Preparation and investigation of Montmorillonite-K10 Polyaniline nanocomposites for optoelectronic applications.

One-dimensional polyaniline (PANI) nanostructures were synthesized in situ in the presence of two-dimensional (2D) Montmorillonite (MMT) clay nanosheets. Strong interactions between the polymer and MMT platelets in the nanocomposites were confirmed through spectroscopic studies. X-ray diffraction and scanning electron microscopic studies revealed the clay's profound effect on the polymer's crystallinity and morphology. The clay nanosheets induced higher crystallinity and well-defined nanorod morphology in the polymer structure. Consequently, the nanocomposite showed an electrical conductivity of 8.72 S/cm, closer to that of the pristine polymer (8.97 S/cm), despite the presence of highly insulting clay material. Surprisingly, a notable decrease in the optical bandgap of the polymer from 3.73 to 2.88 eV of the nanocomposite was also observed. This novel integration of a narrow band gap and high conductivity in PANI/MMT nanocomposites can expand their utility for visible light interactions in areas encompassing photocatalysis, photovoltaics, electro/photochromism, and related technologies.

Impact of automobile exhaust on biochemical and genomorphic characteristics of Mimusops elengi L. growing along roadsides of Lahore city, Pakistan.

Automobile exhaust releases different types of pollutants that are at great risk to the air quality of the environment and incidental distress to the nature of roadside plants. Mimusops elengi L. is an evergreen medicinal tree cultivated along the roadside of Lahore City. This research aimed to investigate physiological, morphological and genomorphic characteristics of M. elengi under the influence of air pollution from vehicles. Healthy and mature leaves were collected from trees on Canal Bank and Mall roads of Lahore as the experimental sites and control sites were 20 km away from the experimental site. Different physiochemical, morphological, air pollution tolerance index (APTI) and molecular analysis for the detection of DNA damage were performed through comet assay. The results demonstrated the mean accumulated Cd, Pb, Cu and Ni heavy metal contents on the leaves were higher than the control plants (1.27, 3.22, 1.32 and 1.46 µg mg-1). APTI of trees was 9.04. Trees in these roads significantly (p < 0.01) had a lower leaf area, petiole length and leaf dry matter content in comparison to control site. Increased comet tail showed that DNA damage was higher for roadside trees than trees in the control area. For tolerance of air pollution, it necessary to check the APTI value for the M. elengi at the polluted road side of Lahore city. For long-term screening, the source and type of pollutants and consistent monitoring of various responses given by the trees should be known.

Scalable synthesis of high-quality, reduced graphene oxide with a large C/O ratio and its dispersion in a chemically modified polyimide matrix for electromagnetic interference shielding applications.

High-purity reduced graphene oxide (RGO or rGO) with appreciable conductivity is a desired conductive filler for lightweight polymer composites used in coatings, electronics, catalysts, electromagnetic interference (EMI) shielding, and energy storage devices. However, the intrinsic conductivity and the uniform dispersion of RGO in relatively polar matrices are challenging, leading to poor overall conductivity and performance of the composite material. The reported study improved the RGO intrinsic conductivity by increasing its C/O ratio while also simultaneously enhancing its compatibility with the polyimide (PI) matrix through ester linkages for better dispersion. A two-step reduction method drastically increased the number of structural defects and carbon content in the resulting RGO, corresponding to a maximum ID/IG and C/O of 1.54 and ∼87, respectively. Moreover, the 2D nanosheets with limited hydroxyl (-OH) groups effectively interacted with anhydride-terminated polyamic acid (AT-PAA) through chemical linkages to make high-performance RGO/PI nanocomposites. Consequently, the polymer matrix composites possessed the highest direct current conductivity of 15.27 ± 0.61 S cm-1 for 20 wt% of the prepared RGO. Additionally, the composite material was highly stiff (3.945 GPa) yet flexible (easily bent through 180°), lightweight (∼0.34 g cm-3), and capable of forming thin films (162 ± 15 µm). Unlike most polymer matrix composites, it showcased one of its class's highest thermal stabilities (a weight loss of only 5% at 638 °C). Ultimately, the composite performed as an effective electromagnetic interference (EMI) shielding material in the X-Band (8 to 12 GHz), demonstrating outstanding shielding effectiveness (SE), shielding effectiveness per unit thickness (SEt), specific shielding effectiveness (SSE), and absolute shielding effectiveness (SSEt) of 46 dB, 2778 dB cm-2, 138 dB cm3 g-1, and 8358 dB cm2 g-1, respectively. As a consequence of this research, the high-purity RGO and its high-performance PI matrix nanocomposites are anticipated to find practical applications in conductive coatings and flexible substrates demanding high-temperature stability.

