Background: Addressing the complex diagnostic challenges of Alzheimer’s disease (AD), this study introduces FusionNet, a groundbreaking framework designed to enhance AD classification through the integration of multi-modal and longitudinal imaging data. Methods: FusionNet synthesizes inputs from Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), and Computed Tomography (CT) scans, harnessing advanced machine learning strategies such as generative adversarial networks (GANs) for robust data augmentation, lightweight neural architectures for efficient computation, and deep metric learning for precise feature extraction. The model uniquely combines cross-sectional and temporal data, significantly enhancing diagnostic accuracy and enabling the early detection and ongoing monitoring of AD. The FusionNet architecture incorporates specialized feature extraction pathways for each imaging modality, a fusion layer to integrate diverse data sources effectively, and attention mechanisms to focus on salient diagnostic features. Results: Demonstrating superior performance, FusionNet achieves an accuracy of 94%, with precision and recall rates of 92% and 93%, respectively. Conclusions: These results underscore its potential as a highly reliable diagnostic tool for AD, facilitating early intervention and tailored treatment strategies. FusionNet’s innovative approach not only improves diagnostic precision but also offers new insights into the progression of Alzheimer’s disease, supporting personalized patient care and advancing our understanding of this debilitating condition.

Background: Reinforcement learning (RL) represents a significant advancement in artificial intelligence (AI), particularly for complex sequential decision-making challenges. Its capability to iteratively refine decisions makes it ideal for applications in medicine, such as the detection of cervical cancer; a major cause of mortality among women globally. The Pap smear test, a crucial diagnostic tool for cervical cancer, benefits from enhancements in AI, facilitating the development of automated diagnostic systems that improve screening effectiveness. This research introduces RL-Cervix.Net, a hybrid model integrating RL with convolutional neural network (CNN) technologies, aimed at elevating the precision and efficiency of cervical cancer screenings. Methods: RL-Cervix.Net combines the robust ResNet-50 architecture with a reinforcement learning module tailored for the unique challenges of cytological image analysis. The model was trained and validated using three extensive public datasets to ensure its effectiveness under realistic conditions. A novel application of RL for dynamic feature refinement and adjustment based on reward functions was employed to optimize the detection capabilities of the model. Results: The innovative integration of RL into the CNN framework allowed RL-Cervix.Net to achieve an unprecedented classification accuracy of 99.98% in identifying atypical cells indicative of cervical lesions. The model demonstrated superior accuracy and interpretability compared to existing methods, addressing variability and complexities inherent in cytological images. Conclusions: The RL-Cervix.Net model marks a significant breakthrough in the application of AI for medical diagnostics, particularly in the early detection of cervical cancer. By significantly improving diagnostic accuracy and efficiency, RL-Cervix.Net has the potential to enhance patient outcomes through earlier and more precise identification of the disease, ultimately contributing to reduced mortality rates and improved healthcare delivery.

Purpose: Cervical cancer significantly impacts global health, where early detection is piv- otal for improving patient outcomes. This study aims to enhance the accuracy of cervical cancer diagnosis by addressing class imbalance through a novel hybrid deep learning model. Methods: The proposed model, RL-CancerNet, integrates EfficientNetV2 and Vision Transformers (ViTs) within a Reinforcement Learning (RL) framework. EfficientNetV2 extracts local features from cervical cytology images to capture fine-grained details, while ViTs analyze these features to recognize global dependencies across image patches. To address class imbalance, an RL agent dynamically adjusts the focus towards minority classes, thus reducing the common bias towards majority classes in medical image classification. Additionally, a Supporter Module incorporating Conv3D and BiLSTM layers with an attention mechanism enhances contextual learning. Results: RL-CancerNet was evaluated on the benchmark cervical cytology datasets Herlev and SipaKMeD, achieving an exceptional accuracy of 99.7%. This performance surpasses several state-of-the-art models, demonstrating the model’s effectiveness in identifying subtle diagnostic features in complex backgrounds. Conclusions: The integration of CNNs, ViTs, and RL into RL-CancerNet significantly improves the diagnostic accuracy of cervical cancer screenings. This model not only advances the field of automated medical screening but also provides a scalable framework adaptable to other medical imaging tasks, potentially enhancing diagnostic processes across various medical domains.

