Detection of COVID-19 using edge devices by a light-weight convolutional neural network from chest X-ray images.

Deep learning is a highly significant technology in clinical treatment and diagnostics nowadays. Convolutional Neural Network (CNN) is a new idea in deep learning that is being used in the area of computer vision. The COVID-19 detection is the subject of our medical study. Researchers attempted to increase the detection accuracy but at the cost of high model complexity. In this paper, we desire to achieve better accuracy with little training space and time so that this model easily deployed in edge devices. In this paper, a new CNN design is proposed that has three stages: pre-processing, which removes the black padding on the side initially; convolution, which employs filter banks; and feature extraction, which makes use of deep convolutional layers with skip connections. In order to train the model, chest X-ray images are partitioned into three sets: learning(0.7), validation(0.1), and testing(0.2). The models are then evaluated using the test and training data. The LMNet, CoroNet, CVDNet, and Deep GRU-CNN models are the other four models used in the same experiment. The propose model achieved 99.47% & 98.91% accuracy on training and testing respectively. Additionally, it achieved 97.54%, 98.19%, 99.49%, and 97.86% scores for precision, recall, specificity, and f1-score respectively. The proposed model obtained nearly equivalent accuracy and other similar metrics when compared with other models but greatly reduced the model complexity. Moreover, it is found that proposed model is less prone to over fitting as compared to other models.

Unravelling the signatures of submarine groundwater discharge and seawater intrusion along the coastal plains of Odisha, India: a multi-proxy approach.

Submarine Groundwater Discharge (SGD) and Seawater Intrusion (SWI) are two contrary hydrological processes that occur across the land-sea continuum and understanding their nature is essential for management and development of coastal groundwater resource. Present study has attempted to demarcate probable zones of SGD and SWI along highly populated Odisha coastal plains which is water stressed due to indiscriminate-exploitation of groundwater leading to salinization and fresh groundwater loss from the alluvial aquifers. A multi-proxy investigation approach including decadal groundwater level dynamics, LANDSAT derived sea surface temperature (SST) anomalies and in-situ physicochemical analysis (pH, EC, TDS, salinity and temperature) of porewater, groundwater and seawater were used to locate the SGD and SWI sites. A total of 340 samples for four seasons (85 samples i.e., 30 porewater, 30 seawater and 25 groundwater in each season) were collected and their in-situ parameters were measured at every 1-2 km gap along ~ 145 km coastline of central Odisha (excluding the estuarine region). Considering high groundwater EC values (> 3000 µS/cm), three probable SWI and low porewater salinities (< 32 ppt in pre- and < 25 ppt in post-monsoons), four probable SGD zones were identified. The identified zones were validated with observed high positive hydraulic gradient (> 10 m) at SGD and negative hydraulic gradient (< 0 m) at SWI sites along with anomalous SST (colder in pre- and warmer in post-monsoon) near probable SGD locations. This study is first of its kind along the Odisha coast and may act as initial basis for subsequent investigations on fresh-saline interaction along the coastal plains where environmental integrity supports the livelihood of coastal communities and the ecosystem.

A new efficient referential genome compression technique for FastQ files.

Hospitals and medical laboratories create a tremendous amount of genome sequence data every day for use in research, surgery, and illness diagnosis. To make storage comprehensible, compression is therefore essential for the storage, monitoring, and distribution of all these data. A novel data compression technique is required to reduce the time as well as the cost of storage, transmission, and data processing. General-purpose compression techniques do not perform so well for these data due to their special features: a large number of repeats (tandem and palindrome), small alphabets, and highly similar, and specific file formats. In this study, we provide a method for compressing FastQ files that uses a reference genome as a backup without sacrificing data quality. FastQ files are initially split into three streams (identifier, sequence, and quality score), each of which receives its own compression technique. A novel quick and lightweight mapping mechanism is also presented to effectively compress the sequence stream. As shown by experiments, the suggested methods, both the compression ratio and the compression/decompression duration of NGS data compressed using RBFQC, are superior to those achieved by other state-of-the-art genome compression methods. In comparison to GZIP, RBFQC may achieve a compression ratio of 80-140% for fixed-length datasets and 80-125% for variable-length datasets. Compared to domain-specific FastQ file referential genome compression techniques, RBFQC has a compression and decompression speed (total) improvement of 10-25%.