Survey regarding the use of endodontic posts among dentists of twin cities, Rawalpindi and Islamabad, Pakistan.

The purpose of the study was to assess the knowledge, attitude, and practices of dentists of twin cities regarding the use of endodontic posts in root canal treated tooth. A questionnaire was created and distributed among dentists of Rawalpindi and Islamabad via social media platforms regarding the use of posts. The results revealed that majority (60%) of the participants used endodontic posts for teeth with adequate ferrule, and believed that the function of endodontic posts is to retain the core material (50.5%). Glass fibre posts were preferred for anterior teeth (87%), whereas metal posts were favoured in posterior teeth (63%). It was concluded that the main function of the endodontic post is to retain the core material. The commonest indication is when there is at least 2mm of ferrule present and the optimal post length is 2/3rd of the root canal.

Study of synergistic effects induced by novel base composites on heavy metals removal and pathogen inactivation.

The green-collar strategies for nanomaterial synthesis with novel structural competencies have received significant attention in nanotechnology owing to their potential benefits. The utilization of silica nanoparticles for wastewater treatment through heavy metal ions remediation is the focal point of the present study. With this intent, silica was extracted from bagasse ash by the sol-gel method and modified using chitosan. Chemical and physical characteristics of silica(S), silica/Chitosan (SCs), were reckoned through X-ray Powder Diffraction (XRD), Fourier Transform Infrared Spectroscopy (FTIR), and Scanning Electron Microscopy (SEM) and the efficiency of synthesized biomaterials for removing heavy metal ions. Cadmium and Lead from wastewater was evaluated by conducting closed batch experiments. Isotherm and kinetics models were applied to understand the adsorption mechanism. Results of heavy metal ions removal showed that the S possesses the highest removal efficiency of 88% for cadmium. Equilibrium was established within 56 min following a Langmuir isotherm model and pseudo-second-order reaction. The synthesized biomaterials were also tested against the fungal (Aspergillus Niger) and bacterial strains (Escherichia coli and Staphylococcus aureus) to determine their antimicrobial properties Maximum inhibition of 26 mm was shown by SCs for E.coli. Synthesized samples were not so effective for A.niger. The high adsorption potential of silica nanoparticles reveals their potential to treat wastewater containing inorganic pollutants like calcium and lead released from the sugar industry firsthand, thereby building a circular economy by controlling the pollution from source to sink. The synthesized silica nanoparticles and silica/chitosan biomaterials demonstrated high adsorption potential for heavy metal ions, making them promising candidates for integration into Algal Membrane Bioreactors to enhance wastewater treatment efficiency and remove toxic pollutants. Their multifunctional properties, including antimicrobial activity, also offer potential for improving microbial control within AMBRs, ensuring a more effective and sustainable wastewater treatment process.

Rapid Method for Quantification of Iron (Fe+3) from Ferrazone (NaFe-EDTA) in Fortified Wheat Flour.

Conventional methods for quantifying the added iron in wheat flour are time-consuming and costly. A rapid method (Time/Sample: 95 min) was developed by modifying the conventional standard method (Time/Sample: 560 min) and validated. Linearity and linear regression of the rapid method presented excellent correlation coefficient (R2) values (0.9976 to 0.9991), which were close to 1, while the limits of agreement (LOA) were in the range of -0.01 to 0.06 mg/kg. The limits of detection (LOD)/specificity and limits of quantitation (LOQ)/sensitivity values were found to be 0.03 and 0.09 mg/kg, respectively. The rapid method was subjected to validation, wherein the precision of intra-assay, inter-assay, and inter-person was determined to be within the range of 1.35-7.25%. These results indicate a high level of accuracy and precision of the method. The percent relative standard deviation (RSD) for recoveries at varying spiking levels, that is, 5, 10, and 15 mg/kg, was determined at 1.33 lying far below the upper limit of acceptability (RSD < 20). Overall, the developed rapid method can be sustainably alternate for conventional methods owing to its ability to produce accurate, precise, robust, and reproducible results.

