Purpose: Gastrointestinal (GI) illness demands precise and efficient diagnostics, yet conventional approaches (e.g., endoscopy and histopathology) are time-consuming and prone to reader variability. This work presents GID-Xpert, a deep learning framework designed to improve feature learning, accuracy, and interpretability for GI disease classification. Methods: GID-Xpert integrates a hierarchical, multi-stage attention-driven mixture of experts with dynamic routing. The architecture couples spatial–channel attention mechanisms with specialized expert blocks; a routing module adaptively selects expert paths to enhance representation quality and reduce redundancy. The model is trained and evaluated on three benchmark datasets—WCEBleedGen, GastroEndoNet, and the King Abdulaziz University Hospital Capsule (KAUHC) dataset. Comparative experiments against state-of-the-art baselines and ablation studies (removing attention, expert blocks, and routing) are conducted to quantify the contribution of each component. Results: GID-Xpert achieves superior performance with 100% accuracy on WCEBleedGen, 99.98% on KAUHC, and 75.32% on GastroEndoNet. Comparative evaluations show consistent improvements over contemporary models, while ablations confirm the additive benefits of spatial–channel attention, expert specialization, and dynamic routing. The design also yields reduced computational cost and improved explanation quality via attention-driven reasoning. Conclusion: By unifying attention, expert specialization, and dynamic routing, GID-Xpert delivers accurate, computationally efficient, and more interpretable GI disease classification. These findings support GID-Xpert as a credible diagnostic aid and a strong foundation for future extensions toward broader GI pathologies and clinical integration.

This paper investigates the effectiveness of various data augmentation techniques for enhancing Arabic speech emotion recognition (SER) using convolutional neural networks (CNNs). Utilizing the Saudi Dialect and BAVED datasets, we address the challenges of limited and imbalanced data commonly found in Arabic SER. To improve model performance, we apply augmentation techniques such as noise addition, time shifting, increasing volume, and reducing volume. Additionally, we examine the optimal number of augmentations required to achieve the best results. Our experiments reveal that these augmentations significantly enhance the CNN’s ability to recognize emotions, with certain techniques proving more effective than others. Furthermore, the number of augmentations plays a critical role in balancing model accuracy. The Saudi Dialect dataset achieved its best results with two augmentations (increasing volume and decreasing volume), reaching an accuracy of 96.81%. Similarly, the BAVED dataset demonstrated optimal performance with a combination of three augmentations (noise addition, increasing volume, and reducing volume), achieving an accuracy of 92.60%. These findings indicate that carefully selected augmentation strategies can greatly improve the performance of CNN-based SER systems, particularly in the context of Arabic speech. This research underscores the importance of tailored augmentation techniques to enhance SER performance and sets a foundation for future advancements in this field.

Background/Objectives: Accurate and reliable automated dermoscopic lesion classification remains challenging. This is due to pronounced dataset bias, limited expert-annotated data, and poor cross-dataset generalization of conventional supervised deep learning models. In clinical dermatology, these limitations restrict the deployment of data-driven diagnostic systems across diverse acquisition settings and patient populations. Methods: Motivated by these challenges, this study proposes a transformer-based, dermatology-specific foundation model. The model learns transferable visual representations from large collections of unlabeled dermoscopic images via self-supervised pretraining. It integrates large-scale dermatology-oriented self-supervised learning with a hierarchical vision transformer backbone. This enables effective capture of both fine-grained lesion textures and global morphological patterns. The evaluation is conducted across three publicly available dermoscopic datasets: ISIC 2018, HAM10000, and PH2. The study assesses in-dataset, cross-dataset, limited-label, ablation, and computational-efficiency settings. Results: The proposed approach achieves in-dataset classification accuracies of 94.87%, 97.32%, and 98.17% on ISIC 2018, HAM10000, and PH2, respectively. It outperforms strong transformer and hybrid baselines. Cross-dataset transfer experiments show consistent performance gains of 3.5–5.8% over supervised counterparts. This indicates improved robustness to domain shift. Furthermore, when fine-tuned with only 10% of the labeled training data, the model achieves performance comparable to fully supervised baselines. Conclusions: This highlights strong data efficiency. These results demonstrate that dermatology-specific foundation learning offers a principled and practical solution for robust dermoscopic lesion classification under realistic clinical constraints.

