Frontiers in Artificial Intelligence最新文献

Camouflaged object detection (COD) aims to identify objects that are visually indistinguishable from their surrounding background, making it challenging to precisely distinguish the boundaries between objects and backgrounds in camouflaged environments. In recent years, numerous studies have leveraged frequency-domain methods to aid in camouflage target detection by utilizing frequency-domain information. However, current methods based on the frequency domain cannot effectively capture the boundary information between disguised objects and the background. To address this limitation, we propose a Laplace transform-guided camouflage object detection network called the Self-Correlation Cross Relation Network (SeCoCR). In this framework, the Laplace-transformed camouflage target is treated as high-frequency information, while the original image serves as low-frequency information. These are then separately input into our proposed Self-Relation Attention module to extract both local and global features. Within the Self-Relation Attention module, key semantic information is retained in the low-frequency data, and crucial boundary information is preserved in the high-frequency data. Furthermore, we design a multi-scale attention mechanism for low- and high-frequency information, Low-High Mix Fusion, to effectively integrate essential information from both frequencies for camouflage object detection. Comprehensive experiments on three COD benchmark datasets demonstrate that our approach significantly surpasses existing state-of-the-art frequency-domain-assisted methods.

Introduction: Privacy has become a significant concern in the digital world, especially concerning the personal data collected by websites and other service providers on the World Wide Web network. One of the significant approaches to enable the individual to control privacy is the privacy policy document, which contains vital information on this matter. Publishing a privacy policy is required by regulation in most Western countries. However, the privacy policy document is a natural free text-based object, usually phrased in a legal language, and rapidly changes, making it consequently relatively hard to understand and almost always neglected by humans.

Methods: This research proposes a novel methodology to receive an unstructured privacy policy text and automatically structure it into predefined parameters. The methodology is based on a two-layer artificial intelligence (AI) process.

Results: In an empirical study that included 49 actual privacy policies from different websites, we demonstrated an average F1-score > 0.8 where five of six parameters achieved a very high classification accuracy.

Discussion: This methodology can serve both humans and AI agents by addressing issues such as cognitive burden, non-standard formalizations, cognitive laziness, and the dynamics of the document across a timeline, which deters the use of the privacy policy as a resource. The study addresses a critical gap between the present regulations, aiming at enhancing privacy, and the abilities of humans to benefit from the mandatory published privacy policy.

Classification is a central task in machine learning, underpinning applications in domains such as finance, medicine, engineering, information technology, and biology. However, machine learning pattern classification can become a complex or even inexplicable task for current robust models due to the complexity of objective datasets, which is why there is a strong interest in achieving high classification performance. On the other hand, in particular cases, there is a need to achieve such performance while maintaining a certain level of explainability in the operation and decisions of classification algorithms, which can become complex. For this reason, an algorithm is proposed that is robust, simple, highly explainable, and applicable to datasets primarily in medicine with complex class imbalance. The main contribution of this research is a novel machine learning classification algorithm based on binary string similarity that is competitive, simple, interpretable, and transparent, as it is clear why a pattern is classified into a given class. Therefore, a comparative study of the performance of the best-known state-of-the-art classification algorithms and the proposed model is presented. The experimental results demonstrate the benefits of the proposal in this research work, which were validated through statistical hypothesis tests to assess significant performance differences.

Background: The integration of large language models (LLMs) into cardio-oncology patient education holds promise for addressing the critical gap in accessible, accurate, and patient-friendly information. However, the performance of publicly available LLMs in this specialized domain remains underexplored.

Objectives: This study evaluates the performance of three LLMs (ChatGPT-4, Kimi, DouBao) act as assistants for physicians in cardio-oncology patient education and examines the impact of prompt engineering on response quality.

Methods: Twenty standardized questions spanning cardio-oncology topics were posed twice to three LLMs (ChatGPT-4, Kimi, DouBao): once without prompts and once with a directive to simplify language, generating 240 responses. These responses were evaluated by four cardio-oncology specialists for accuracy, comprehensiveness, helpfulness, and practicality. Readability and complexity were assessed using a Chinese text analysis framework.

Results: Among 240 responses, 63.3% were rated "correct," 35.0% "partially correct," and 1.7% "incorrect." No significant differences in accuracy were observed between models (p = 0.26). Kimi demonstrated no incorrect responses. Significant declines in comprehensiveness (p = 0.03) and helpfulness (p < 0.01) occurred post-prompt, particularly for DouBao (accuracy: 57.5% vs. 7.5%, p < 0.01). Readability metrics (readability age, difficulty score, total word count, sentence length) showed no inter-model differences, but prompts reduced complexity (e.g., DouBao's readability age decreased from 12.9 ± 0.8 to 10.1 ± 1.2 years, p < 0.01).

Conclusion: Publicly available LLMs provide largely accurate responses to cardio-oncology questions, yet their utility is constrained by inconsistent comprehensiveness and sensitivity to prompt design. While simplifying language improves readability, it risks compromising clinical relevance. Tailored fine-tuning and specialized evaluation frameworks are essential to optimize LLMs for patient education in cardio-oncology.

Introduction: Pulmonary hypertension (PH) has an incidence of approximately 6 cases per million adults, with a global prevalence ranging from 49 to 55 cases per million adults. Recent advancements in artificial intelligence (AI) have demonstrated promising improvements in the diagnostic accuracy of imaging for PH, achieving an area under the curve (AUC) of 0.94, compared to seasoned professionals.

Research objective: To systematically synthesize available evidence on the comparative accuracy of AI versus manual interpretation in detecting PH across various chest imaging modalities, i.e., chest X-ray, echocardiography, CT scan and cardiac MRI.

