Physiologically based pharmacokinetic modeling of metal nanoparticles for risk assessment of inhalation exposures: a state-of-the-science expert panel review.

A critical review of the current state-of-the-science for the physiologically based pharmacokinetic (PBPK) modeling of metal nanoparticles and their application to human health risk assessment for inhalation exposures was conducted. A systematic literature search was used to identify four model groups (defined as a primary publication along with multiple supplementary publications) subject to review. Using a recent guideline document from the Organization for Economic Cooperation and Development (OECD) for PBPK model evaluation, these model groups were critically peer-reviewed by an independent panel of experts to identify those to be considered for modeling and simulation application. Based upon the expert panel input, model confidence scores for the four model groups ranged from 30 to 41 (out of a maximum score of 50). The three highest-scoring model groups were then applied to compare predictions to a different metal nanoparticle (i.e. not specifically used to parameterize the original models) using a recently published data set for tissue burdens in rats, as well as predicting human tissue burdens expected for corresponding occupational exposures. Overall, the rat models performed reasonably well in predicting the lung but tended to overestimate systemic tissue burdens. Data needs for improving the state-of-the-science, including quantitative particle characterization in tissues, nanoparticle-corona data, long-term exposure data, interspecies extrapolation methods, and human biomonitoring/toxicokinetic data are discussed.

Revolutionizing breast ultrasound diagnostics with EfficientNet-B7 and Explainable AI.

Breast cancer is a leading cause of mortality among women globally, necessitating precise classification of breast ultrasound images for early diagnosis and treatment. Traditional methods using CNN architectures such as VGG, ResNet, and DenseNet, though somewhat effective, often struggle with class imbalances and subtle texture variations, leading to reduced accuracy for minority classes such as malignant tumors. To address these issues, we propose a methodology that leverages EfficientNet-B7, a scalable CNN architecture, combined with advanced data augmentation techniques to enhance minority class representation and improve model robustness. Our approach involves fine-tuning EfficientNet-B7 on the BUSI dataset, implementing RandomHorizontalFlip, RandomRotation, and ColorJitter to balance the dataset and improve model robustness. The training process includes early stopping to prevent overfitting and optimize performance metrics. Additionally, we integrate Explainable AI (XAI) techniques, such as Grad-CAM, to enhance the interpretability and transparency of the model's predictions, providing visual and quantitative insights into the features and regions of ultrasound images influencing classification outcomes. Our model achieves a classification accuracy of 99.14%, significantly outperforming existing CNN-based approaches in breast ultrasound image classification. The incorporation of XAI techniques enhances our understanding of the model's decision-making process, thereby increasing its reliability and facilitating clinical adoption. This comprehensive framework offers a robust and interpretable tool for the early detection and diagnosis of breast cancer, advancing the capabilities of automated diagnostic systems and supporting clinical decision-making processes.

Microsurgical lesionectomy for drug-resistant insular cortex epilepsy in focal cortical dysplasia type IIB: a pediatric case report.

Introduction and importance: Focal cortical dysplasia (FCD) is a significant cause of drug-resistant epilepsy, often necessitating surgical intervention. Type IIb FCD poses challenges due to its strong association with drug-resistant seizures. Effective management involves advanced imaging, intraoperative neurophysiological monitoring, and precise surgical techniques. This case study illustrates these strategies in an 11-year-old female with drug-resistant epilepsy attributed to Type IIb FCD. Case presentation: The patient, an 11-year-old female, had drug-resistant seizures despite various anticonvulsant treatments. Preoperative 3 Tesla (3T) MRI revealed an ill-defined lesion in the right frontal operculum. The surgical team used neuro-navigation for intraoperative guidance and electrocorticography for lesionectomy. Pathology confirmed Type IIb FCD with rare concentric calcifications. Clinical discussion: Drug-resistant seizures in FCD often require surgery when medications fail. This case highlights the importance of comprehensive preoperative evaluations and advanced imaging, such as 3T MRI, to accurately identify lesions. Intraoperative neurophysiological monitoring, including electrocorticography, ensures precise resection of the epileptogenic zone. The unusual finding of concentric calcifications in Type IIb FCD is noteworthy, suggesting the need for further research to understand their impact on the disease. Conclusion: Microsurgical lesionectomy is crucial for managing drug-resistant seizures in Type IIb FCD. Combining advanced imaging with intraoperative monitoring improves surgical precision and outcomes. The rare pathological finding of calcifications highlights the diversity of FCD manifestations, warranting further study. These techniques can significantly enhance seizure control and quality of life in patients with drug-resistant epilepsy.

