Bridging Convolutional Neural Networks and Transformers for Efficient Crack Detection in Concrete Building Structures.

Detecting cracks in building structures is an essential practice that ensures safety, promotes longevity, and maintains the economic value of the built environment. In the past, machine learning (ML) and deep learning (DL) techniques have been used to enhance classification accuracy. However, the conventional CNN (convolutional neural network) methods incur high computational costs owing to their extensive number of trainable parameters and tend to extract only high-dimensional shallow features that may not comprehensively represent crack characteristics. We proposed a novel convolution and composite attention transformer network (CCTNet) model to address these issues. CCTNet enhances crack identification by processing more input pixels and combining convolution channel attention with window-based self-attention mechanisms. This dual approach aims to leverage the localized feature extraction capabilities of CNNs with the global contextual understanding afforded by self-attention mechanisms. Additionally, we applied an improved cross-attention module within CCTNet to increase the interaction and integration of features across adjacent windows. The performance of CCTNet on the Historical Building Crack2019, SDTNET2018, and proposed DS3 has a precision of 98.60%, 98.93%, and 99.33%, respectively. Furthermore, the training validation loss of the proposed model is close to zero. In addition, the AUC (area under the curve) is 0.99 and 0.98 for the Historical Building Crack2019 and SDTNET2018, respectively. CCTNet not only outperforms existing methodologies but also sets a new standard for the accurate, efficient, and reliable detection of cracks in building structures.

Advancing Hyperspectral Image Analysis with CTNet: An Approach with the Fusion of Spatial and Spectral Features.

Hyperspectral image classification remains challenging despite its potential due to the high dimensionality of the data and its limited spatial resolution. To address the limited data samples and less spatial resolution issues, this research paper presents a two-scale module-based CTNet (convolutional transformer network) for the enhancement of spatial and spectral features. In the first module, a virtual RGB image is created from the HSI dataset to improve the spatial features using a pre-trained ResNeXt model trained on natural images, whereas in the second module, PCA (principal component analysis) is applied to reduce the dimensions of the HSI data. After that, spectral features are improved using an EAVT (enhanced attention-based vision transformer). The EAVT contained a multiscale enhanced attention mechanism to capture the long-range correlation of the spectral features. Furthermore, a joint module with the fusion of spatial and spectral features is designed to generate an enhanced feature vector. Through comprehensive experiments, we demonstrate the performance and superiority of the proposed approach over state-of-the-art methods. We obtained AA (average accuracy) values of 97.87%, 97.46%, 98.25%, and 84.46% on the PU, PUC, SV, and Houston13 datasets, respectively.

Birth Asphyxia among Neonates Admitted to the Neonatal Intensive Care Unit of a Tertiary Care Hospital.

Introduction: Birth asphyxia causes significant morbidity and mortality among neonates, especially in low-income and middle-income countries like Nepal. However, there is a paucity of data regarding its burden. This study aimed to find the prevalence of birth asphyxia among neonates admitted to the neonatal intensive care unit of a tertiary care hospital. Methods: This descriptive cross-sectional study was conducted among neonates at a tertiary care hospital between 15 January 2022 to 14 January 2023 after obtaining ethical approval from the Institutional Review Committee. Neonates with gestational age ≥35 weeks were included and those with major congenital anomalies were excluded. A convenience sampling method was used. A point estimate was calculated at a 95% Confidence Interval. Results: Among 902 neonates, 120 (13.30%) (11.08-15.52, 95% Confidence Interval) had birth asphyxia. A total of 108 (90%) were outborn, and 84 (70%) were males. HIE stage-I, II and III were seen in 47 (39.17%), 64 (53.33%) and 9 (7.50%) of the asphyxiated neonates respectively. Poor suck 92 (76.67%), seizures 73 (60.83%) and lethargy 70 (58.33%) were common abnormal neurological findings. Death occurred in 15 (12.50%) neonates in the hospital. Conclusions: The prevalence of birth asphyxia was found to be similar to other studies done in similar settings. The high burden underscores an urgent need to implement better perinatal care and delivery room management practices. Keywords: hypoxic-ischemic encephalopathy; neonates; prevalence.

Helicobacter pylori and Epstein-Barr virus infection in cell polarity alterations.

