembly for Gossypium bickii and insights into its genome evolution and formation of pigment glands and gossypol.

The pigment gland is a morphological characteristic of Gossypium and its related genera. Gossypium bickii (G1) is characterized by delayed pigment gland morphogenesis in the cotyledons. In this study, a reference-grade genome of G1 was generated, and comparative genomics analysis showed that G1 was closest to Gossypium australe (G2), followed by A- and D-genome species. Two large fragment translocations in chromosomes 5 and 13 were detected between the G genome and other Gossypium genomes and were unique to the G1 and G2 genomes. Compared with the G2 genome, two large fragment inversions in chromosomes 12 and 13 were detected in G1. According to the phylogeny, divergence time, and similarity analysis of nuclear and chloroplast genomes, G1 was formed by hybridization between Gossypium sturtianum (C1) and a common ancestor of G2 and Gossypium nelsonii (G3). The coordinated expression patterns of pigment gland formation (GoPGF) and gossypol biosynthesis genes in G1 were verified to be consistent with its phenotype, and nine genes that were related to the process of pigment gland formation were identified. A novel gene, GbiCYP76B6, regulated by GoPGF, was found to affect gossypol biosynthesis. These findings offer insights into the origin and evolution of G1 and its mechanism of pigment gland formation and gossypol biosynthesis.

AWANet: Attentive-Aware Wide-Kernels Asymmetrical Network with Blended Contour Information for Salient Object Detection.

Although deep learning-based techniques for salient object detection have considerably improved over recent years, estimated saliency maps still exhibit imprecise predictions owing to the internal complexity and indefinite boundaries of salient objects of varying sizes. Existing methods emphasize the design of an exemplary structure to integrate multi-level features by employing multi-scale features and attention modules to filter salient regions from cluttered scenarios. We propose a saliency detection network based on three novel contributions. First, we use a dense feature extraction unit (DFEU) by introducing large kernels of asymmetric and grouped-wise convolutions with channel reshuffling. The DFEU extracts semantically enriched features with large receptive fields and reduces the gridding problem and parameter sizes for subsequent operations. Second, we suggest a cross-feature integration unit (CFIU) that extracts semantically enriched features from their high resolutions using dense short connections and sub-samples the integrated information into different attentional branches based on the inputs received for each stage of the backbone. The embedded independent attentional branches can observe the importance of the sub-regions for a salient object. With the constraint-wise growth of the sub-attentional branches at various stages, the CFIU can efficiently avoid global and local feature dilution effects by extracting semantically enriched features via dense short-connections from high and low levels. Finally, a contour-aware saliency refinement unit (CSRU) was devised by blending the contour and contextual features in a progressive dense connected fashion to assist the model toward obtaining more accurate saliency maps with precise boundaries in complex and perplexing scenarios. Our proposed model was analyzed with ResNet-50 and VGG-16 and outperforms most contemporary techniques with fewer parameters.

Facile Synthesis of La- and Chitosan-Doped CaO Nanoparticles and Their Evaluation for Catalytic and Antimicrobial Potential with Molecular Docking Studies.

In the current study, a low-cost and straightforward coprecipitation technique was adopted to synthesize CaO and La-doped CS/CaO NPs. Different weight ratios (2 and 4) of La were doped into fixed amounts of CS and CaO. Synthesized samples exhibited outstanding catalytic performance by degrading methylene blue (MB) in a highly efficient manner. The X-ray diffraction technique detected the presence of a cubic phase of CaO and a decrease in crystallite size of the samples with the addition of La. Fourier transform infrared spectroscopy confirmed the presence of the dopant and the base material with functional groups at 712 cm-1. A decrease in the absorption intensity of doped CaO was observed with an increasing amount of dopants La and CS accompanied by a blueshift leading to an increase in the band gap energy from 4.17 to 4.42 eV, as recorded with an ultraviolet-visible spectrophotometer. The presence of dopants (La and CS) and the evaluation of the elemental constitution of Ca and O were supported with the energy-dispersive spectroscopy technique. In an acidic medium, the catalytic activity against the MB dye was reduced (93.8%) for 4% La-doped CS/CaO. For La-doped CS/CaO, vast inhibition domains ranged within 4.15-4.70 and 5.82-8.05 mm against Escherichia coli while 4.15-5.20 and 6.65-13.10 mm against Staphylococcus aureus (S. aureus) at the least and maximum concentrations, correspondingly. In silico molecular docking studies suggested these nanocomposites of chitosan as possible inhibitors against the enoyl-acyl carrier protein reductase (FabI) from S. aureus.