Knowledge, attitude, and perceptions about cancer genetic testing in clinical practice in Karachi, Pakistan.

Healthcare professionals (HCP) play an important role in the practical application of genetic screening tests but often feel inadequately prepared for cancer genetic testing (CGT) in clinical care. As the complexity of gene-related malignancies increases, it demands HCPs' preparedness to cater to patients' needs. Therefore, the aim of our study is to assess the knowledge, attitude, and practices of HCPs in Pakistan regarding the application of cancer genetics. Our cross-sectional survey was conducted from April 2022 to June 2022 amongst HCPs at a private and a governmental institution in Karachi, Pakistan. Non-probability random convenience sampling was used to select the population; however. non-clinical HCPs, as well as Interns, were excluded from our study. A total of 210 HCPs, 56.7% (119) bearing an experience of over 5 years of clinical experience, were included in this study. Most respondents from both hospitals deemed their knowledge inadequate, with only 2% (2) and 1.8% (2) being extremely knowledgeable, respectively. 68.6% (144) HCPs displayed a positive attitude towards CGT, with 55.2% (116) participants perceiving CGT in a positive light. As compared to the private sector, significantly more HCPs in the public sector dedicated ≥ 5 h/week for CME (P = 0.006), and were better prepared to counsel patients (P = 0.021) and interpret results concerning CGT (P = 0.020). Additionally, screening tests for specific cancer types were popularly considered a worthwhile avenue of investment to improve the current state of CGT in our healthcare system [47.6% (N = 100)]. Demonstrating a lack of knowledge among Pakistani doctors, our results call upon the need for additional training concerning CGT in both the public and private sectors alike. Understanding specific gaps in knowledge may further help enhance post-graduate training programs and eventually lead to effective incorporation of CGT into our healthcare setting.

Deep features optimization based on a transfer learning, genetic algorithm, and extreme learning machine for robust content-based image retrieval.

The recent era has witnessed exponential growth in the production of multimedia data which initiates exploration and expansion of certain domains that will have an overwhelming impact on human society in near future. One of the domains explored in this article is content-based image retrieval (CBIR), in which images are mostly encoded using hand-crafted approaches that employ different descriptors and their fusions. Although utilization of these approaches has yielded outstanding results, their performance in terms of a semantic gap, computational cost, and appropriate fusion based on problem domain is still debatable. In this article, a novel CBIR method is proposed which is based on the transfer learning-based visual geometry group (VGG-19) method, genetic algorithm (GA), and extreme learning machine (ELM) classifier. In the proposed method, instead of using hand-crafted features extraction approaches, features are extracted automatically using a transfer learning-based VGG-19 model to consider both local and global information of an image for robust image retrieval. As deep features are of high dimension, the proposed method reduces the computational expense by passing the extracted features through GA which returns a reduced set of optimal features. For image classification, an extreme learning machine classifier is incorporated which is much simpler in terms of parameter tuning and learning time as compared to other traditional classifiers. The performance of the proposed method is evaluated on five datasets which highlight the better performance in terms of evaluation metrics as compared with the state-of-the-art image retrieval methods. Its statistical analysis through a nonparametric Wilcoxon matched-pairs signed-rank test also exhibits significant performance.

Stress Estimation Model for the Sustainable Health of Cancer Patients.