Impacts of climate change and coastal salinization on the environmental risk of heavy metal contamination along the odisha coast, India.

Climate change-mediated rise in sea level and storm surges, along with indiscriminate exploitation of groundwater along populous coastal regions have led to seawater intrusion. Studies on groundwater salinization and heavy metal contamination trends are limited. Present study investigated the heavy metal contamination, associated risks and provided initial information on the impacts of groundwater salinization on heavy metals along the coastal plains of Odisha, India. Total 50 groundwater samples (25 each in post- and pre-monsoon) were collected and analysed. Concentrations of Fe (44%), Mn (44%), As (4%) and Al (4%) in post-monsoon and Fe (32%), Mn (32%), As (4%), B (8%) and Ni (16%) in pre-monsoon exceeded Bureau of Indian Standards (BIS) drinking water limits. High concentrations of heavy metals (Fe, Sr, Mn, B, Ba, Li, Ni and Co) and high EC (>3000 µS/cm) indicated that the groundwater-seawater mixing process has enhanced the leaching and ion exchange of metallic ions in central part of the study area. Multivariate statistical analysis suggested leaching process, seawater intrusion and agricultural practices as the main heavy metal sources in the groundwater. 4% of samples in post- and 16% in pre-monsoon represented high heavy metal pollution index (HPI). Pollution indices indicated the central and south-central regions are highly polluted due to saline water intrusion and high agricultural activities. Ecological risks in the groundwater systems found low (ERI <110) in both seasons. Children population found more susceptible to health risks than adults. Hazard index (HI > 1) has shown significant non-carcinogenic risks where Fe, Mn, As, B, Li and Co are the potential contributors. Incremental lifetime cancer risk (ILCR >1.0E-03) has suggested high carcinogenic risks, where As and Ni are the major contributors. The study concluded that groundwater salinization could increase the heavy metal content and associated risks. This would help policymakers to take appropriate measures for sustainable coastal groundwater management.

DMF-Net: a deep multi-level semantic fusion network for high-resolution chest CT and X-ray image de-noising.

Medical images such as CT and X-ray have been widely used for the detection of several chest infections and lung diseases. However, these images are susceptible to different types of noise, and it is hard to remove these noises due to their complex distribution. The presence of such noise significantly deteriorates the quality of the images and significantly affects the diagnosis performance. Hence, the design of an effective de-noising technique is highly essential to remove the noise from chest CT and X-ray images prior to further processing. Deep learning methods, mainly, CNN have shown tremendous progress on de-noising tasks. However, existing CNN based models estimate the noise from the final layers, which may not carry adequate details of the image. To tackle this issue, in this paper a deep multi-level semantic fusion network is proposed, called DMF-Net for the removal of noise from chest CT and X-ray images. The DMF-Net mainly comprises of a dilated convolutional feature extraction block, a cascaded feature learning block (CFLB) and a noise fusion block (NFB) followed by a prominent feature extraction block. The CFLB cascades the features from different levels (convolutional layers) which are later fed to NFB to attain correct noise prediction. Finally, the Prominent Feature Extraction Block(PFEB) produces the clean image. To validate the proposed de-noising technique, a separate and a mixed dataset containing high-resolution CT and X-ray images with specific and blind noise are used. Experimental results indicate the effectiveness of the DMF-Net compared to other state-of-the-art methods in the context of peak signal-to-noise ratio (PSNR) and structural similarity measurement (SSIM) while drastically cutting down on the processing power needed.