Hydrologic variability governs GHG emissions in rice-based cropping systems of Eastern India.

Reducing methane (CH4) emissions is increasingly recognized as an urgent greenhouse gas mitigation priority for avoiding ecosystem 'tipping points' that will accelerate global warming. Agricultural systems, namely ruminant livestock and rice cultivation are dominant sources of CH4 emissions. Efforts to reduce methane from rice typically focus on water management strategies that implicitly assume that irrigated rice systems are consistently flooded and that farmers exert a high level of control over the field water balance. In India most rice is cultivated during the monsoon season and hydrologic variability is common, particularly in the Eastern Gangetic Plains (EGP) where high but variable rainfall, shallow groundwater, and subtle differences in topography interact to create complex mosaics of field water conditions. Here, we characterize the hydrologic variability of monsoon season rice fields (n = 207) in the Indian EGP ('Eastern India') across two contrasting climate years (2021, 2022) and use the Denitrification Decomposition (DNDC) model to estimate GHG emissions for the observed hydrologic conditions. Five distinct clusters of field hydrology patterns were evident in each year, but cluster characteristics were not stable across years. In 2021, average GHG emissions (8.14 mt CO2-eq ha-1) were twice as high as in 2022 (3.81 mt CO2-eq ha-1). Importantly, intra-annual variability between fields was also high, underlining the need to characterize representative emission distributions across the landscape and across seasons to appropriately target GHG mitigation strategies and generate accurate baseline values. Simulation results were also analyzed to identify main drivers of emissions, with readily identified factors such as flooding period and hydrologic interactions with crop residues and nitrogen management practices emerging as important. These insights provide a foundation for understanding landscape variability in GHG emissions from rice in Eastern India and suggest priorities for mitigation that honor the hydrologic complexity of the region.

Effect of season on histoarchitecture of pineal gland in buffalo (Bubalus bubalis).

Background: The photoperiod and other seasonal variations are the key factors that affect reproduction and production of the animals. The pineal gland secretes melatonin hormone that affects several physiological functions of the body during different seasons. Aims: The present study was conducted to study the histoarchitectural and micrometrical changes in the pineal gland of buffalo (Bubalus bubalis) during different seasons of the year. Methods: Pineal glands of 30 adult female Jaffarabadi buffaloes were collected from the slaughterhouse during the winter, summer, and rainy seasons. Samples were processed by standard histological procedures and stained with various stains for histological and micrometrical observations. Results: The pinealocytes constituted a major cellular portion of pineal parenchyma. The pinealocyte nuclei were lightly stained and more euchromatic during the winter season whereas darkly stained and slightly heterochromatic during summer. The calcium deposits occupied a larger area of pineal parenchyma during the summer as compared to the winter season. The pinealocyte density, the nuclear diameter of pinealocytes, and the number of argyrophilic nucleolar organizer regions (AgNOR) were highest during the winter season as compared to the summer and rainy seasons. Conclusion: The present study shows the influence of season on the histoarchitecture and histometry of the pineal gland of buffalo and indicated higher pineal activity during the winter season in this species.

Evaluation of Antidepresant Activity and Phytochemical Screening of Plant Cordia Dichotoma.