Good health is the most important and very necessary characteristic for stress-free, skillful, and hardworking people with a cooperative environment to create a sustainable society. Validating two algorithms, namely, sequential minimal optimization for regression (SMOreg) using vector machine and linear regression (LR) and using their predicted cancer patients' cases, this study presents a patient's stress estimation model (PSEM) to forecast their families' stress for patients' sustainable health and better care with early management by under-study cancer hospitals. The year-wise predictions (1998-2010) by LR and SMOreg are verified by comparing with observed values. The statistical difference between the predictions (2021-2030) by these models is analyzed using a statistical t-test. From the data of 217067 patients, patients' stress-impacting factors are extracted to be used in the proposed PSEM. By considering the total population of under-study areas and getting the predicted population (2021-2030) of each area, the proposed PSEM forecasts overall stress for expected cancer patients (2021-2030). Root mean square error (RMSE) (1076.15.46) for LR is less than RSME for SMOreg (1223.75); hence, LR remains better than SMOreg in forecasting (2011-2020). There is no significant statistical difference between values (2021-2030) predicted by LR and SMOreg (p value = 0.767 > 0.05). The average stress for a family member of a cancer patient is 72.71%. It is concluded that under-study areas face a minimum of 2.18% stress, on average 30.98% stress, and a maximum of 94.81% overall stress because of 179561 expected cancer patients of all major types from 2021 to 2030.

Fecal Loading at Caecum as a New Radiological Sign for Diagnosing Acute Appendicitis.

Background The present study aimed to address the importance of a new radiological sign - the presence of fecal loading at the caecum - for the diagnosis of acute appendicitis. Methodology A cross-sectional study was conducted at the Department of General Surgery, Jinnah Postgraduate Medical Centre, Karachi from January 2020 to June 2020. Patients who presented in the emergency with acute pain at the right iliac fossa fulfilling the criteria of acute appendicitis (AA) according to the Alvarado scoring system, and were planned for appendectomy were included. Before surgery plain abdominal radiographs were taken in anteroposterior view in the supine position and were evaluated for the presence of fecal loading at the caecum. After that all patients underwent surgery and radiologic findings were correlated with histopathologic findings. Results The mean age of patients was 32.19±7.34 years. There were 83 (55.3%) male and 67 (44.7%) female patients. Out of 150, there were 144 (96.0%) patients in whom fecal loading in the caecum was diagnosed on plain radiographs. On histopathology reporting, acute appendicitis was diagnosed in 143 (95.3%) patients. Regarding accuracy, fecal loading at the caecum was found to have a sensitivity of 98.6%, specificity of 83.3%, a positive predictive value of 99.3%, and a negative predictive value of 71.4%.  Conclusion According to the results of the present study and existing literature, we suggest using fecal loading at the caecum along with a clinical scoring system for the diagnosis of acute appendicitis. As per our findings, fecal loading at the caecum is a valuable sign on plain abdominal radiograph for the diagnosis of AA. It has a sensitivity of 98.6% and a specificity of 83.3%. This sign typically becomes undetectable after an appendectomy. It will help to improve the accuracy of diagnosis of acute appendicitis, and hence will reduce the chances of negative appendectomy.

Skin cancer detection from dermoscopic images using deep learning and fuzzy k-means clustering.

Melanoma skin cancer is the most life-threatening and fatal disease among the family of skin cancer diseases. Modern technological developments and research methodologies made it possible to detect and identify this kind of skin cancer more effectively; however, the automated localization and segmentation of skin lesion at earlier stages is still a challenging task due to the low contrast between melanoma moles and skin portion and a higher level of color similarity between melanoma-affected and -nonaffected areas. In this paper, we present a fully automated method for segmenting the skin melanoma at its earliest stage by employing a deep-learning-based approach, namely faster region-based convolutional neural networks (RCNN) along with fuzzy k-means clustering (FKM). Several clinical images are utilized to test the presented method so that it may help the dermatologist in diagnosing this life-threatening disease at its earliest stage. The presented method first preprocesses the dataset images to remove the noise and illumination problems and enhance the visual information before applying the faster-RCNN to obtain the feature vector of fixed length. After that, FKM has been employed to segment the melanoma-affected portion of skin with variable size and boundaries. The performance of the presented method is evaluated on the three standard datasets, namely ISBI-2016, ISIC-2017, and PH2, and the results show that the presented method outperforms the state-of-the-art approaches. The presented method attains an average accuracy of 95.40, 93.1, and 95.6% on the ISIC-2016, ISIC-2017, and PH2 datasets, respectively, which is showing its robustness to skin lesion recognition and segmentation.