The asymmetrical distribution of the cellular organelles inside the cell is maintained by a group of cell polarity proteins. The maintenance of polarity is one of the vital host defense mechanisms against pathogens, and the loss of it contributes to infection facilitation and cancer progression. Studies have suggested that infection of viruses and bacteria alters cell polarity. Helicobacter pylori and Epstein-Barr virus are group I carcinogens involved in the progression of multiple clinical conditions besides gastric cancer (GC) and Burkitt's lymphoma, respectively. Moreover, the coinfection of both these pathogens contributes to a highly aggressive form of GC. H. pylori and EBV target the host cell polarity complexes for their pathogenesis. H. pylori-associated proteins like CagA, VacA OipA, and urease were shown to imbalance the cellular homeostasis by altering the cell polarity. Similarly, EBV-associated genes LMP1, LMP2A, LMP2B, EBNA3C, and EBNA1 also contribute to altered cell asymmetry. This review summarized all the possible mechanisms involved in cell polarity deformation in H. pylori and EBV-infected epithelial cells. We have also discussed deregulated molecular pathways like NF-κB, TGF-ß/SMAD, and ß-catenin in H. pylori, EBV, and their coinfection that further modulate PAR, SCRIB, or CRB polarity complexes in epithelial cells.

Multi-scale feature fusion-based lightweight dual stream transformer for detection of paddy leaf disease.

Traditionally, rice leaf disease identification relies on a visual examination of abnormalities or an analytical result obtained by growing bacteria in the research lab. This method of visual evaluation is qualitative and error-prone. On the other hand, an artificial neural network system is fast and more accurate. Several pieces of research using traditional machine learning and deep convolution neural networks (CNN) have been utilized to overcome the issues. Still, these methods need more semantic contextual global and local feature extraction. Due to this, efficiency is less. Hence, in the present study, a multi-scale feature fusion-based RDTNet has been designed. The RDTNet contains two modules, and the first module extracts feature via three scales from the local binary pattern (LBP), gray, and a histogram of orient gradient (HOG) image. The second module extracts semantic global and local features through the transformer and convolution block. Furthermore, the computing cost is reduced by dividing the query into two parts and feeding them to convolution and the transformer block. The results indicate that the proposed method has a very high average precision, f1-score, and accuracy of 99.55%, 99.54%, and 99.53%, respectively. It is suggestive of improved classification accuracy using multi-scale features and the transformer. The model has also been validated on other datasets confirming that the present model can be used for real-time rice disease diagnosis. In the future, such models can be used for monitoring other crops, including wheat, tomato, and potato.

Neurocognitive Disorders in HIV-positive Patients.

Human immunodeficiency viruses (HIV) associated neurocognitive disorders (HAND) encompasses a group of syndromes of various degrees of impairment in cognition and daily functioning of HIV positive individuals. Although the widespread use of highly active antiretroviral therapy (HAART) has drastically reduced the prevalence of severe form of HAND, like HIV associated dementia (HAD), the prevalence of HAND and associated morbidity remains high. OBJECTIVES: (1) To know the prevalence of HAND in HIV-infected patients of a multi-ethnic population. (2) To describe various types of neurocognitive impairment among patients of HAND and study the factors affecting HAND. STUDY DESIGN: This study was a cross-sectional descriptive study conducted on 250 HIV-positive patients in outpatient department (OPD) of a tertiary care center in Mumbai, conducted over a period of 12 months. Patients with HIV-1 attending the OPD and having a minimal formal education of 4 years were included. Patients with concomitant delirium, any known central nervous system (CNS) disorder, any psychiatric disorder, and pregnant females were excluded. Outcome measures-the test batteries used were (1) International HIV Dementia Scale (IHDS) and (2) Addenbrookes cognitive examination-revised (ACE-R) scale. RESULTS: Of 250 subjects studied, 55.6% (139) were males and 44.4 % (111) were females. The mean age of study population was 39.42 years. The mean years of education were 8.32 years. The mean duration of infection (diagnosis of HIV-positive state) was 64.49 months and the mean duration of HAART intake in our patients was 52.30 months. The mean cluster of differentiation 4 (CD4) counts of our subjects were 527.13 per cumm [standard deviation (SD) of 234.13]. The mean nadir CD4 counts were 224.35 per cumm (SD of 115.09). Using the ACE-R scale, the prevalence of HAND was 71.60%, of which 37.20% had an asymptomatic neurological impairment, 29.60% had mild cognitive dysfunction, and 4.80% had HAD. Memory, verbal fluency and visuospatial abilities were the most affected domains on the ACE-R and memory recall and psychomotor speed were affected more on the IHDS. The prevalence of HAND was more with increasing age (p = 0.020), lesser education (p < 0.00) and lesser nadir CD4 counts (p < 0.00). However, it was not affected by the duration of the disease and the current CD4 counts (p > 0.05). CONCLUSION: Human immunodeficiency viruses (HIV) associated neurocognitive disorders HAND is common in HIV-positive patients, most of whom are asymptomatic. Older patients with less education and severe disease, having lower nadir counts are at the highest risk of HAND. Memory, verbal fluency, and visuospatial abilities were the most commonly affected domains.