INTRODUCTION: The traditional medicinal system of India, Ayurveda, has mentioned Cordia Dichotoma as a potential treatment for various ailments. In the current research, the extracts of Cordia Dichotoma was examined to evaluate their antidepressant potential. MATERIALS AND METHODS: Here, green leaves of Cordia Dichotoma were used to prepare chloroform, ethanol, and aqueous extracts (referred to as CdCe, CdEe, and CdAe respectively). The research focused on investigating the antidepressant effects of these extracts using behavioral models in experimental animals. Additionally, locomotor activity was assessed as part of the evaluation process. RESULTS: Immobility time was reduced with CdEe Cordia Dichotoma rFST & mTST when at 200 mg/kg and 400 mg/kg body weight. The CdAe showed reduction in immobility time in the repeated rFST) at 400 mg/kg, while in the mTST, significant effects were observed at 200 and 400 mg/kg. Regarding the chloroform extract, it only exhibited a significant reduction in immobility time in the modified Tail Suspension Test (mTST) at a low dose of 200 mg/kg. However, no noticeable change in motor dysfunction was observed with CCl4 and aqueous extracts at doses of 200 and 400 mg/kg. It is worth noting that the chloroform extract (CdCe) did lead to a significant decrease in locomotor activity at the same dosage level. Taken together, these findings suggest that extracts obtained from Cordia Dichotoma leaves may possess antidepressant properties.

A selective photoinduced radical O-alkenylation of phenols and naphthols with terminal alkynes.

The visible light-promoted O-alkenylation of phenols and naphthols with terminal alkynes is achieved using 2,4,6-tris(4-fluorophenyl)pyrylium tetrafluoroborate (T(p-F)PPT) as a photocatalyst at room temperature without the need of any external ligand or additive. Apart from its excellent functional group tolerance, the protocol described herein represents an appealing alternative strategy to classical transition-metal catalysed hydroarylation reactions. Mechanistic investigations revealed that the reaction involves a radical pathway. The utility of the hydroarylated products for the synthesis of fused benzofurans via a one-pot annulation was also demonstrated. Herein, we report the first intermolecular radical hydroarylation of alkynes.

Rubella immunity among pregnant women and the burden of congenital rubella syndrome (CRS) in India, 2022.

BACKGROUND: India aims to eliminate rubella and congenital rubella syndrome (CRS) by 2023. We conducted serosurveys among pregnant women to monitor the trend of rubella immunity and estimate the CRS burden in India following a nationwide measles and rubella vaccination campaign. METHODS: We surveyed pregnant women at 13 sentinel sites across India from Aug to Oct 2022 to estimate seroprevalence of rubella IgG antibodies. Using age-specific seroprevalence data from serosurveys conducted during 2017/2019 (prior to and during the vaccination campaign) and 2022 surveys (after the vaccination campaign), we developed force of infection (FOI) models and estimated incidence and burden of CRS. RESULTS: In 2022, rubella seroprevalence was 85.2% (95% CI: 84.0, 86.2). Among 10 sites which participated in both rounds of serosurveys, the seroprevalence was not different between the two periods (pooled prevalence during 2017/2019: 83.5%, 95% CI: 82.1, 84.8; prevalence during 2022: 85.1%, 95% CI: 83.8, 86.3). The estimated annual incidence of CRS during 2017/2019 in India was 218.3 (95% CI: 209.7, 226.5) per 100, 000 livebirths, resulting in 47,120 (95% CI: 45,260, 48,875) cases of CRS every year. After measles-rubella (MR) vaccination campaign, the estimated incidence of CRS declined to 5.3 (95% CI: 0, 21.2) per 100,000 livebirths, resulting in 1141 (95% CI: 0, 4,569) cases of CRS during the post MR-vaccination campaign period. CONCLUSION: The incidence of CRS in India has substantially decreased following the nationwide MR vaccination campaign. About 15% of women in childbearing age in India lack immunity to rubella and hence susceptible to rubella infection. Since there are no routine rubella vaccination opportunities for this age group under the national immunization program, it is imperative to maintain high rates of rubella vaccination among children to prevent rubella virus exposure among women of childbearing age susceptible for rubella.

Spatial auto-correlation and endemicity pattern analysis of crimes against children in Tamil Nadu from 2017 to 2021.