Host instars preference, density-dependent parasitism and behavioral perspective of parasitoids (Aphidius colemani, Aphidius matricariae and Aphelinus abdominalis) in Aphis glycines and Aphis gossypii

ABSTRACT Three parasitoid species Aphidius colemani, Aphidius matricariae (Hymenoptera: Braconidae) and Aphelinus abdominalis (Hymenoptera: Aphelinidae) were evaluated concerning their parasitism potential in two aphid species, Aphis glycines and Aphis gossypii (Hemiptera: Aphididae). The feeding of these two aphid species, even at low sums, can significantly damage photosynthesis and is found to transmit many kinds of plant viruses, which impact potential adverse effects on the plants. The overall parasitization on all nymphal ages in As. glycines was accomplished by Ad. colemani (60.50%), Ad. matricariae (49.16%) and Al. abdominalis (40%), while in As. gossypii parasitism exhibited by Ad. colemani (79.48%), Ad. matricariae (65.33%) and Al. abdominalis (58.83%). Aphelinus abdominalis exhibited the lowest parasitism in both given species as hosts. Significant differences in parasitism of different parasitoids and host species were observed. Concerning the preference of nymphal instars, we found that parasitoids species prefer to parasitize 1st- 4th instars in As. gossypii while in As. glycines 2nd, 1st, 3rd and 4th. Our results showed that the parasitism increases with the increase of parasitoid numbers and hosts densities.

Brain tumor segmentation using K-means clustering and deep learning with synthetic data augmentation for classification.

Image processing plays a major role in neurologists' clinical diagnosis in the medical field. Several types of imagery are used for diagnostics, tumor segmentation, and classification. Magnetic resonance imaging (MRI) is favored among all modalities due to its noninvasive nature and better representation of internal tumor information. Indeed, early diagnosis may increase the chances of being lifesaving. However, the manual dissection and classification of brain tumors based on MRI is vulnerable to error, time-consuming, and formidable task. Consequently, this article presents a deep learning approach to classify brain tumors using an MRI data analysis to assist practitioners. The recommended method comprises three main phases: preprocessing, brain tumor segmentation using k-means clustering, and finally, classify tumors into their respective categories (benign/malignant) using MRI data through a finetuned VGG19 (i.e., 19 layered Visual Geometric Group) model. Moreover, for better classification accuracy, the synthetic data augmentation concept i s introduced to increase available data size for classifier training. The proposed approach was evaluated on BraTS 2015 benchmarks data sets through rigorous experiments. The results endorse the effectiveness of the proposed strategy and it achieved better accuracy compared to the previously reported state of the art techniques.

Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture.

Brain tumor is one of the most dreadful natures of cancer and caused a huge number of deaths among kids and adults from the past few years. According to WHO standard, the 700,000 humans are being with a brain tumor and around 86,000 are diagnosed since 2019. While the total number of deaths due to brain tumors is 16,830 since 2019 and the average survival rate is 35%. Therefore, automated techniques are needed to grade brain tumors precisely from MRI scans. In this work, a new deep learning-based method is proposed for microscopic brain tumor detection and tumor type classification. A 3D convolutional neural network (CNN) architecture is designed at the first step to extract brain tumor and extracted tumors are passed to a pretrained CNN model for feature extraction. The extracted features are transferred to the correlation-based selection method and as the output, the best features are selected. These selected features are validated through feed-forward neural network for final classification. Three BraTS datasets 2015, 2017, and 2018 are utilized for experiments, validation, and accomplished an accuracy of 98.32, 96.97, and 92.67%, respectively. A comparison with existing techniques shows the proposed design yields comparable accuracy.

Endoscopic thyroid lobectomy vs Conventional open thyroid lobectomy.