COVID-19 radiograph prognosis using a deep CResNeXt network.

COVID-19 has caused an epidemic in the entire world and it is caused by the novel virus SARS-COV-2. In severe conditions, this virus can cause a critical lung infection or viral pneumonia. To administer the correct treatment to patients, COVID-19 testing is important for diagnosing and determining patients who are infected with COVID-19, as opposed to those infected with other bacterial or viral infections. In this paper, a CResNeXt chest radiograph COVID-19 prediction model is proposed using residual network architecture. The advantage of the proposed model is that it requires lesser free hyper-parameters as compared to other residual networks. In addition, the training time per epochs of the model is very less compared to VGG19, ResNet-50, ResNeXt. The proposed CResNeXt model's binary classification (COVID-19 versus No-Finding) accuracy is observed to be 98.63% and 99.99% and multi-class classification (COVID-19, Pneumonia, and No-Finding) accuracy is observed to be 97.42% and 99.27% on the original and augmented datasets, respectively.

Undermined Skin Lesion Emerged as Tubercular Meningitis: A Case Report.

Cutaneous tuberculosis is a rare type of extrapulmonary tuberculosis and it is uncommon even in places where tuberculosis is widespread. A 32-year-old female presented with fever and headache along with prior history of an ulcer in her leg which was treated as cellulitis at another centre. The neck rigidity, and the Kernig and Budzinski sign were also positive. There were also features of increased intracranial pressure. The non-contrast computed tomography showed bilateral hydrocephalus and hypodense areas. She was managed for increased intracranial pressure and anti-tubercular therapy for disseminated tuberculosis. Biopsy of non-healing wounds should be checked for lupus vulgaris. Keywords: case reports; lupus vulgaris; meningitis; skin; tuberculosis.

The Effect of Cadmium Tolerant Plant Growth Promoting Rhizobacteria on Plant Growth Promotion and Phytoremediation: A Review.

Cadmium (Cd) is a heavy metal of considerable toxicity with destructive impacts on plants, microbes and environments. Its toxicity is due to mishandling and manual hazards in plants and is primarily observed within the soil to cause decline of plants and microbial activity inside the rhizosphere. Cadmium accumulation in crops and the probability of Cd entering the food chain are grave for public health in the worldwide. Cadmium toxicity leads to depletion in seed germination, initial seedling growth, plant biomass, chlorosis, necrosis, hindrance of photosynthetic machinery and other physiological and biological activities in plants. Cadmium triggers the reactive oxygen species (ROS) that influences gene mutation and DNA damage that affects the cell cycle and cell division. Cd toxicity altered the levels of phenolic compounds, carbohydrates, glycine betaine, proline and organic acids in crops. Under stress conditions, the plant growth promoting rhizobacteria (PGPR) have various properties such as enzymatic activities, plant growth hormones production, phosphate solubilization, siderophores production and chelating agents that help the plants tolerate against Cd stress and also increase phenolic compound levels and osmolytes. Hence, this review highlights the crucial role of cadmium tolerant PGPR for crop production, declining metal phytoavailability and enhancing morphological and physiological boundaries of plants under stress conditions. It could be an environment friendly and cost effective technology under sustainable crop production.

Hybrid SFNet Model for Bone Fracture Detection and Classification Using ML/DL.

