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.

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.

Advanced AI-driven approach for enhanced brain tumor detection from MRI images utilizing EfficientNetB2 with equalization and homomorphic filtering.

Brain tumors pose a significant medical challenge necessitating precise detection and diagnosis, especially in Magnetic resonance imaging(MRI). Current methodologies reliant on traditional image processing and conventional machine learning encounter hurdles in accurately discerning tumor regions within intricate MRI scans, often susceptible to noise and varying image quality. The advent of artificial intelligence (AI) has revolutionized various aspects of healthcare, providing innovative solutions for diagnostics and treatment strategies. This paper introduces a novel AI-driven methodology for brain tumor detection from MRI images, leveraging the EfficientNetB2 deep learning architecture. Our approach incorporates advanced image preprocessing techniques, including image cropping, equalization, and the application of homomorphic filters, to enhance the quality of MRI data for more accurate tumor detection. The proposed model exhibits substantial performance enhancement by demonstrating validation accuracies of 99.83%, 99.75%, and 99.2% on BD-BrainTumor, Brain-tumor-detection, and Brain-MRI-images-for-brain-tumor-detection datasets respectively, this research holds promise for refined clinical diagnostics and patient care, fostering more accurate and reliable brain tumor identification from MRI images. All data is available on Github: https://github.com/muskan258/Brain-Tumor-Detection-from-MRI-Images-Utilizing-EfficientNetB2 ).

Laser light: Illuminating the path to enhanced periodontal care.

The utilisation of laser technology in the realm of periodontal care represents a significant advancement in clinical practice. This article delves into the historical context of laser therapy in medicine, from its inception in 1960 to its evolution into low-level laser therapy (LLLT). LLLT, often referred to as photobiomodulation (PBM), has garnered attention due to its potential to enhance periodontal treatment outcomes. The article thoroughly examines the mechanisms of action of photobiomodulation therapy PBM(T), covering its impact on cellular and tissue levels. The authors explore the evidence-based recommendations for the use of PBM(T) in periodontal care, shedding light on its potential to improve periodontal conditions, especially when applied as an adjunct to conventional treatments. They investigate the role of PBM(T) in individuals and its possible contribution to periodontal health. Additionally, the article delves into its application in periodontal regenerative procedures and its ability to expedite soft tissue wound healing and the effects of PBM(T) in reducing periodontal inflammation and mitigating post-periodontal surgery discomfort. In conclusion, the article calls for enhanced clinical research to streamline laser procedures, develop antimicrobial photodynamic therapy, and conduct well-designed randomised controlled trials (RCTs). It also emphasises the importance of understanding the impact of laser therapy on therapeutic and biological goals, the potential to reduce invasive procedures, and the necessity of adequate research funding.

MicroRNA regulatory networks associated with abnormal muscle repair in survivors of critical illness.

BACKGROUND: Intensive care unit (ICU)-acquired weakness is characterized by muscle atrophy and impaired contractility that may persist after ICU discharge. Dysregulated muscle repair and regeneration gene co-expression networks are present in critical illness survivors with persistent muscle wasting and weakness. We aimed to identify microRNAs (miRs) regulating the gene networks and determine their role in the self-renewal of muscle in ICU survivors. METHODS: Muscle whole-transcriptome expression was assessed with microarrays in banked quadriceps biopsies obtained at 7 days and 6 months post-ICU discharge from critically ill patients (n = 15) in the RECOVER programme and healthy individuals (n = 8). We conducted an integrated miR-messenger RNA analysis to identify miR/gene pairs associated with muscle recovery post-critical illness and evaluated their impact on myoblast proliferation and differentiation in human AB1167 and murine C2C12 cell lines in vitro. Select target genes were validated with quantitative PCR. RESULTS: Twenty-two miRs were predicted to regulate the Day 7 post-ICU muscle transcriptome vs. controls. Thirty per cent of all differentially expressed genes shared a 3'UTR regulatory sequence for miR-424-3p/5p, which was 10-fold down-regulated in patients (P < 0.001) and correlated with quadriceps size (R = 0.86, P < 0.001), strength (R = 0.75, P = 0.007), and physical function (Functional Independence Measures motor subscore, R = 0.92, P < 0.001) suggesting its potential role as a master regulator of early recovery of muscle mass and strength following ICU discharge. Network analysis demonstrated enrichment for cellular respiration and muscle fate commitment/development related genes. At 6 months post-ICU discharge, a 14-miR expression signature, including miRs-490-3p and -744-5p, identified patients with muscle mass recovery vs. those with sustained atrophy. Constitutive overexpression of the novel miR-490-3p significantly inhibited AB1167 and C2C12 myoblast proliferation (cell count AB1167 miR-490-3p mimic or scrambled-miR transfected myoblasts 7926 ± 4060 vs. 14 159 ± 3515 respectively, P = 0.006; proportion Ki67-positive nuclei AB1167 miR-490-3p mimic or scrambled-miR transfected myoblasts 0.38 ± 0.07 vs. 0.54 ± 0.06 respectively, P < 0.001; proliferating cell nuclear antigen expression AB1167 miR-490-3p mimic or scrambled-miR transfected myoblasts 11.48 ± 1.97 vs. 16.75 ± 1.19 respectively, P = 0.040). Constitutive overexpression of miR-744-5p, a known regulator of myogenesis, significantly inhibited AB1167 and C2C12 myoblast differentiation (fusion index AB1167 miR-744-5p mimic or scrambled-miR transfected myoblasts 8.31 ± 7.00% vs. 40.29 ± 9.37% respectively, P < 0.001; myosin heavy chain expression miR-744-5p mimic or scrambled-miR transfected myoblasts 0.92 ± 0.39 vs. 13.53 ± 5.5 respectively, P = 0.01). CONCLUSIONS: Combined functional transcriptomics identified 36 miRs including miRs-424-3p/5p, -490-3p, and -744-5p as potential regulators of gene networks associated with recovery of muscle mass and strength following critical illness. MiR-490-3p is identified as a novel regulator of myogenesis.