BACKGROUND AND OBJECTIVE: Surgical managements for these suspicious nontoxic swellings requires open conventional method of thyroidectomy by neck incisions that can result in prominent scars and immediate risk usually hemorrhage. However new technological innovations came into practiced that include video assisted minimal invasive endoscopy by axillo-breast approach that gives very promising results with excellent cosmesis. In this study, we compared conventional open surgery with minimal invasive endoscopic techniques and associate various complaints and complications that were encountered in surgery. METHODS: Sixty patients were enrolled in this comparative study. It was conducted from period February 2018 to February 2019. The patients were randomized alternatively in two groups. Group-I patients underwent conventional lobectomy while Group-II patients were operated endoscopically, Patients having nodules less than 3cm and Thy 1 and 2 were included in this study. Patient having nodules greater than 3cm, Multinodular goiter, recurrent nodule and Thy 3-6 were excluded from the study. RESULTS: Patients who underwent endoscopic lobectomy were much more satisfied about scar marks whereas some developed post-operative complications. It included hoarseness of voice in Three (13.62%) patients, two patients developed seroma (9.08%), three patients (13.62%) erythema, whereas no postoperative complications were seen in patients who underwent open thyroid lobectomy. No signs of hypocalcemia noted in both approaches. CONCLUSIONS: The complications with endoscopic approaches are higher but they are minor and resolved spontaneously within maximum period of six weeks. However scar mark satisfaction was much higher in endoscopic lobectomy group.

Microscopic melanoma detection and classification: A framework of pixel-based fusion and multilevel features reduction.

The numbers of diagnosed patients by melanoma are drastic and contribute more deaths annually among young peoples. An approximately 192,310 new cases of skin cancer are diagnosed in 2019, which shows the importance of automated systems for the diagnosis process. Accordingly, this article presents an automated method for skin lesions detection and recognition using pixel-based seed segmented images fusion and multilevel features reduction. The proposed method involves four key steps: (a) mean-based function is implemented and fed input to top-hat and bottom-hat filters which later fused for contrast stretching, (b) seed region growing and graph-cut method-based lesion segmentation and fused both segmented lesions through pixel-based fusion, (c) multilevel features such as histogram oriented gradient (HOG), speeded up robust features (SURF), and color are extracted and simple concatenation is performed, and (d) finally variance precise entropy-based features reduction and classification through SVM via cubic kernel function. Two different experiments are performed for the evaluation of this method. The segmentation performance is evaluated on PH2, ISBI2016, and ISIC2017 with an accuracy of 95.86, 94.79, and 94.92%, respectively. The classification performance is evaluated on PH2 and ISBI2016 dataset with an accuracy of 98.20 and 95.42%, respectively. The results of the proposed automated systems are outstanding as compared to the current techniques reported in state of art, which demonstrate the validity of the proposed method.

A comprehensive study of mobile-health based assistive technology for the healthcare of dementia and Alzheimer's disease (AD).

Assistive technology (AT) involvement in therapeutic treatment has provided simple and efficient healthcare solutions to people. Within a short span of time, mobile health (mHealth) has grown rapidly for assisting people living with a chronic disorder. This research paper presents the comprehensive study to identify and review existing mHealth dementia applications (apps), and also synthesize the evidence of using these applications in assisting people with dementia including Alzheimer's disease (AD) and their caregivers. Six electronic databases searched with the purpose of finding literature-based evidence. The search yielded 2818 research articles, with 29 meeting quantified inclusion and exclusion criteria. Six groups and their associated sub-groups emerged from the literature. The main groups are (1) activities of daily living (ADL) based cognitive training, (2) monitoring, (3) dementia screening, (4) reminiscence and socialization, (5) tracking, and (6) caregiver support. Moreover, two commercial mobile application stores i.e., Apple App Store (iOS) and Google Play Store (Android) explored with the intention of identifying the advantages and disadvantages of existing commercially available dementia and AD healthcare apps. From 678 apps, a total of 38 mobile apps qualified as per defined exclusion and inclusion criteria. The shortlisted commercial apps generally targeted different aspects of dementia as identified in research articles. This comprehensive study determined the feasibility of using mobile Health based applications for dementia including AD individuals and their caregivers regardless of limited available research, and these apps have capability to incorporate a variety of strategies and resources to dementia community care.

A Deep Learning Approach for Automated Diagnosis and Multi-Class Classification of Alzheimer's Disease Stages Using Resting-State fMRI and Residual Neural Networks.