An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consuming process. The development of machine learning (ML), as well as deep learning (DL), has set a new path in medical image diagnosis. In this study, we proposed a novel multi-scale feature fusion of a convolution neural network (CNN) and an improved canny edge algorithm that segregate fracture and healthy bone image. The hybrid scale fracture network (SFNet) is a novel two-scale sequential DL model. This model is highly efficient for bone fracture diagnosis and takes less computation time compared to other state-of-the-art deep CNN models. The innovation behind this research is that it works with an improved canny edge algorithm to obtain edges in the images that localize the fracture region. After that, grey images and their corresponding canny edge images are fed to the proposed hybrid SFNet for training and evaluation. Furthermore, the performance is also compared with the state-of-the-art deep CNN models on a bone image dataset. Our results showed that SFNet with canny (SFNet + canny) achieved the highest accuracy, F1-score and recall of 99.12%, 99% and 100%, respectively, for bone fracture diagnosis. It showed that using a canny edge algorithm improves the performance of CNN.

Intracranial Calcification and Seizure with Down Syndrome: A Case Report.

Down syndrome is a genetic disorder caused by an extra copy of chromosome number 21. New onset of seizure in adults with Down syndrome is rare. The exact pathogenesis of intracranial calcification and seizure in Down syndrome is unknown, however, a possible association between hypocalcemia and vitamin D deficiency in Down syndrome was reported. An 18-year-old girl with nasal bridge, mongoloid slants, clinodactyly and saddle gap of toes, and prominent Downs phenotypes was present with a low level of parathyroid hormone, calcium, and vitamin D. Due to a higher prevalence of intracranial calcification in people with Down syndrome, there is an increased possibility of hypocalcemia and vitamin D deficiency. Hence, serum levels of calcium and vitamin D should always be checked before starting treatment with anti-epileptic drugs. Keywords: basal ganglia; Down syndrome; seizure; trisomy 21.

Bone Cancer Detection Using Feature Extraction Based Machine Learning Model.

Bone cancer is considered a serious health problem, and, in many cases, it causes patient death. The X-ray, MRI, or CT-scan image is used by doctors to identify bone cancer. The manual process is time-consuming and required expertise in that field. Therefore, it is necessary to develop an automated system to classify and identify the cancerous bone and the healthy bone. The texture of a cancer bone is different compared to a healthy bone in the affected region. But in the dataset, several images of cancer and healthy bone are having similar morphological characteristics. This makes it difficult to categorize them. To tackle this problem, we first find the best suitable edge detection algorithm after that two feature sets one with hog and another without hog are prepared. To test the efficiency of these feature sets, two machine learning models, support vector machine (SVM) and the Random forest, are utilized. The features set with hog perform considerably better on these models. Also, the SVM model trained with hog feature set provides an F1-score of 0.92 better than Random forest F1-score 0.77.

Validation of Accuracy of Non-Invasive Imaging Methods (Magnetic Resonance Imaging (MRI) Fat Fraction Calculation and Computed Tomography (CT) Liver Attenuation Index) for Hepatic Graft Fat Quantification in Living Liver Transplant Donors.

BACKGROUND Diagnosis of significant hepatic graft steatosis remains vital for success of any transplant program as it has an impact on donor morbidity and recipient survival. Even histopathological quantification faces limitations. The present study compared the diagnostic accuracy of CT-LAI and MRI fat fraction imaging with histopathological analysis for donor graft parenchymal fat quantification. MATERIAL AND METHODS CT-LAI and MR-FF values and histopathological fat quantification results of 273 patients were identified from electronic records of the author's institutes from September 2015 to April 2020. Data analysis was done using SPSS version 21.0. RESULTS Most participants were young with nearly equal sex distribution and significant number of overweight and obese patients. Moderate agreement and significant positive correlation were found between MR fat fraction (%) and biopsy-macrosteatosis (%). Diagnostic accuracy and negative predictive value of MRI for fat fraction calculation was high (95.24% and 98.07% for fat fraction of 10% threshold, respectively), and it further improved for fat fraction threshold of 15%. CONCLUSIONS MRI-based fat quantification calculation displayed near-perfect negative predictive values and very high diagnostic accuracy, suggesting that it can obviate the need for biopsy in patients with graft fat percentage <10% on MRI.

Indian Medical Undergraduates' Perceptions of Effective Teaching Methods: A Cross-Sectional Study.