A Highly Selective Fluorescent Probe for Detection of Hydrogen Sulfide in Living Systems: In Vitro and in Vivo Applications.

A fluorescein-based fluorescent probe has been designed and synthesised that selectively detects H2 S in aqueous medium, among various analytes tested. This fluorescein-based fluorescent probe has also been successfully utilised for real-time imaging of exo- and endogenously produced H2 S in cancer cells and normal cells. Moreover, the probe can also detect H2 S in the rat brain hippocampus at variable depths and in living nematodes.

A lysosome targetable fluorescent probe for endogenous imaging of hydrogen peroxide in living cells.

A lysosome targetable naphthalimide based fluorescent probe (LyNC) has been designed and synthesized which detects hydrogen peroxide (H2O2) with high selectivity and sensitivity in brain tissues and in living nematodes among various ROS/RNS tested. Further, the probe LyNC was successfully employed in exogenous and endogenous imaging of H2O2 in living cell lines.

Tinospora cordifolia ameliorates anxiety-like behavior and improves cognitive functions in acute sleep deprived rats.

Sleep deprivation (SD) leads to the spectrum of mood disorders like anxiety, cognitive dysfunctions and motor coordination impairment in many individuals. However, there is no effective pharmacological remedy to negate the effects of SD. The current study examined whether 50% ethanolic extract of Tinospora cordifolia (TCE) can attenuate these negative effects of SD. Three groups of adult Wistar female rats - (1) vehicle treated-sleep undisturbed (VUD), (2) vehicle treated-sleep deprived (VSD) and (3) TCE treated-sleep deprived (TSD) animals were tested behaviorally for cognitive functions, anxiety and motor coordination. TSD animals showed improved behavioral response in EPM and NOR tests for anxiety and cognitive functions, respectively as compared to VSD animals. TCE pretreatment modulated the stress induced-expression of plasticity markers PSA-NCAM, NCAM and GAP-43 along with proteins involved in the maintenance of LTP i.e., CamKII-α and calcineurin (CaN) in hippocampus and PC regions of the brain. Interestingly, contrary to VSD animals, TSD animals showed downregulated expression of inflammatory markers such as CD11b/c, MHC-1 and cytokines along with inhibition of apoptotic markers. This data suggests that TCE alone or in combination with other memory enhancing agents may help in managing sleep deprivation associated stress and improving cognitive functions.

A bodipy based fluorescent probe for evaluating and identifying cancer, normal and apoptotic C6 cells on the basis of changes in intracellular viscosity.

The applications of a bodipy based probe 1 for the identification of diseased cell population out of normal cells on the basis of changes in intracellular viscosity have been explored. Probe 1 works on the principle of restriction of rotation in viscous medium and the molecular rotor nature of probe 1 is supported by low temperature 1H NMR and variable dihedral angle DFT and TD-DFT studies. More importantly, probe 1 is the first probe which shows its practical application in monitoring micro-viscosity changes in a cell based model system of undifferentiated, differentiated and apoptotic C6 glial cells. Further, probe 1 can effectively monitor the apoptosis pathway by showing an increase in fluorescence intensity from cancerous cells to apoptotic cells via real time live-cell video imaging. Moreover, the viscosity changes in living cells were proved by fluorescence lifetime imaging (FLIM) studies, flow cytometry using Annexin-V and Bcl-xl expression by immunocytofluorescence (ICC) and western blot analysis.

Withania somnifera aqueous extract facilitates the expression and release of GnRH: In vitro and in vivo study.

Ashwagandha (Withania somnifera) has a long history in traditional medicines as an aphrodisiac. It has been known to influence sexual behaviour in animal models but mechanism of action is still unknown. The present study was aimed to investigate the mechanisms by which Ashwagandha extract exert its gonadotropic activities. Due to the complexity of neuroendocrine pathways, there are limited in vitro models available despite the strong demand for such systems to study and predict neuroendocrine effects of chemicals or natural products. Immortalized rat hypothalamic GnV-3 cell line was investigated as a model to screen for neuroendocrine effects of Ashwagandha extract. GnV-3 cells were cultured under different media conditions and evaluated after treatment with Ashwagandha water extract, for GnRH expression and release by immunostaining and ELISA respectively. These cells acquired differentiated morphology, characteristic shape displayed by preoptic GnRH neurons in vivo. In addition, GnV-3 cells exhibited upregulation of plasticity related polysialylated neural cell adhesion molecule (PSA-NCAM) and mature dendrite marker microtubule associated protein (MAP2) as well as GnRH expression and release. Chloroform fraction of the extract proved to exhibit all the bioactive properties as it induced differentiation and upregulated GnRH and MAP2 expression in GnV-3 cells, similar to Ashwagandha extract. Withanone and Withaferin A were found to be present in ASH-WEX and chloroform fraction while Withanone came out to be the major constituent of chloroform fraction. The preliminary in vivo studies in adult male animals showed that ASH-WEX was able to upregulate the GnRH levels although non-significantly. Taken together, this data demonstrate significant morphological and physiological changes in GnV-3 cells after treatment with Ashwagandha extract and may suggest the potential beneficial effects of Ashwagandha on reproductive functions in vivo.

A bodipy based dual functional probe for the detection of hydrogen sulfide and H2S induced apoptosis in cellular systems.

A bodipy based dual functional probe 1 has been designed and synthesized, which selectively detects H2S as well as monitors H2S induced apoptosis in cells.