Artificial intelligence (AI) has significantly impacted thyroid cancer diagnosis in recent years, offering advanced tools and methodologies that promise to revolutionize patient outcomes. This review provides an exhaustive overview of the contemporary frameworks employed in the field, focusing on the objective of AI-driven analysis and dissecting methodologies across supervised, unsupervised, and ensemble learning. Specifically, we delve into techniques such as deep learning, artificial neural networks, traditional classification, and probabilistic models (PMs) under supervised learning. With its prowess in clustering and dimensionality reduction, unsupervised learning (USL) is explored alongside ensemble methods, including bagging and potent boosting algorithms. The thyroid cancer datasets (TCDs) are integral to our discussion, shedding light on vital features and elucidating feature selection and extraction techniques critical for AI-driven diagnostic systems. We lay out the standard assessment criteria across classification, regression, statistical, computer vision, and ranking metrics, punctuating the discourse with a real-world example of thyroid cancer detection using AI. Additionally, this study culminates in a critical analysis, elucidating current limitations and delineating the path forward by highlighting open challenges and prospective research avenues. Through this comprehensive exploration, we aim to offer readers a panoramic view of AI’s transformative role in thyroid cancer diagnosis, underscoring its potential and pointing toward an optimistic future.

The rapid advancement of Transformer-based models has reshaped the landscape of uncrewed aerial vehicle (UAV) systems by enhancing perception, decision-making, and autonomy. This review article systematically categorizes and evaluates recent developments in Transformer architectures applied to UAVs, including attention mechanisms, convolutional neural network (CNN)-Transformer hybrids, reinforcement learning (RL)-Transformers, and large language models (LLMs). Unlike previous surveys, this work presents a unified taxonomy of Transformer-based UAV models, highlights emerging applications such as precision agriculture and autonomous navigation, and provides comparative analyses through structured tables and performance benchmarks. The article also reviews key datasets, simulators, and evaluation metrics used in the field. Furthermore, it identifies existing gaps in the literature, outlines critical challenges in computational efficiency and real-time deployment, and offers future research directions. This comprehensive synthesis aims to guide researchers and practitioners in understanding and advancing Transformer-driven UAV technologies.

The application of computer-aided diagnosis (CAD) systems in ultrasound (US) image analysis using maching learning (ML) has been widely explored. Recently, deep learning (DL) has played a pivotal role in advancing this research. This paper proposes an automated method for thyroid cancer (TC) image classification, utilizing transfer learning (TL) with VGG16, a well-established pre-trained neural network. The approach involves preprocessing, data augmentation, and classification using TL. The results are compared to convolutional neural networks (CNNs) for distinguishing between benign and malignant thyroid nodules (TNs). Model performance is evaluated using accuracy, precision, sensitivity, specificity, and F1-score metrics. The promising results highlight the effectiveness of TL in US image analysis. The best results, achieved using the TL algorithm, include an accuracy of 0.9878, sensitivity of 0.9705, specificity of 0.9854, and an F1-score of 0.9866. These values represent significant improvements over the baseline models, and the study is conducted using the DDTI dataset for TC, distinguishing between benign and malignant cases.

The rapid advancement of Transformer-based models has reshaped the landscape of uncrewed aerial vehicle (UAV) systems by enhancing perception, decision-making, and autonomy. This review paper systematically categorizes and evaluates recent developments in Transformer architectures applied to UAVs, including attention mechanisms, CNN-Transformer hybrids, reinforcement learning Transformers, and large language models (LLMs). Unlike previous surveys, this work presents a unified taxonomy of Transformer-based UAV models, highlights emerging applications such as precision agriculture and autonomous navigation, and provides comparative analyses through structured tables and performance benchmarks. The paper also reviews key datasets, simulators, and evaluation metrics used in the field. Furthermore, it identifies existing gaps in the literature, outlines critical challenges in computational efficiency and real-time deployment, and offers future research directions. This comprehensive synthesis aims to guide researchers and practitioners in understanding and advancing Transformer-driven UAV technologies.

Background and Objectives: Classification of thyroid nodules (TN) in ultrasound remains challenging due to limited labelled data and the limited capacity of conventional feature representations to capture complex, multi-directional textures. This work aims to improve data-efficient TN classification by integrating a geometry-adaptive Bandelet Transform (BT) with transfer learning (TL) to enhance feature representation and generalisation. Methods: The proposed pipeline first applies BT to strengthen directional and structural encoding in ultrasound images via quadtree-driven geometric adaptation. It then mitigates class imbalance using SMOTE and increases data diversity through targeted data augmentation. The resulting representations are classified using multiple ImageNet-pretrained architectures, where VGG19 yields the most consistent performance. Results: Experiments on the publicly available DDTI dataset show that BT-based preprocessing consistently improves performance over classical wavelet representations across multiple quadtree thresholds, with the best results obtained at $T=30$. Under this setting, the proposed BT+TL (VGG19) model achieves 98.91% accuracy, 98.11% sensitivity, 97.31% specificity, and a 98.89% F1-score, outperforming comparable approaches reported in the literature. Conclusions: Coupling geometry-adaptive transforms with modern TL backbones provides a robust and data-efficient strategy for ultrasound TN classification, particularly under limited annotation and challenging texture variability. The complete project is publicly available.