Gaze estimation is increasingly pivotal in applications spanning virtual reality, augmented reality, and driver monitoring systems, necessitating efficient yet accurate models for mobile deployment. Current methodologies often fall short, particularly in mobile settings, due to their extensive computational requirements or reliance on intricate pre-processing. Addressing these limitations, we present Mobile-GazeCapsNet, an innovative gaze estimation framework that harnesses the strengths of capsule networks and integrates them with lightweight architectures such as MobileNet v2, MobileOne, and ResNet-18. This framework not only eliminates the need for facial landmark detection but also significantly enhances real-time operability on mobile devices. Through the innovative use of Self-Attention Routing, GazeCapsNet dynamically allocates computational resources, thereby improving both accuracy and efficiency. Our results demonstrate that GazeCapsNet achieves competitive performance by optimizing capsule networks for gaze estimation through Self-Attention Routing (SAR), which replaces iterative routing with a lightweight attention-based mechanism, improving computational efficiency. Our results show that GazeCapsNet achieves state-of-the-art (SOTA) performance on several benchmark datasets, including ETH-XGaze and Gaze360, achieving a mean angular error (MAE) reduction of up to 15% compared to existing models. Furthermore, the model maintains a real-time processing capability of 20 milliseconds per frame while requiring only 11.7 million parameters, making it exceptionally suitable for real-time applications in resource-constrained environments. These findings not only underscore the efficacy and practicality of GazeCapsNet but also establish a new standard for mobile gaze estimation technologies.

Background/Objectives: Accurate and efficient segmentation of cervical cells is crucial for the early detection of cervical cancer, enabling timely intervention and treatment. Existing segmentation models face challenges with complex cellular arrangements, such as overlapping cells and indistinct boundaries, and are often computationally intensive, which limits their deployment in resource-constrained settings. Methods: In this study, we introduce a lightweight and efficient segmentation model specifically designed for cervical cell analysis. The model employs a MobileNetV2 architecture for feature extraction, ensuring a minimal parameter count conducive to real-time processing. To enhance boundary delineation, we propose a novel force map approach that drives pixel adjustments inward toward the centers of cells, thus improving cell separation in densely packed areas. Additionally, we integrate extreme point supervision to refine segmentation outcomes using minimal boundary annotations, rather than full pixel-wise labels. Results: Our model was rigorously trained and evaluated on a comprehensive dataset of cervical cell images. It achieved a Dice Coefficient of 0.87 and a Boundary F1 Score of 0.84, performances that are comparable to those of advanced models but with considerably lower inference times. The optimized model operates at approximately 50 frames per second on standard low-power hardware. Conclusions: By effectively balancing segmentation accuracy with computational efficiency, our model addresses critical barriers to the widespread adoption of automated cervical cell segmentation tools. Its ability to perform in real time on low-cost devices makes it an ideal candidate for clinical applications and deployment in low-resource environments. This advancement holds significant potential for enhancing access to cervical cancer screening and diagnostics worldwide, thereby supporting broader healthcare initiatives.

Tunnel fires pose a severe threat to human safety and infrastructure, necessitating the development of advanced and efficient fire detection systems. This paper presents a novel lightweight deep learning (DL) model specifically designed for real-time fire classification in tunnel environments. This model integrates MobileNetV3 for spatial feature extraction, Temporal Convolutional Networks (TCNs) for temporal sequence analysis, and advanced attention mechanisms, including Convolutional Block Attention Modules (CBAMs) and Squeeze-and-Excitation (SE) blocks, to prioritize critical features such as flames and smoke patterns while suppressing irrelevant noise. The model is trained on a custom dataset containing real tunnel fire incidents generated using a newly prepared dataset. This approach enhances the model generalization capabilities, enabling it to handle diverse fire scenarios, including those with low visibility, high smoke density, and variable ventilation conditions. Deployment optimizations, such as quantization and layer fusion, ensure computational efficiency, achieving an average inference time of 12ms/frame, making it suitable for resource-constrained environments like IoT and edge devices. The experimental results demonstrate that the proposed model achieves an accuracy of 96.5%, a precision of 95.7%, and a recall of 97.2%, significantly outperforming state-of-the-art (SOTA) models such as ResNet50 and YOLOv5 in both accuracy and real-time performance. Robustness tests under challenging conditions validate model reliability and adaptability, marking it as a critical advancement in tunnel fire detection systems. This study provides valuable insights into the design and deployment of efficient fire classification systems for safety-critical applications. The proposed model offers a scalable, high-performance solution for tunnel fire monitoring and establishes a benchmark for future research in real-time video-based classification under complex environmental conditions.