Enhanced framework for COVID-19 prediction with computed tomography scan images using dense convolutional neural network and novel loss function.

Recent studies have shown that computed tomography (CT) scan images can characterize COVID-19 disease in patients. Several deep learning (DL) methods have been proposed for diagnosis in the literature, including convolutional neural networks (CNN). But, with inefficient patient classification models, the number of 'False Negatives' can put lives at risk. The primary objective is to improve the model so that it does not reveal 'Covid' as 'Non-Covid'. This study uses Dense-CNN to categorize patients efficiently. A novel loss function based on cross-entropy has also been used to improve the CNN algorithm's convergence. The proposed model is built and tested on a recently published large dataset. Extensive study and comparison with well-known models reveal the effectiveness of the proposed method over known methods. The proposed model achieved a prediction accuracy of 93.78%, while false-negative is only 6.5%. This approach's significant advantage is accelerating the diagnosis and treatment of COVID-19.

De novo transcriptome assembly and analysis of gene expression in different tissues of moth bean (Vigna aconitifolia) (Jacq.) Marechal.

BACKGROUND: The underutilized species Vigna aconitifolia (Moth Bean) is an important legume crop cultivated in semi-arid conditions and is valued for its seeds for their high protein content. It is also a popular green manure cover crop that offers many agronomic benefits including nitrogen fixation and soil nutrients. Despite its economic potential, genomic resources for this crop are scarce and there is limited knowledge on the developmental process of this plant at a molecular level. In the present communication, we have studied the molecular mechanisms that regulate plant development in V. aconitifolia, with a special focus on flower and seed development. We believe that this study will greatly enrich the genomic resources for this plant in form of differentially expressed genes, transcription factors, and genic molecular markers. RESULTS: We have performed the de novo transcriptome assembly using six types of tissues from various developmental stages of Vigna aconitifolia (var. RMO-435), namely, leaves, roots, flowers, pods, and seed tissue in the early and late stages of development, using the Illumina NextSeq platform. We assembled the transcriptome to get 150938 unigenes with an average length of 937.78 bp. About 79.9% of these unigenes were annotated in public databases and 12839 of those unigenes showed a significant match in the KEGG database. Most of the unigenes displayed significant differential expression in the late stages of seed development as compared with leaves. We annotated 74082 unigenes as transcription factors and identified 12096 simple sequence repeats (SSRs) in the genic regions of V.aconitifolia. Digital expression analysis revealed specific gene activities in different tissues which were validated using Real-time PCR analysis. CONCLUSIONS: The Vigna aconitifolia transcriptomic resources generated in this study provide foundational resources for gene discovery with respect to various developmental stages. This study provides the first comprehensive analysis revealing the genes involved in molecular as well as metabolic pathways that regulate seed development and may be responsible for the unique nutritive values of moth bean seeds. Hence, this study would serve as a foundation for characterization of candidate genes which would not only provide novel insights into understanding seed development but also provide resources for improved moth bean and related species genetic enhancement.

Infection, cases due to SARS-CoV-2 in rural areas during early COVID-19 vaccination: findings from serosurvey study in a rural cohort of eastern India.

COVID-19 serosurvey provides a better estimation of people who have developed antibody against the infection. But limited information on such serosurveys in rural areas poses many hurdles to understand the epidemiology of the virus and to implement proper control strategies. This study was carried out in the rural catchment area of Model Rural Health Research Unit in Odisha, India during March-April 2021, the initial phase of COVID vaccination. A total of 60 village clusters from four study blocks were identified using probability proportionate to size sampling. From each cluster, 60 households and one eligible participant from each household (60 per cluster) were selected for the collection of blood sample and socio-demographic data. The presence of SARS-CoV-2 antibody was tested using the Elecsys Anti-SARS-CoV-2 immunoassay. The overall seroprevalence after adjusting for test performance was 54.21% with an infection to case ratio of 96.89 along with 4.25% partial and 6.79% full immunisation coverage. Highest seroprevalence was observed in the age group of 19-44 years and females had both higher seroprevalence as well as vaccine coverage. People of other backward caste also had higher seropositivity than other caste categories. The study emphasises on continuing surveillance for COVID-19 cases and prioritizing COVID-19 vaccination for susceptible groups for better disease management.