Alzheimer's disease (AD) is an incurable neurodegenerative disorder accounting for 70%-80% dementia cases worldwide. Although, research on AD has increased in recent years, however, the complexity associated with brain structure and functions makes the early diagnosis of this disease a challenging task. Resting-state functional magnetic resonance imaging (rs-fMRI) is a neuroimaging technology that has been widely used to study the pathogenesis of neurodegenerative diseases. In literature, the computer-aided diagnosis of AD is limited to binary classification or diagnosis of AD and MCI stages. However, its applicability to diagnose multiple progressive stages of AD is relatively under-studied. This study explores the effectiveness of rs-fMRI for multi-class classification of AD and its associated stages including CN, SMC, EMCI, MCI, LMCI, and AD. A longitudinal cohort of resting-state fMRI of 138 subjects (25 CN, 25 SMC, 25 EMCI, 25 LMCI, 13 MCI, and 25 AD) from Alzheimer's Disease Neuroimaging Initiative (ADNI) is studied. To provide a better insight into deep learning approaches and their applications to AD classification, we investigate ResNet-18 architecture in detail. We consider the training of the network from scratch by using single-channel input as well as performed transfer learning with and without fine-tuning using an extended network architecture. We experimented with residual neural networks to perform AD classification task and compared it with former research in this domain. The performance of the models is evaluated using precision, recall, f1-measure, AUC and ROC curves. We found that our networks were able to significantly classify the subjects. We achieved improved results with our fine-tuned model for all the AD stages with an accuracy of 100%, 96.85%, 97.38%, 97.43%, 97.40% and 98.01% for CN, SMC, EMCI, LMCI, MCI, and AD respectively. However, in terms of overall performance, we achieved state-of-the-art results with an average accuracy of 97.92% and 97.88% for off-the-shelf and fine-tuned models respectively. The Analysis of results indicate that classification and prediction of neurodegenerative brain disorders such as AD using functional magnetic resonance imaging and advanced deep learning methods is promising for clinical decision making and have the potential to assist in early diagnosis of AD and its associated stages.

An automated nuclei segmentation of leukocytes from microscopic digital images.

Leukemia is a life-threatening disease. So far diagnosing of leukemia is manually carried out by the Hematologists that is time-consuming and error-prone. The crucial problem is leukocytes' nuclei segmentation precisely. This paper presents a novel technique to solve the problem by applying statistical methods of Gaussian mixture model through expectation maximization for the basic and challenging step of leukocytes' nuclei segmentation. The proposed technique is being tested on a set of 365 images and the segmentation results are validated both qualitatively and quantitatively with current state-of-the-art methods on the basis of ground truth data (manually marked images by medical experts). The proposed technique is qualitatively compared with current state-of-the-art methods on the basis of ground truth data through visual inspection on four different grounds. Finally, the proposed technique quantitatively achieved an overall segmentation accuracy, sensitivity and precision of 92.8%, 93.5% and 98.16% respectively while an overall F-measure of 95.75%.

Profile and predictors of hepatitis and HIV infection in patients on hemodialysis of Quetta, Pakistan.

Hemodialysis (HD) is the most commonly used treatment in patients with end-stage renal failure or disease (ESRD) worldwide. Blood-borne viral diseases are the major causes of mortality and morbidity in patients on HD. This study aims to analyze the prevalence and to concentrate on the key risk factors that are responsible for hepatitis B virus (HBV), hepatitis C virus (HCV), and human immunodeficiency virus (HIV) infection in patients on HD visiting two dialysis centers in the city of Quetta in southwestern Pakistan. The overall incidence of HBV was found to be 16.1%, the overall incidence of HCV was found to be 43.2%, and two patients (1.6%) were found to be positive for both HBV and HCV. HIV was not found among patients seen at both hospitals during the study period. The main risk factors for development of a viral infection were the length of time on HD (p = 0.007), number of sessions (p = 0.001), and level of education (p = 0.092). Biochemical and hematological parameters including urea, creatinine, uric acid, and calcium levels, red blood cell count, white blood cell count, hemoglobin levels, and platelet count were also studied in patients on HD. HD is becoming one of the major factors causing a viral infection because a patient can possibly become infected during an HD session via a blood transfusion, dialysis machines, instruments and/or other contaminated equipment. In order to control the spread of viral infections, increased public awareness, vaccinations, and health education programs for both health care providers and patients are needed, and proper screening programs should be instituted before dialysis is performed.