INTRODUCTION: It becomes a challenge for a teacher to find a student-friendly approach to teach too many students in a class. The teaching methods used during medical education have a significant impact on learning among medical students. A practical and informative teaching technique is considered an essential component of that education. The present study aimed to determine the best interactive teaching method based on Indian medical undergraduates' perceptions. MATERIALS AND METHODS: The current investigation was a cross-sectional descriptive study that included 100 undergraduate medical students. A structured sample class on a specified topic was conducted using Microsoft PowerPoint (PPT) and a "chalk and talk" (CNT) method. Students' opinions of the class were assessed via a Likert scale questionnaire in which, for each of the two methods, the students were asked to rank twelve comments on a four-point scale: strongly agree, agree, disagree, or strongly disagree. Descriptive statistics were calculated to evaluate the distributions of their responses. The z test for two proportions was used to test a significant difference in respondents' proportions towards various perceptions regarding the two teaching methods under study. The data were analyzed using SPSS software version 22. RESULTS: Students understood the lesson content better when the teacher used the CNT approach (p<0.005). The CNT method was also associated with better interaction than the PPT technique (p=0.03) and facilitated better student concentration and retention of the class content (p=0.03). The students reported that there was less eye contact associated with the PPT technique (61%) but found the content thus delivered fascinating (78%), informative (91%), and organized (85%) as compared to the CNT approach. CONCLUSION: The traditional CNT approach is an effective classroom teaching method. The current study highlights student preferences for a combined teaching method that includes CNT and PPT.

Tocilizumab improves survival in severe COVID-19 pneumonia with persistent hypoxia: a retrospective cohort study with follow-up from Mumbai, India.

BACKGROUND: Cytokine storm triggered by Severe Coronavirus Disease 2019 (COVID-19) is associated with high mortality. With high Interleukin -6 (IL-6) levels reported in COVID-19 related deaths in China, IL-6 is considered to be the key player in COVID-19 cytokine storm. Tocilizumab, a monoclonal antibody against IL-6 receptor, is used on compassionate grounds for treatment of COVID-19 cytokine storm. The aim of this study was to assess effect of tocilizumab on mortality due to COVID-19 cytokine storm. METHOD: This retrospective, observational study included patients of severe COVID-19 pneumonia with persistent hypoxia (defined as saturation 94% or less on supplemental Oxygen of 15 L per minute through non-rebreathing mask or PaO2/FiO2 ratio of less than 200) who were admitted to a tertiary care center in Mumbai, India, between 31st March to 5th July 2020. In addition to standard care, single Inj. Tocilizumab 400 mg was given intravenously to 151 consecutive COVID-19 patients with persistent hypoxia, from 13th May to 5th July 2020. These 151 patients were retrospectively analysed and compared with historic controls, ie consecutive COVID-19 patients with persistent hypoxia, defined as stated above (N = 118, from our first COVID-19 admission on 31st March to 12th May 2020 i.e., till tocilizumab was available in hospital). Univariate and multivariate Cox regression analysis was performed for identifying predictors of survival. Statistical analysis was performed using IBM SPSS version 26. RESULTS: Out of 269 (151 in tocilizumab group and 118 historic controls) patients studied from 31st March to 5th July 2020, median survival in the tocilizumab group was significantly longer than in the control group; 18 days (95% CI, 11.3 to 24.7) versus 9 days (95% CI, 5.7 to 12.3); log rank p 0.007. On multivariate Cox regression analysis, independent predictors of survival were use of tocilizumab (HR 0.621, 95% CI 0.427-0.903, P 0.013) and higher oxygen saturation. CONCLUSION: Tocilizumab may improve survival in severe COVID-19 pneumonia with persistent hypoxia. Randomised controlled trials on use of tocilizumab as rescue therapy in patients of severe COVID-19 pneumonia with hypoxia (PaO2/FiO2 less than 200) due to hyperinflammatory state, are warranted.

A Three-Year Study on Acute Poisoning Cases Brought for Medico-Legal Autopsy in a North-Eastern City of India.

