Disease recognition has been revolutionized by autonomous systems in the rapidly developing field of medical technology. A crucial aspect of diagnosis involves the visual assessment and enumeration of white blood cells in microscopic peripheral blood smears. This practice yields invaluable insights into a patient’s health, enabling the identification of conditions of blood malignancies such as leukemia. Early identification of leukemia subtypes is paramount for tailoring appropriate therapeutic interventions and enhancing patient survival rates. However, traditional diagnostic techniques, which depend on visual assessment, are arbitrary, laborious, and prone to errors. The advent of ML technologies offers a promising avenue for more accurate and efficient leukemia classification. In this study, we introduced a novel approach to leukemia classification by integrating advanced image processing, diverse dataset utilization, and sophisticated feature extraction techniques, coupled with the development of TL models. Focused on improving accuracy of previous studies, our approach utilized Kaggle datasets for binary and multiclass classifications. Extensive image processing involved a novel LoGMH method, complemented by diverse augmentation techniques. Feature extraction employed DCNN, with subsequent utilization of extracted features to train various ML and TL models. Rigorous evaluation using traditional metrics revealed Inception-ResNet’s superior performance, surpassing other models with F1 scores of 96.07% and 95.89% for binary and multiclass classification, respectively. Our results notably surpass previous research, particularly in cases involving a higher number of classes. These findings promise to influence clinical decision support systems, guide future research, and potentially revolutionize cancer diagnostics beyond leukemia, impacting broader medical imaging and oncology domains.

Timely and specific interventions can substantially help in managing the disease, provided that the PD is diagnosed at an early stage. This paper compares machine learning (ML) and deep learning (DL) methods of PD detection with the help of vocal characteristics of a canonical sample (197 samples with 22 voice attributes pre-extracted). To reduce the issue of class imbalance, the Synthetic Minority Over-Sampling Technique (SMOTE) was used on the training data, which enhanced the strength of the models. The classical Machine Learning (ML) classifiers, such as Logistic Regression, Support Vector Machine, Random Forest, Extra Trees, Decision Tree, AdaBoost, and K-Nearest Neighbors (KNN) were evaluated, and KNN produced the best accuracy of 85% as well as competitive accuracy, recall, F1 score, and AUC ROC. In the case of deep learning, 1D CNN, 2D CNN, and LSTM were used, and 2D CNN and LSTM performed better than 1D CNN, with test accuracy of 89.7% and 84.6%, respectively, indicating their capability to learn both time-based and spatial patterns in data. Interpretability was added through Local Interpretable Model Agnostic Explanations (LIME) to ML models that point to Spread2, Recurrence Period Density Entropy, and MDVP-related frequency measures as significant vocal biomarkers. Although the framework has constraints relating to data volume and single modality, it offers a reproducible, interpretable baseline of PD detection and highlights the possibilities of explainable AI and neural networks as an assistant clinical decision-making tool. In the future, larger, multi-modal datasets are needed to offer better generalizability.

Accurate brain tumor classification from Magnetic Resonance Imaging (MRI) remains challenging due to dataset heterogeneity, class imbalance, and limited interpretability, while practical deployment further requires models that balance predictive performance with computational efficiency. In this work, we propose NeuroTrustNet , an integrated multimodal framework that combines complementary convolutional neural network (CNN), Vision Transformer (ViT), and handcrafted radiomic representations through the proposed Adaptive Attention Stacking (AAS) mechanism, enabling sample-specific feature fusion to improve robustness under cross-dataset variability while maintaining deployment-oriented computational efficiency. To evaluate performance under different computational constraints, we consider both high-capacity ensemble models (CNN and ViT ensembles) and lightweight architectures (RapidNet and AdaptoVision) as baseline systems. Experimental results on a large multi-dataset corpus show that while high-capacity ensembles achieve the highest accuracy (up to 96% on an external test set), the proposed NeuroTrustNet maintains competitive performance (94%) while reducing the computational cost of the fusion optimization stage by approximately 80% compared with full end-to-end ensemble training, highlighting its suitability for deployment-oriented medical AI systems operating under computational constraints while maintaining an effective balance between accuracy and efficiency. To further enhance interpretability, we incorporate a post-hoc interpretability component combining visual attribution maps with structured textual summaries derived from model outputs, enabling transparent and human-readable insights without influencing model predictions. The results demonstrate the potential of NeuroTrustNet as a deployment-oriented multimodal decision-support framework, providing a competitive balance between predictive performance, computational efficiency, and interpretability under cross-dataset variability.