Background: A child is a nation's supreme asset and future. India homes 444 million children, aged between 0 and 18 years, contributing to 19% of the world's children. Crime against children is detrimental to their mental and physical health and affects their growth and development. The National Crime Record Bureau recently reported that a crime targeting children happens every 4 minutes. There is a paucity of literature regarding the burden of crime against children. To understand the magnitude and spatial distribution of crime against children, a retrospective surveillance study was conducted in the state of Tamil Nadu, India, from 2017 to 2021. Materials and Methods: This is a cross-sectional analytical type of study conducted in KIMSRC, Chengalpattu, Tamil Nadu. The data from the yearly crime review bulletin of Tamil Nadu from 2017 to 2021 were cleaned, transformed, and analyzed using Python v3.8 and subjected to geospatial auto-correlation and hotspot analysis using the Getis-Ord Gi* in ArcGIS Pro v3.1. The endemicity pattern was studied through cluster analysis with Hierarchical Density Based Scanning in Python and visualization in ArcGIS pro v3.1 in the study area. Results: In Tamil Nadu, only one hotspot district in 2017 [Tiruppattur (95% confidence, P < 0.05)] and one hotspot in 2020 [Villupuram (90% confidence, P < 0.1)] were identified, with others being insignificant. The districts which show very high prevalence of crimes against children are Chennai, Ranipet, Chengalpattu, Viluppuram, Tiruvannamalai, Vellore, Tiruppattur, Krishnagiri, Dharmapuri, Salem, Cuddalore, Thanjavur, Tiruchirappalli, Karur, Tiruppur, Coimbatore, Dindigul, Pudukkottai, Sivaganga, Tenkasi, Thoothukkudi, Tirunelveli, and Kanniyakumari. Conclusion: This study identifies key areas within the state of Tamil Nadu which have a high prevalence of crimes against children and also areas that are hotspots for such crimes. Greater resources and measures can now be targeted toward these areas by stakeholders, which can help in the reduction of crimes against children.

An XAI-enhanced efficientNetB0 framework for precision brain tumor detection in MRI imaging.

BACKGROUND: Accurately diagnosing brain tumors from MRI scans is crucial for effective treatment planning. While traditional methods heavily rely on radiologist expertise, the integration of AI, particularly Convolutional Neural Networks (CNNs), has shown promise in improving accuracy. However, the lack of transparency in AI decision-making processes presents a challenge for clinical adoption. METHODS: Recent advancements in deep learning, particularly the utilization of CNNs, have facilitated the development of models for medical image analysis. In this study, we employed the EfficientNetB0 architecture and integrated explainable AI techniques to enhance both accuracy and interpretability. Grad-CAM visualization was utilized to highlight significant areas in MRI scans influencing classification decisions. RESULTS: Our model achieved a classification accuracy of 98.72 % across four categories of brain tumors (Glioma, Meningioma, No Tumor, Pituitary), with precision and recall exceeding 97 % for all categories. The incorporation of explainable AI techniques was validated through visual inspection of Grad-CAM heatmaps, which aligned well with established diagnostic markers in MRI scans. CONCLUSION: The AI-enhanced EfficientNetB0 framework with explainable AI techniques significantly improves brain tumor classification accuracy to 98.72 %, offering clear visual insights into the decision-making process. This method enhances diagnostic reliability and trust, demonstrating substantial potential for clinical adoption in medical diagnostics.

Prevalence of Avian coccidiosis in India: a review.

Coccidiosis stands as a highly significant and economically impactful parasitic ailment in poultry, attributed to the intracellular parasite belonging to the genus Eimeria. This affliction poses considerable financial challenges to the poultry industry and is prevalent in most tropical and subtropical regions globally. The primary mode of transmission is through the fecal-oral route, predominantly affecting young chicks and chickens within intensive rearing systems. There are nine distinct Eimeria species that affect poultry, manifesting primarily in caecal and intestinal forms. Diagnosis typically relies on examining fecal samples for oocysts and post-mortem lesions. Molecular techniques are employed for both diagnosis and control of poultry coccidiosis. To combat the disease, anticoccidials are consistently incorporated into feed and water, but this practice may contribute to the emergence of resistant strains. Various vaccines, including live or live attenuated options, are currently in use for coccidiosis prevention.