PURPOSE: Death due to acute poisoning is one of the significant health challenges to cope-up. It is imperative to know the death victims' pattern due to acute poisoning to prepare the relevant preventive and remedial measures. Therefore, the present study aimed to assess the pattern of the dead victims of acute poisoning in a tertiary care centre. MATERIALS AND METHODS: It is a hospital record-based study and conducted in a tertiary care centre. Descriptive statistics to study the distribution of the cases among different age groups, sex, type of poison compounds was computed and analysed using SPSS software version 20. RESULTS: The present study detected poisonous substances in 244 (41.8%) cases out of 584 death cases of suspected acute poisoning with the male preponderance of 62.29%. A higher incidence of acute poisoning was noticed among the young age group 21-30 years (33.6%) with 48 (31.6%) cases among males and 34 (36.9%) cases of the female. The Organophosphates (OP) was the main compound found in 151 (61.9%) fatal cases, followed by Carbamate in 45 (18.4%) cases. We also observed a maximum, 76 (36.2%) cases of suicidal victims in the age group of 21-30 years. Children and lower age group were more vulnerable to accidental poisoning as 26.5% cases of accidental death were reported in both the age group of 0-10 and 11-20 years respectively, gradually declining and practically found nil in above 60 years group. These differences of frequencies were found statistically significant (p < 0.0001), χ 2 = 55.1. CONCLUSION: The results suggest due consideration to the young adolescents' groups without any sexual discrimination to define guidelines for appropriate handling, storage and transportation of the poisonous compounds. Organophosphate's involvement as the most preferred agent in acute poisoning is to be remembered to help manage poisoning cases.

Germylene stabilized group 12 metal complexes and their reactivity with chalcogens.

This manuscript reports the first examples of germylene stabilized cadmium complexes {[{(i-Bu)2ATIGe(i-Pr)}2(CdI2)] (3, monomeric), [{(i-Bu)2ATIGe(i-Pr)(CdCl2)}2] (6, dimeric), [{(i-Bu)2ATIGe(i-Pr)(CdI2)}2] (7, dimeric)} and novel germylene zinc complexes {[{(i-Bu)2ATIGe(i-Pr)}2(ZnCl2)] (2, monomeric), [{(i-Bu)2ATIGe(i-Pr)(ZnI2)}2] (5, dimeric)} (ATI = aminotroponiminate). The reactions of germylene zinc complex [{(i-Bu)2ATIGe(i-Pr)(ZnCl2)}2] (4) with elemental sulphur and selenium resulted in the first examples of germathione and germaselenone stabilized ZnCl2 complexes [{(i-Bu)2ATIGe(i-Pr)(S)(ZnCl2)}2] (8) and [{(i-Bu)2ATIGe(i-Pr)(Se)(ZnCl2)}2] (9), respectively. Compound 4 was obtained through the reaction of compound 2 with ZnCl2. Interconversions between the monomeric and dimeric zinc/cadmium complexes (2 ↔ 4/3 ↔ 7) are shown. Compounds 2-3 and 5-9 are characterized by multinuclear NMR spectroscopy and single crystal X-ray diffraction studies are performed on compounds 2-3, 5-7, and 9. To understand the nature of bonding in the first examples of germylene cadmium complexes, ab initio calculations are also carried out on compounds 3 and 7.

Pseudohalogenogermylenes versus Halogenogermylenes: Difference in their Complexation Behavior towards Group 6 Metal Carbonyls.

Pseudohalogenogermylenes [(iBu)2 ATI]GeY (Y=NCO 4, NCS 5) show different coordination behavior towards group 6 metal carbonyls in comparison to the corresponding halogenogermylenes [(iBu)2 ATI]GeX (X=F 1, Cl 2, Br 3) (ATI=aminotroponiminate). The reactions of compounds 4-5 and 1-3 with cis-[M(CO)4 (COD)] (M=Mo, W, COD=cyclooctadiene) gave trans-germylene metal complexes {[(iBu)2 ATI]GeY}2 M(CO)4 (Y=NCO, M=Mo 6, W 11; Y=NCS, M=Mo 7) and cis-germylene metal complexes {[(iBu)2 ATI]GeX}2 M(CO)4 (M=Mo, X=F 8, Cl 9, Br 10; M=W, X=Cl 12), respectively. Theoretical studies on compounds 7 and 9 reveal that donor-acceptor interactions from Mo to Ge atoms are better stabilized in the observed trans and cis geometries than in the hypothetical cis and trans structures, respectively.