Background and Objective: Accurate classification of standard fetal ultrasound planes is a critical step in prenatal diagnostics, enabling reliable biometric measurements and anomaly detection. Conventional deep learning approaches, particularly convolutional neural networks (CNNs) and transformers, often face challenges such as domain variability, noise artifacts, class imbalance, and poor calibration, which limit their clinical utility. This study proposes a hybrid state–space and vision transformer framework designed to address these limitations by integrating sequential dynamics and global contextual reasoning. Methods: The proposed framework comprises five stages: (i) preprocessing for ultrasound harmonization using intensity normalization, anisotropic diffusion filtering, and affine alignment; (ii) hybrid feature encoding with a state–space model (SSM) for sequential dependency modeling and a vision transformer (ViT) for global self-attention; (iii) multi-task learning (MTL) with anatomical regularization leveraging classification, segmentation, and biometric regression objectives; (iv) gated decision fusion for balancing local sequential and global contextual features; and (v) calibration strategies using temperature scaling and entropy regularization to ensure reliable confidence estimation. The framework was comprehensively evaluated on three publicly available datasets: FETAL_PLANES_DB, HC18, and a large-scale fetal head dataset. Results: The hybrid framework consistently outperformed baseline CNN, SSM-only, and ViT-only models across all tasks. On FETAL_PLANES_DB, it achieved an accuracy of 95.8%, a macro-F1 of 94.9%, and an ECE of 1.5%. On the Fetal Head dataset, the model achieved 94.1% accuracy and a macro-F1 score of 92.8%, along with superior calibration metrics. For HC18, it achieved a Dice score of 95.7%, an IoU of 91.7%, and a mean absolute error of 2.30 mm for head circumference estimation. Cross-dataset evaluations confirmed the model’s robustness and generalization capability. Ablation studies further demonstrated the critical role of SSM, ViT, fusion gating, and anatomical regularization in achieving optimal performance. Conclusions: By combining state–space dynamics and transformer-based global reasoning, the proposed framework delivers accurate, calibrated, and clinically meaningful predictions for fetal ultrasound plane classification and biometric estimation. The results highlight its potential for deployment in real-time prenatal screening and diagnostic systems.

PatternFusion is a new ensemble framework that attempts to overcome the drawbacks of classical time-series analysis with the property of interpretability, along with high performance and multi-scale temporal detection. Predesign pattern recognition approaches in time-series usually work individually, forgetting about the collaborative potential of statistical models with deep learning structures. To address this, PatternFusion integrates seamlessly the BiLSTM networks for temporal memory, the CNN modules for spatial analysis and the LightGBM for statistical interpretability by a dynamic attention-driven fusion mechanism. Our multi-criteria optimization approach increases precision, robustness against a noisy input, interpretability, and the computational efficiency. A large set of experiments on various benchmark datasets proves the dominance on all F1-score, AUC, and EER measures that characterize robust detection of complex temporal patterns. Key innovations are adaptive attention-based fusion, multi-scale temporal feature encoding, explicit confidence quantification and temporal post-processing. These features combined together allow high-fidelity monitoring in critical applications like healthcare, finance, industrial systems and environmental sensing making PatternFusion a transformative solution for real-time, interpretable time-series pattern recognition.

Background: Diagnosing CNS tumors through MRI is limited by significant variability in scanner hardware, acquisition protocols, and intensity characteristics at clinical centers, resulting in substantial domain shifts that lead to diminished reliability for automated models. Methods: We present a Domain-Adaptive MRI Learning Model (DA-MLM) consisting of an adversarially aligned hybrid 3D CNN–transformer encoder with contrastive regularization and covariance-based feature harmonization. Varying sequence MRI inputs ($T1$, $T1ce$, $T2$, and $FLAIR$) were inputted to multi-scale convolutional layers followed by global self-attention to effectively capture localized tumor structure and long-range spatial context, with domain adaptation that harmonizes feature distribution across datasets. Results: On the BraTS 2020 dataset, we found DA-MLM achieved 94.8% accuracy, 93.6% macro-F1, and 96.2% AUC, improving upon previously established benchmarks by 2–4%. DA-MLM also attained Dice score segmentation of 93.1% (WT), 91.4% (TC), and 89.5% (ET), improving upon 2–3.5% for CNN and transformer methods. On the REMBRANDT dataset, DA-MLM achieved 92.3% accuracy with segmentation improvements of 3–7% over existing U-Net and expert annotations. Robustness testing indicated 40–60% less degradation under noise, contrast shift, and motion artifacts, and synthetic shifts in scanner location showed negligible performance impairment (<0.06). Cross-domain evaluation also demonstrated 5–11% less degradation than existing methods. Conclusions: In summary, DA-MLM demonstrates improved accuracy, segmentation fidelity, and robustness to perturbations, as well as strong cross-domain generalization indicating the suitability for deployment in multicenter MRI applications where variation in imaging performance is unavoidable.