Modified U-NET Architecture for Segmentation of Skin Lesion.

Dermoscopy images can be classified more accurately if skin lesions or nodules are segmented. Because of their fuzzy borders, irregular boundaries, inter- and intra-class variances, and so on, nodule segmentation is a difficult task. For the segmentation of skin lesions from dermoscopic pictures, several algorithms have been developed. However, their accuracy lags well behind the industry standard. In this paper, a modified U-Net architecture is proposed by modifying the feature map's dimension for an accurate and automatic segmentation of dermoscopic images. Apart from this, more kernels to the feature map allowed for a more precise extraction of the nodule. We evaluated the effectiveness of the proposed model by considering several hyper parameters such as epochs, batch size, and the types of optimizers, testing it with augmentation techniques implemented to enhance the amount of photos available in the PH2 dataset. The best performance achieved by the proposed model is with an Adam optimizer using a batch size of 8 and 75 epochs.

Central hubs prediction for bio networks by directed hypergraph - GA with validation to COVID-19 PPI.

Network structures have attracted much interest and have been rigorously studied in the past two decades. Researchers used many mathematical tools to represent these networks, and in recent days, hypergraphs play a vital role in this analysis. This paper presents an efficient technique to find the influential nodes using centrality measure of weighted directed hypergraph. Genetic Algorithm is exploited for tuning the weights of the node in the weighted directed hypergraph through which the characterization of the strength of the nodes, such as strong and weak ties by statistical measurements (mean, standard deviation, and quartiles) is identified effectively. Also, the proposed work is applied to various biological networks for identification of influential nodes and results shows the prominence the work over the existing measures. Furthermore, the technique has been applied to COVID-19 viral protein interactions. The proposed algorithm identified some critical human proteins that belong to the enzymes TMPRSS2, ACE2, and AT-II, which have a considerable role in hosting COVID-19 viral proteins and causes for various types of diseases. Hence these proteins can be targeted in drug design for an effective therapeutic against COVID-19.

Association of quorum sensing and biofilm formation with Salmonella virulence: story beyond gathering and cross-talk.

Enteric fever (typhoid and paratyphoid fever) is a public health concern which contributes to mortality and morbidity all around the globe. It is caused mainly due to ingestion of contaminated food and water with a gram negative, rod-shaped, flagellated bacterium known as Salmonella enterica serotype typhi (typhoid fever) or paratyphi (paratyphoid fever). Clinical problems associated with Salmonellosis are mainly bacteraemia, gastroenteritis and enteric fever. The bacteria undergo various mechanisms to escape itself from immune reaction of the host, modulating immune response at the site of infection leading to virulence factor production and anti-microbial resistance. Biofilm is one of the adaptation mechanisms through which Salmonella survives in unfavourable conditions and thus is considered as a major threat to public health. Another property of the bacteria is "Quorum Sensing", which is a cell-cell communication and most of the pathogenic bacteria use it to coordinate the production of several virulence factors and other behaviours such as swarming and biofilm formation. Earlier, quorum sensing was believed to be just a medium for communication but, later on, its role in virulence has been studied. However, there are negligible information relating to interaction between quorum sensing and biofilm formation and how these events play crucial role in Salmonella pathogenesis. The review is a summary of updated information regarding how Salmonella uses these properties to spread more and survive better, making a challenge for clinicians and public health experts. Therefore, this review would help bring an insight regarding how biofilm formation and quorum sensing are inter-related and their role in pathogenesis and virulence of Salmonella.

Spatial heterogeneity in discontinuation of modern spacing method in districts of India.