Effect of phytopigments on discoloration of nanohybrid composite: An in vitro study.

Objective: The purpose of this study is to comparatively evaluate the effect of discoloration of nanohybrid composite by four different phytopigments. Materials and Methods: Fifty disk-shaped samples of nanohybrid (3M Filtek Z350) resin composites were prepared using an acrylic template of dimension 5 mm × 3 mm. They were randomly divided into five groups and immersed in solutions of tomato powder, beetroot powder, java plum powder, and turmeric powder. Distilled water was used as the control group. The samples were placed in respective solutions for 3 h daily and stored in artificial saliva for the rest of the day for 28 days. Color values (L*, a*, b*) were measured by colorimeter using the CIE L*a*b* system at the end of the 7th and 28th days of immersion. Color differences ΔE*ab were statistically analyzed. Results: All the samples showed a change in color of nanohybrid composite resin to varying degrees. The mean ΔE*ab value obtained with beetroot solution was the highest among all the groups at the end of the 7th and 28th days, depicting that beetroot solution showed maximum mean color variation, followed by java plum solution, turmeric solution, and tomato solution. Conclusion: All the phytopigments used in this study have the potential to discolor the nanohybrid composite resin, with beetroot causing the most severe discoloration.

Enhancing the Bioavailability of the Ellagitannin, Geraniin: Formulation, Characterization, and in vivo Evaluation.

Geraniin (GE), an ellagitannin (ET) renowned for its promising health advantages, faces challenges in its practical applications due to its limited bioavailability. This innovative and novel formulation of GE and soy-phosphatidylcholine (GE-PL) complex has the potential to increase oral bioavailability, exhibiting high entrapment efficiency of 100.2 ± 0.8 %, and complexation efficiency of 94.6 ± 1.1 %. The small particle size (1.04 ± 0.11 µm), low polydispersity index (0.26 ± 0.02), and adequate zeta potential (-26.1 ± 0.12 mV), indicate its uniformity and stability. Moreover, the formulation also demonstrates improved lipophilicity, reduced aqueous and buffer solubilities, and better partition coefficient. It has been validated by various analytical techniques, including Fourier-transform infrared spectroscopy (FTIR), differential scanning calorimetry (DSC), and X-ray diffraction (XRD) studies. Oral bioavailability and pharmacokinetics of free GE and GE-PL complex investigated in rabbits demonstrated enhanced plasma concentration of ellagic acid (EA) compared to free GE. Significantly, GE, whether in its free form or as part of the GE-PL complex, was not found in the circulatory system. However, EA levels were observed at 0.5 h after administration, displaying two distinct peaks at 2 ± 0.03 h (T1max) and 24 ± 0.06 h (T2max). These peaks corresponded to peak plasma concentrations (C1max and C2max) of 588.82 ng/mL and 711.13 ng/mL respectively, signifying substantial 11-fold and 5-fold enhancements when compared to free GE. Additionally, it showed an increased area under the curve (AUC), the elimination half-life (t1/2, el) and the elimination rate constant (Kel). The formulation of the GE-PL complex prolonged the presence of EA in the bloodstream and improved its absorption, ultimately leading to a higher oral bioavailability. In summary, the study highlights the significance of the GE-PL complex in overcoming the bioavailability limitations of GE, paving the way for enhanced therapeutic outcomes and potential applications in drug delivery and healthcare.

Computational therapeutic repurposing of tavaborole targeting arginase-1 for venous leg ulcer.