Dental age estimation of Malaysian Indian children and adolescents: applicability of Chaillet and Demirjian's modified method using artificial neural network.

BACKGROUND: Recognising the importance of dental age (DA) estimation in forensic investigations, a variety of methods abound in the literature due to population-specific attributes. A reference eight-tooth method developed by Chaillet and Demirjian estimated the DA of children and adolescents. AIM: This study aims to investigate the applicability of Chaillet and Demirjian's method among Malaysian Indians aged 5.00-17.99 years. SUBJECTS AND METHODS: Dental panoramic tomographs of Malaysian Indians aged 5.00-17.99 years were statistically analysed using paired t-test and artificial neural networks multilayer perceptron (ANN-MLP). RESULTS: A total of 1015 dental panoramic tomographs were analysed. Paired t-test analysis against the reference dental maturity scores revealed underestimation of DA in boys of 1.68 years and girls of 2.56 years indicating inaccurate age estimation. A population-specific prediction model with a new set of dental maturity scores was established on Chaillet and Demirjian's scores using ANN-MLP. The new dental maturity scores showed accurate estimation of DA with differences between CA and DA being 12 and 25 days for boys and girls, respectively. Furthermore, a new DA prediction formula was developed using regression analysis following the establishment of new dental scores based on ANN-MLP. CONCLUSION: A novel Malaysian Indian-specific prediction model that demonstrated accurate DA estimation was established.

Dental age estimation of Malaysian children: a comparison of two-dimensional versus three-dimensional imaging analyses of the developing root apices.

AIM: This study compared the effectiveness of the three-dimensional (3D) cone beam computed tomography (CBCT) method of age estimation developed by Asif et al. with two-dimensional Cameriere's method. SUBJECTS AND METHODS: CBCT images belonging to 129 Malaysian Chinese and Malay ethnic groups aged 7-14 years were investigated and analysed. RESULTS: The results indicated a strong correlation between chronological age and the predictor variables for both Cameriere's (r = 0.984) and Asif's (r = 0.988) methods of age estimation. Fisher Z test analysis indicated no statistically significant difference in the correlation values between the two methods. Mean absolute error (MAE) value of 0.613 was observed for Cameriere's and 0.290 was observed for Asif's method. CONCLUSIONS: The results indicated that the methods of age estimation from both Asif et al. and Cameriere et al. are applicable on Malaysian children. However, Asif et al.'s 3D CBCT method of age estimation resulted in greater accuracy and reliability in estimating chronological age.

A deep fuzzy model for diagnosis of COVID-19 from CT images.

From early 2020, a novel coronavirus disease pneumonia has shown a global "pandemic" trend at an extremely fast speed. Due to the magnitude of its harm, it has become a major global public health event. In the face of dramatic increase in the number of patients with COVID-19, the need for quick diagnosis of suspected cases has become particularly critical. Therefore, this paper constructs a fuzzy classifier, which aims to detect infected subjects by observing and analyzing the CT images of suspected patients. Firstly, a deep learning algorithm is used to extract the low-level features of CT images in the COVID-CT dataset. Subsequently, we analyze the extracted feature information with attribute reduction algorithm to obtain features with high recognition. Then, some key features are selected as the input for the fuzzy diagnosis model to the training model. Finally, several images in the dataset are used as the test set to test the trained fuzzy classifier. The obtained accuracy rate is 94.2%, and the F1-score is 93.8%. Experimental results show that, compared with the deep learning diagnosis methods widely used in medical image analysis, the proposed fuzzy model improves the accuracy and efficiency of diagnosis, which consequently helps to curb the spread of COVID-19.