BACKGROUND: Despite six decades of official family planning programme, the use of modern contraceptive method remained low in India. The discontinuation of modern spacing method (DMSM) has also increased from 42.3% in 2005-06 to 43.6% during 2015-16. Discontinuation rate is higher for Injectable (51%), followed by condom (47%), pill (42%) and lowest in IUD (26%). METHODS: Data from NFHS-4 (2015-16) comprising of 601,509 households, 699,686 women and a sample of 119,548 episode of modern spacing method was used for the analysis. Multiple decrement life table has used to estimate 12-month discontinuation rate of modern spacing methods (DMSM). Moran's I statistics, Bivariate LISA cluster map has used to understand the spatial correlates and clustering the DMSM. OLS model and impact analysis has used to assess the significant associated covariates with discontinuation. RESULT: The 12-month DMSM in India is 43.5%; largely due to desire for becoming pregnant and method failure. The high discontinuation rate was observed in most of the southern (62%) and central (46%) regions of India. DMSM has significantly and spatially associated with neighbouring districts of India (Moran's I = 0.47, p-value = 0.00). The prevalence of modern spacing method is negatively associated with discontinuation in the neighbouring districts of India. The unmet need (ß = 0.84, 95% CI 0.55-1.14), desire of children (ß = 0.26, 95% CI - 0.05-0.57) and female sterilization (ß = 0.54, 95% CI 0.14-0.95) were three main contributing factor to DMSM. CONCLUSION: Districts of high DMSM need programmatic intervention. More attention for counselling to client, health worker outreach to user and better quality care services will stimulate non-user of contraception.

Contraceptive discontinuation is major issue of family planning of India. Without getting proper knowledge of modern spacing method, women facing serious health related issues so that they tend to discontinue their family planning method. We examine the spatial heterogeneity of discontinuation of modern spacing method in 640 district of India. Using secondary data of NFHS-4 (2015­16), we calculated 12-month discontinuation rate of any method and any modern spacing method by reason of discontinuation, also we presented discontinuation pattern by regions of India. To measure the spill over effect and associated factor of discontinuation of modern spacing method, we used OLS model and estimated Impact result. The findings of our study conveys that desire to become pregnant is the leading cause of discontinuation for both any method and any modern spacing method (12.43%), followed by other fertility related reasons and methods relates reason's (4.40%). Method failure, side effect of method and method related reason together accounts 12% of contraceptive discontinuation in India. Very low use of modern spacing method of districts should be given more attention for policy maker and planner to increase the use of modern spacing method. The districts of high discontinuation of modern spacing method need programmatic intervention. More attention for counselling to client, health worker outreach to user and better quality care services will stimulate non-user of contraception.

Circulating HLA-DR+CD4+ effector memory T cells resistant to CCR5 and PD-L1 mediated suppression compromise regulatory T cell function in tuberculosis.

Chronic T cell activation is a hallmark of pulmonary tuberculosis (PTB). The mechanisms underpinning this important phenomenon are however, poorly elucidated, though known to rely on control of T effector cells (Teff) by regulatory T cells (Treg). Our studies show that circulating natural Treg cells in adults with PTB preserve their suppressive potential but Teff cells from such subjects are resistant to Treg-mediated suppression. We found this to be due to expansion of an activated Teff subset identified by Human Leukocyte Antigen (HLA)-DR expression. Sensitivity to suppression was restored to control levels by depletion of this subset. Comparative transcriptome analysis of Teff cells that contain HLA-DR+ cells versus the fraction depleted of this population identified putative resistance mechanisms linked to IFNG, IL17A, IL22, PD-L1 and ß-chemokines CCL3L3, CCL4 expression. Antibody blocking experiments confirmed HLA-DR+ Teff cells, but not the fraction depleted of HLA-DR+ effectors, to be resistant to Treg suppression mediated via CCR5 and PD-L1 associated pathways. In the presence of HLA-DR+ Teff cells, activation of NFκB downstream of CCR5 and PD-L1 was perturbed. In addition, HLA-DR+ Teff cells expressed significantly higher levels of Th1/Th17 cytokines that may regulate Treg function through a reciprocal counter-balancing relationship. Taken together, our study provides novel insight on how activated HLA-DR+CD4+ T cells may contribute to disease associated inflammation by compromising Treg-mediated suppression in PTB.

