Background: Brain tumors are among the most difficult diseases to deal with in modern medicine due to the uncontrolled cell proliferation, which causes grave damage to the nervous system. Brain tumors can be broadly classified into two categories: primary tumors, which originate within the brain, and secondary tumors, which are metastatic in nature. Effective glioma, meningioma, and pituitary tumor diagnosis and treatment requires the precise differentiation of these tumors as well as non-tumors for improved clinical outcomes. Methods: Here, we present a new method to classify brain tumors based on the MobileNetV2 architecture with advanced preprocessing for high accuracy. We accessed an MRI image dataset from Kaggle that contained 1311 images in the test set. We split the data into 80% training and 20% testing. All images underwent extensive preprocessing, including grayscale conversion, noise removal, and contrast-limited-adaptive-histogram equalization (CLAHE). All images were resized to 224 × 224 pixels. Using transfer learning, the baseline frozen layers were kept intact while the top layers were trained with a learning rate of 0.0001, which was tuned to the model’s requirements using early stopping to avoid overfitting. Results: With the outlined methodology, we obtained an astounding accuracy of 99.16%, including strong performance in the no-tumor category, where recall rates were approaching 100% and false positive rates were minimized. Conclusions: These findings strongly indicate that the application of lightweight convolutional neural networks in diagnostic imaging can considerably expedite accurate brain tumor identification by radiologists.

Oral cancer (OC) remains a major global health concern with survival often limited by late diagnosis. Early and accurate detection is essential to improve patient outcomes and guide treatment decisions. In this study we propose a computer aided diagnostic (CAD) framework for classifying oral squamous cell carcinoma from histopathology images. The model combines Swin transformer for hierarchical feature extraction with vision transformer (ViT) to capture long range dependencies across image regions. SHapley Additive exPlanations (SHAP) based feature selection enhances interpretability by highlighting the most informative features while preprocessing steps such as stain normalization and contrast enhancement improve model generalization and reduce sample variability. Evaluated on a publicly available dataset the framework achieved 99.25% accuracy (ACC) 99.21% sensitivity and a matthews correlation coefficient (MCC) of 98.21% outperforming existing methods. Ablation studies highlighted the importance of positional encoding and statistical analyses confirmed the robustness and reliability of results. To support real-time inference and scalable deployment the proposed model has been integrated into a FastAPI-based web application. This framework offers a powerful interpretable and practical tool for early OC detection and has potential for integration into routine clinical workflows.

Kidney disease is a social and global health concern where early detection is crucial to reducing mortality and improving treatment outcomes. Traditional diagnostic methods are time-consuming and prone to human error. To address the issue, this study proposes an efficient automated deep learning diagnostic system using medical imaging for kidney disease detection and classification. The framework integrates DenseNet121 and EfficientNetB0 for deep feature extraction, followed by SVM, Random Forest, and XGBoost classifiers combined via soft voting. The proposed system was evaluated on 12,446 CT images encompassing four kidney classes: cyst, stone, tumor, and normal. The proposed model achieved outstanding performance metrics with an accuracy of 99.24% and an F1-score of 99%. The proposed model enables early and accurate detection of kidney disease, aiding timely treatment, especially in resource-limited settings.

Due to the advancement of technology and the exponential proliferation of digital sources and textual data, the extraction of high-quality keyphrases and the summarizing of content at a high standard has become increasingly difficult in current research. Extracting high-quality keyphrases and summing texts at a high level demands the use of keyphrase frequency as a feature for keyword extraction, which is becoming more popular. This article proposed a novel unsupervised keyphrase frequency analysis (KFA) technique for feature extraction of keyphrases that is corpus-independent, domain-independent, language-agnostic, and length-free documents, and can be used by supervised and unsupervised algorithms. This proposed technique has five essential phases: data acquisition; data pre-processing; statistical methodologies; curve plotting analysis; and curve fitting technique. First, the technique begins by collecting five different datasets from various sources and then feeding those datasets into the data pre-processing phase using text pre-processing techniques. The preprocessed data is then transmitted to the region-based statistical process, followed by the curve plotting phase, and finally, the curve fitting approach. Afterward, the proposed technique is tested and assessed using five (5) standard datasets. Then, the proposed technique is compared with our recommended systems to prove its efficacy, benefits, and significance. Finally, the experimental findings indicate that the proposed technique effectively analyses the keyphrase frequency from articles and delivers the keyphrase frequency of 70.63% in 1st region and 10.74% in 2nd region of the total present keyphrase frequency.