Venous leg ulcers (VLUs) pose a growing healthcare challenge due to aging, obesity, and sedentary lifestyles. Despite various treatments available, addressing the complex nature of VLUs remains difficult. In this context, this study investigates repurposing boronated drugs to inhibit arginase 1 activity for VLU treatment. The molecular docking study conducted by Schrodinger GLIDE targeted the binuclear manganese cluster of arginase 1 enzyme (2PHO). Further, the ligand-protein complex was subjected to molecular dynamic studies at 500 ns in Gromacs-2019.4. Trajectory analysis was performed using the GROMACS simulation package of protein RMSD, RMSF, RG, SASA, and H-Bond. The docking study revealed intriguing results where the tavaborole showed a better docking score (-3.957 Kcal/mol) compared to the substrate L-arginine (-3.379 Kcal/mol) and standard L-norvaline (-3.141 Kcal/mol). Tavaborole interaction with aspartic acid ultimately suggests that the drug molecule binds to the catalytic site of arginase 1, potentially influencing the enzyme's function. The dynamics study revealed the compounds' stability and compactness of the protein throughout the simulation. The RMSD, RMSF, SASA, RG, inter and intra H-bond, PCA, FEL, and MMBSA studies affirmed the ligand-protein and protein complex flexibility, compactness, binding energy, van der waals energy, and solvation dynamics. These results revealed the stability and the interaction of the ligand with the catalytic site of arginase 1 enzyme, triggering the study towards the VLU treatment.

Performance evaluation of different empirical models for reference evapotranspiration estimation over Udhagamandalm, The Nilgiris, India.

Evapotranspiration (ETo) is an important component of the hydrological cycle and reliable estimates of ETo are essential for assessing crop water requirements and irrigation management. Direct measurement of evapotranspiration is both costly and involves complex and intricate procedures. Hence, empirical models are commonly utilized to estimate ETo using accessible meteorological data. Given that empirical methods operate on various assumptions, it is essential to assess their performance to pinpoint the most suitable methods for ETo calculation based on the availability of input data and the specific climatic conditions of a region. This study aims to evaluate different empirical methods of ETo in the tropical highland Udhagamandalam region of Tamil Nadu, India, utilizing sixty years of meteorological data from 1960-2020. In this study, 8 temperature-based and 10 radiation-based empirical models are evaluated against ETo estimates derived from pan evaporation observation and the FAO Penman-Monteith method (FAO-PM), respectively. Statistical error metrics indicate that both temperature and radiation-based models perform better for the Udhagamandalam region. However, radiation-based models performed better than the temperature based models. This is possibly due to the high humidity of the study region throughout the year. The results suggest that simple temperature and radiation-based models using minimum meteorological information are adequate to estimate ETo and thus find potential application in agricultural water practices, hydrological processes, and irrigation management.

Refining neural network algorithms for accurate brain tumor classification in MRI imagery.

Brain tumor diagnosis using MRI scans poses significant challenges due to the complex nature of tumor appearances and variations. Traditional methods often require extensive manual intervention and are prone to human error, leading to misdiagnosis and delayed treatment. Current approaches primarily include manual examination by radiologists and conventional machine learning techniques. These methods rely heavily on feature extraction and classification algorithms, which may not capture the intricate patterns present in brain MRI images. Conventional techniques often suffer from limited accuracy and generalizability, mainly due to the high variability in tumor appearance and the subjective nature of manual interpretation. Additionally, traditional machine learning models may struggle with the high-dimensional data inherent in MRI images. To address these limitations, our research introduces a deep learning-based model utilizing convolutional neural networks (CNNs).Our model employs a sequential CNN architecture with multiple convolutional, max-pooling, and dropout layers, followed by dense layers for classification. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The proposed model demonstrates a significant improvement in diagnostic accuracy, achieving an overall accuracy of 98% on the test dataset. The precision, recall, and F1-scores ranging from 97 to 98% with a roc-auc ranging from 99 to 100% for each tumor category further substantiate the model's effectiveness. Additionally, the utilization of Grad-CAM visualizations provides insights into the model's decision-making process, enhancing interpretability. This research addresses the pressing need for enhanced diagnostic accuracy in identifying brain tumors through MRI imaging, tackling challenges such as variability in tumor appearance and the need for rapid, reliable diagnostic tools.

Integrated approach of federated learning with transfer learning for classification and diagnosis of brain tumor.