Histological anomalies and alterations in enzyme activities of the earthworm Glyphidrillus tuberosus exposed to high concentrations of phosphogypsum.

Phosphogypsum (PG) is the major solid waste generated by phosphate fertilizer plants and is used worldwide as sulfur and calcium supplement in agricultural soil. Considering the probability of elevated doses of PG during agricultural applications, this study was carried out to assess its impact on the connective tissue, tissue cholinesterase (ChE) activity, lactate dehydrogenase (LDH) activity, and lipid peroxidation (LPX) level of the tropical earthworm Glyphidrillus tuberosus (Stephenson) found in abundance in the rice fields in India. Consistent loss of connective tissue and sloughing of the intestinal epithelium were observed in worms exposed to 10%, 15%, and 20% concentrations of PG in soil over an incubation period of 30 days. ChE, LDH activities, and the level of LPX indicated highly significant variation (p < 0.01) between pre and postclitellar regions of the worm and concentrations of treatment. ChE activity was higher in postclitellar with respect to preclitellar region; however, the values for LDH activity and LPX level were higher in preclitellar region in comparison to postclitellar region in both PG treated and control worms. It was concluded that PG concentration at and beyond 10% could cause damage to muscle fibers and bring about significant alterations in these enzyme activities in G.tuberosus thus affecting the physiology and ecological functions of these worms.

Expression of two WFDC1/ps20 isoforms in prostate stromal cells induces paracrine apoptosis through regulation of PTGS2/COX-2.

BACKGROUND: WFDC1/Prostate stromal 20 (ps20) is a small secreted protein highly expressed within the prostate stroma. WFDC1/ps20 expression is frequently downregulated or lost in prostate cancer (PCa) and ps20 has demonstrated growth-suppressive functions in numerous tumour model systems, although the mechanisms of this phenomenon are not understood. METHODS: Ps20 was cloned and overexpressed in DU145, PC3, LNCaP and WPMY-1 cells. Cellular growth, cell cycle and apoptosis were characterised. WPMY-1 stromal cells expressing ps20 were characterised by transcriptome microarray and the function of WPMY-1 conditioned media on growth of PCa cell lines was assessed. RESULTS: Prostrate stromal 20 expression enhanced the proliferation of LNCaP cells, whereas stromal WPMY-1 cells were inhibited and underwent increased apoptosis. Prostrate stromal 20-expressing WPMY-1 cells secrete a potently proapoptotic conditioned media. Prostrate stromal 20 overexpression upregulates expression of cyclooxygenase-2 (COX-2) in LNCaP and WPMY-1 cells, and induces expression of a growth-suppressive phenotype, which inhibits proliferation of PCa cells by ps20-expressing WPMY-1 conditioned media. This growth suppression was subsequently shown to be dependent on COX-2 function. CONCLUSIONS: This work posits that expression of ps20 in the prostate stroma can regulate growth of epithelial and other tissues through the prostaglandin synthase pathway, and thereby restricts development and progression of neoplasms. This provides a rational for selective pressure against ps20 expression in tumour- associated stroma.

Genetic association and altered gene expression of osteoprotegerin in otosclerosis patients.