Methods: Following PRISMA guidelines, a comprehensive search was conducted across five databases-PubMed, Embase, ScienceDirect, Scopus, and the Cochrane Library-from inception through March 2025. Statistical analysis was performed using R (version 2024.12.1 + 563) with 2 × 2 contingency data. Sensitivity, specificity, and diagnostic odds ratio (DOR) were pooled using a bivariate random-effects model (reitsma() from the mada package), while the AUC were meta-analyzed using logit-transformed values via the metagen() function from the meta package.

Results: This meta-analysis of 12 studies, encompassing 7,459 patients, demonstrated a statistically significant improvement in diagnostic accuracy of PH with AI integration, evidenced by a logit mean difference in AUC of 0.43 (95% CI: 0.23-0.64; p < 0.0001) and low heterogeneity (I ² = 21.0%, τ ² < 0.0001, p = 0.2090), which was consolidated by pooled AUC of 0.934 on bivariate model. Pooled sensitivity and specificity for AI models were 0.83 (95% CI: 0.73-0.90) and 0.91 (95% CI: 0.86-0.95), respectively, with substantial heterogeneity for sensitivity (I ² = 83.8%, τ ² = 0.4934, p < 0.0001) and moderate for specificity (I ² = 41.5%, τ ² = 0.1015, p = 0.1146); the diagnostic odds ratio was 54.26 (95% CI: 22.50-130.87) with substantial heterogeneity (I ² = 70.7%, τ ² = 0.8451, p = 0.0023). Sensitivity analysis showed stable estimates and did not reduce heterogeneity across outcomes.

Conclusion: AI-integrated imaging significantly enhances diagnostic accuracy for pulmonary hypertension, with higher sensitivity (0.83) and specificity (0.91) compared to manual interpretation across chest imaging modalities. However, further high-quality trials with externally validated cohorts may be needed to confirm these findings and reduce variability among AI models across diverse clinical settings.

[This corrects the article DOI: 10.3389/frai.2025.1701951.].

Painting authentication is an inherently complex task, often relying on a combination of connoisseurship and technical analysis. This study focuses on the authentication of a single painting attributed to Paolo Veronese, using a convolutional neural network approach tailored to severe data scarcity. To ensure that stylistic comparisons were based on artistic execution rather than iconographic differences, the dataset was restricted to paintings depicting the Holy Family, the same subject as the work under authentication. A custom shallow convolutional network was developed to process multichannel inputs (RGB, grayscale, and edge maps) extracted from overlapping patches via a sliding-window strategy. This patch-based design expanded the dataset from a small number of paintings to thousands of localized patches, enabling the model to learn microtextural and brushstroke features. Regularization techniques were employed to enhance generalization, while a painting-level cross-validation strategy was used to prevent data leakage. The model achieved high classification performance (accuracy of 94.51%, Area under the Curve 0.99) and generated probability heatmaps that revealed stylistic coherence in authentic Veronese works and fragmentation in non-Veronese paintings. The work under examination yielded an intermediate global mean Veronese probability (61%) with extensive high-probability regions over stylistically salient passages, suggesting partial stylistic affinity. The results support the use of patch-based models for stylistic analysis in art authentication, especially under domain-specific data constraints. While the network provides strong probabilistic evidence of stylistic affinity, definitive attribution requires further integration with historical, technical, and provenance-based analyses.

This study reviews the advancements in AI-driven methods for predicting stock prices, tracing their evolution from traditional approaches to modern finance. The role of AI in the market extends beyond predictive systems to encompass the intersection of financial markets with emerging technologies, such as blockchain, and the potential influence of quantum computing on economic modeling. A decentralized finance system examines the application of Reinforcement Learning in financial market prediction, highlighting its potential for continuous learning from dynamic market conditions. The study discusses the development of hybrid prediction models, stock market machine learning systems, and AI-driven investment portfolio management. The potential of quantum computing enhances portfolio analysis, fraud detection, optimization, and asset valuation for complex market predictions, as well as the impact of blockchain technologies on transparency, security, and efficiency. Machine learning techniques can significantly automate data collection and purification. Financial decision-making and the application of time-series analysis techniques can be readily learned through deep reinforcement learning for stock price prediction. Deep Neural Networks and Strategic Asset Allocation can be managed by evaluating performance and portfolio using real-time market insights from AI models. Although there are numerous ethical, sentimental, regulatory, and data quality issues in market prediction, the future job market is heavily dependent on these criteria, particularly through effective risk management and fraud detection.

Cyberbullying on social networks has emerged as a pressing global issue, yet research in low-resource languages such as Bengali remains underdeveloped due to the scarcity of high-quality datasets, linguistic resources, and targeted methodologies. Many existing approaches overlook essential language-specific preprocessing, neglect the integration of advanced transformer-based models, and do not adequately address model validation, scalability, and adaptability. To address these limitations, this study introduces three Bengali-specific preprocessing strategies to enhance feature representation. It then proposes Transformer-stacking, an effective hybrid detection framework that combines three transformer models, XLM-R-base, multilingual BERT, and Bangla-Bert-Base, via a stacking strategy with a multi-layer perceptron classifier. The framework is evaluated on a publicly available Bengali cyberbullying dataset comprising 44,001 samples across both binary (Sub-task A) and multiclass (Sub-task B) classification settings. Transformer-stacking achieves an F1-score of 93.61% and an accuracy of 93.62% for Sub-task A, and an F1-score and accuracy of 89.23% for Sub-task B, outperforming eight baseline transformer models, four transformer ensemble techniques, and recent state-of-the-art methods. These improvements are statistically validated using McNemar's test. Furthermore, experiments on two external Bengali datasets, focused on hate speech and abusive language, demonstrate the model's scalability and adaptability. Overall, Transformer-stacking offers an effective and generalizable solution for Bengali cyberbullying detection, establishing a new benchmark in this underexplored domain.