Brain tumor classification using MRI images is a crucial yet challenging task in medical imaging. Accurate diagnosis is vital for effective treatment planning but is often hindered by the complex nature of tumor morphology and variations in imaging. Traditional methodologies primarily rely on manual interpretation of MRI images, supplemented by conventional machine learning techniques. These approaches often lack the robustness and scalability needed for precise and automated tumor classification. The major limitations include a high degree of manual intervention, potential for human error, limited ability to handle large datasets, and lack of generalizability to diverse tumor types and imaging conditions.To address these challenges, we propose a federated learning-based deep learning model that leverages the power of Convolutional Neural Networks (CNN) for automated and accurate brain tumor classification. This innovative approach not only emphasizes the use of a modified VGG16 architecture optimized for brain MRI images but also highlights the significance of federated learning and transfer learning in the medical imaging domain. Federated learning enables decentralized model training across multiple clients without compromising data privacy, addressing the critical need for confidentiality in medical data handling. This model architecture benefits from the transfer learning technique by utilizing a pre-trained CNN, which significantly enhances its ability to classify brain tumors accurately by leveraging knowledge gained from vast and diverse datasets.Our model is trained on a diverse dataset combining figshare, SARTAJ, and Br35H datasets, employing a federated learning approach for decentralized, privacy-preserving model training. The adoption of transfer learning further bolsters the model's performance, making it adept at handling the intricate variations in MRI images associated with different types of brain tumors. The model demonstrates high precision (0.99 for glioma, 0.95 for meningioma, 1.00 for no tumor, and 0.98 for pituitary), recall, and F1-scores in classification, outperforming existing methods. The overall accuracy stands at 98%, showcasing the model's efficacy in classifying various tumor types accurately, thus highlighting the transformative potential of federated learning and transfer learning in enhancing brain tumor classification using MRI images.

Towards blockchain based federated learning in categorizing healthcare monitoring devices on artificial intelligence of medical things investigative framework.

Categorizing Artificial Intelligence of Medical Things (AIoMT) devices within the realm of standard Internet of Things (IoT) and Internet of Medical Things (IoMT) devices, particularly at the server and computational layers, poses a formidable challenge. In this paper, we present a novel methodology for categorizing AIoMT devices through the application of decentralized processing, referred to as "Federated Learning" (FL). Our approach involves deploying a system on standard IoT devices and labeled IoMT devices for training purposes and attribute extraction. Through this process, we extract and map the interconnected attributes from a global federated cum aggression server. The aim of this terminology is to extract interdependent devices via federated learning, ensuring data privacy and adherence to operational policies. Consequently, a global training dataset repository is coordinated to establish a centralized indexing and synchronization knowledge repository. The categorization process employs generic labels for devices transmitting medical data through regular communication channels. We evaluate our proposed methodology across a variety of IoT, IoMT, and AIoMT devices, demonstrating effective classification and labeling. Our technique yields a reliable categorization index for facilitating efficient access and optimization of medical devices within global servers.

Deep transfer learning with fuzzy ensemble approach for the early detection of breast cancer.

Breast Cancer is a significant global health challenge, particularly affecting women with higher mortality compared with other cancer types. Timely detection of such cancer types is crucial, and recent research, employing deep learning techniques, shows promise in earlier detection. The research focuses on the early detection of such tumors using mammogram images with deep-learning models. The paper utilized four public databases where a similar amount of 986 mammograms each for three classes (normal, benign, malignant) are taken for evaluation. Herein, three deep CNN models such as VGG-11, Inception v3, and ResNet50 are employed as base classifiers. The research adopts an ensemble method where the proposed approach makes use of the modified Gompertz function for building a fuzzy ranking of the base classification models and their decision scores are integrated in an adaptive manner for constructing the final prediction of results. The classification results of the proposed fuzzy ensemble approach outperform transfer learning models and other ensemble approaches such as weighted average and Sugeno integral techniques. The proposed ResNet50 ensemble network using the modified Gompertz function-based fuzzy ranking approach provides a superior classification accuracy of 98.986%.