Otosclerosis (OTSC) is a late-onset hearing disorder characterized by increased bone turnover in the otic capsule. Disturbed osteoprotegerin expression has been found in the otosclerotic foci which may have an important role in the pathogenesis of OTSC. To identify the genetic risk factors, we sequenced the coding region and exon-intron boundaries of the OPG gene in 254 OTSC patients and 262 controls. Sequence analysis identified five known polymorphisms c.9C>G, c.30+15C>T, c.400+4C>T, c.768A>G, and c.817+8A>C. Testing of these SNPs revealed sex specific association with c.9C>G in males and c.30+15C>T in females after multiple correction. Furthermore, meta-analysis provided evidence of association of the c.9C>G polymorphism with OTSC. In secondary analysis, we investigated the mRNA expression of OPG and associated genes RANK and RANKL in otosclerotic tissues compared to controls. Expression analysis revealed significantly missing/reduced OPG expression only in otosclerotic tissues. However, the signal sequence polymorphism c.9C>G has shown no effect on OPG mRNA expression. In conclusion, our results suggest that the risk of OTSC is influenced by variations in the OPG gene along with other factors which might regulate its altered expression in otosclerotic tissues. Further research is warranted to elucidate the mechanisms underlying these observations.

Computational analysis of human gut microbial prolyl oligopeptidases (POPs) reveal candidate genes as therapeutics for celiac disease.

Celiac disease (CD) is a common autoimmune disorder in which the patients are unable to digest gluten, which is present in foods made up of wheat, barley and rye. Whilst diagnosis happens late in 80% of the cases, avoidance of such foods appears to be the common solution. Alternative management strategies are required for the patients and their families since CD is also genetically carried over. Probiotic therapeutics and the consumption of appropriate enzymes, such as prolyloligopeptidases (POPs), from gut-friendly bacteria could reduce the disease burden and provide a better lifestyle for CD patients. We have examined around 5000 gut bacterial genomes and identified nearly 4000 non-redundant putative POPs. A select set of 10 gut bacterial POP sequences were subject to three-dimensional modelling, ligand docking and molecular dynamics simulations where stable interactions were observed between the POPs and gluten peptides. Our study provides sequence and structural analysis of potential POP enzymes in gut bacterial genomes, which form a strong basis to offer probiotic solutions to CD patients. In particular, these enzymes could be lead future therapeutics for this disease.

Correlation Between Radiological and Functional Outcomes Following Operative and Nonoperative Management of Acetabular Fractures: A Prospective Observational Study.

INTRODUCTION: The management of acetabular fractures is a complicated orthopedic procedure that has been advancing with time. Newer radiological tools like CT scans help surgeons to identify and manage these fractures more attentively. The study was conducted to evaluate the clinical and radiographic outcomes in patients with acetabular fractures managed either conservatively or by open reduction and internal fixation. MATERIALS AND METHOD: The study was done on 35 patients aged 18-60 years, with acetabular fractures treated either surgically or conservatively. Clinical scorings and radiological scoring were only taken and noted at three- and six-month intervals using Matta's radiographic scoring and modified Merle d'Aubigne and Postel clinical hip scoring. Clinico-radiological variables and complications were compared between the two groups. The data obtained was subjected to statistical analyses using IBM Statistical Package of Social Sciences (SPSS) 2.0 version software (Chicago, IL, USA) at a level of significance being p<0.05. RESULTS:  Out of a total of 35 patients, 19 were treated surgically and 16 conservatively. In patients belonging to the surgical treatment group, a maximum of 57.9% were aged 40-50 years, whereas the maximum patients (50%) of the conservative treatment group were aged <40 years, with male predominance in both groups. The type of fracture was recorded according to Judet and Letournel in both groups. Merle d'Aubigne's scoring and Matta's hip score were recorded at three and six months in both groups. A positive correlation was seen between radiological and functional outcomes at three and six months, which means that the higher the radiological scoring, the better the functional outcome of the patient managed either conservatively or surgically in the entire cohort. CONCLUSION:  Our study revealed that surgically managed patients had better functional and radiological outcomes than the patients who were conservatively managed at six months of follow-up. However, this is associated with more complications depending on fracture complexity and initial presentation of hip dislocation. The higher the radiological scoring, the better the functional outcome of the patient managed either conservatively or surgically in the entire cohort.

BT-CNN: a balanced binary tree architecture for classification of brain tumour using MRI imaging.

Deep learning is a very important technique in clinical diagnosis and therapy in the present world. Convolutional Neural Network (CNN) is a recent development in deep learning that is used in computer vision. Our medical investigation focuses on the identification of brain tumour. To improve the brain tumour classification performance a Balanced binary Tree CNN (BT-CNN) which is framed in a binary tree-like structure is proposed. It has a two distinct modules-the convolution and the depthwise separable convolution group. The usage of convolution group achieves lower time and higher memory, while the opposite is true for the depthwise separable convolution group. This balanced binarty tree inspired CNN balances both the groups to achieve maximum performance in terms of time and space. The proposed model along with state-of-the-art models like CNN-KNN and models proposed by Musallam et al., Saikat et al., and Amin et al. are experimented on public datasets. Before we feed the data into model the images are pre-processed using CLAHE, denoising, cropping, and scaling. The pre-processed dataset is partitioned into training and testing datasets as per 5 fold cross validation. The proposed model is trained and compared its perforarmance with state-of-the-art models like CNN-KNN and models proposed by Musallam et al., Saikat et al., and Amin et al. The proposed model reported average training accuracy of 99.61% compared to other models. The proposed model achieved 96.06% test accuracy where as other models achieved 68.86%, 85.8%, 86.88%, and 90.41% respectively. Further, the proposed model obtained lowest standard deviation on training and test accuracies across all folds, making it invariable to dataset.

Stroke incidence, mortality, subtypes in rural and urban populations in five geographic areas of India (2018-2019): results from the National Stroke Registry Programme.

Background: Increasing stroke burden in India demands a long-term stroke surveillance framework. Earlier studies in India were urban-based, short term and provided limited data on stroke incidence and its outcomes. This gap is addressed by the establishment of five population-based stroke registries (PBSRs) of the National Stroke Registry Programme, India. This paper describes stroke incidence, mortality and age, sex, and subtypes distribution in the five PBSRs with urban and rural populations. Methods: First-ever incident stroke patients in age group ≥18 years, resident for at least one year in the defined geographic area, identified from health facilities were registered. Death records with stroke as the cause of death from the Civil Registration System (CRS) were included. Transient ischemic attack (TIA) was excluded. Three PBSRs (Cuttack, Tirunelveli, Cachar) included urban and rural populations. PBSRs in Kota and Varanasi were urban areas. The crude and age-standardized incidence rate (ASR) by age, sex, and residence (urban and rural), rate ratios of ASR, case fatality proportions and rates at day 28 after onset of stroke were calculated for years 2018-2019. Findings: A total of 13,820 registered first-ever stroke cases that included 985 death certificate-only cases (DCOs) were analysed. The pooled crude incidence rate was 138.1 per 100,000 population with an age-standardized incidence rate (ASR) of 103.4 (both sexes), 125.7 (males) and 80.8 (females). The risk of stroke among rural residents was one in seven (Cuttack), one in nine (Tirunelveli), and one in 15 (Cachar). Ischemic stroke was the most common type in all PBSRs. Age-standardized case fatality rates (ASCFR) per 100,000 population for pooled PBSRs was 30.0 (males) and 18.8 (females), and the rate ratio (M/F) ranged from 1.2 (Cuttack) to 2.0 (Cachar). Interpretation: Population-based registries have provided a comprehensive stroke surveillance platform to measure stroke burden and outcomes by age, sex, residence and subtype across India. The rural-urban pattern of stroke incidence and mortality shall guide health policy and programme planning to strengthen stroke prevention and treatment measures in India. Funding: The National Stroke Registry Programme is funded through the intramural funding of the Indian Council of Medical Research, Department of Health Research, Ministry of Health and Family Welfare, India.