Search Results (134)

Background: Papillary thyroid microcarcinoma (PTMC), a subtype of papillary thyroid carcinoma ≤ 1 cm in diameter, has shown a marked increase in incidence in recent decades, largely due to the widespread use of neck ultrasonography and fine needle aspiration cytology. Despite its generally indolent course, optimal management of PTMC remains controversial, with treatment strategies ranging from active surveillance to total thyroidectomy. Methods: This retrospective study analyzes five years of experience at a single tertiary care center, including 130 patients diagnosed with PTMC following thyroid surgery between July 2018 and December 2023. Clinical, cytological, and pathological data were collected and analyzed to identify factors influencing surgical decision-making and postoperative outcomes. Patients underwent either total thyroidectomy or hemithyroidectomy, with central and lateral lymph node dissection performed as indicated. Follow-up included clinical and biochemical surveillance for a mean duration of 3 years. Results: Total thyroidectomy was performed in 89.3% of patients, while hemithyroidectomy was limited to 10.7%. Multifocality was observed in 26.1% of cases, with bilateral involvement in 17.7%. Occult lymph node metastases were found in 14.6% (central compartment) and 3.8% (lateral neck). Postoperative radioactive iodine therapy was administered in 23.8% of patients. At final follow-up, 90.7% were disease-free. No significant predictors of recurrence or adverse outcomes were identified, though multifocality and lymph node involvement influenced surgical planning. Conclusions: Our findings support a risk-adapted surgical approach to PTMC, favoring total thyroidectomy in patients with suspicious or multifocal disease to avoid reoperation. While active surveillance and minimally invasive techniques are emerging, total thyroidectomy remains a safe and effective strategy in selected cases. Prospective, multicenter studies are needed to further refine management guidelines for this increasingly common thyroid malignancy. Full article

The increasing complexity of financial reporting has enabled the implementation of innovative accounting practices that often obscure a company’s actual performance. This project seeks to uncover manipulative behaviours by constructing an anomaly detection model that utilises unsupervised machine learning techniques. We examined a dataset of 149,566 Slovak firms from 2016 to 2023, which included 12 financial parameters. Utilising TwoSteps and K-means clustering in IBM SPSS, we discerned patterns of normative financial activity and computed an abnormality index for each firm. Entities with the most significant deviation from cluster centroids were identified as suspicious. The model attained a silhouette score of 1.0, signifying outstanding clustering quality. We discovered a total of 231 anomalous firms, predominantly concentrated in sectors C (32.47%), G (13.42%), and L (7.36%). Our research indicates that anomaly-based models can markedly enhance the precision of fraud detection, especially in scenarios with scarce labelled data. The model integrates intricate data processing and delivers an exhaustive study of the regional and sectoral distribution of anomalies, thereby increasing its relevance in practical applications. Full article

Increased digital banking operations have brought about a surge in suspicious activities, necessitating heightened real-time fraud detection systems. Conversely, traditional static approaches encounter challenges in maintaining privacy while adapting to new fraudulent trends. In this paper, we provide a unique approach to tackling those challenges by integrating VAE-QLSTM with Federated Learning (FL) in a semi-decentralized architecture, maintaining privacy alongside adapting to emerging malicious behaviors. The suggested architecture builds on the adeptness of VAE-QLSTM to capture meaningful representations of transactions, serving in abnormality detection. On the other hand, QLSTM combines quantum computational capability with temporal sequence modeling, seeking to give a rapid and scalable method for real-time malignancy detection. The designed approach was set up through TensorFlow Federated on two real-world datasets—notably IEEE-CIS and European cardholders—outperforming current strategies in terms of accuracy and sensitivity, achieving 94.5% and 91.3%, respectively. This proves the potential of merging VAE-QLSTM with FL to address fraud detection difficulties, ensuring privacy and scalability in advanced banking networks. Full article

Integrated sensing and communication (ISAC) has attracted extensive attention as a key technology to improve spectrum utilization and system performance for future wireless sensor networks. At the same time, active surveillance, as a legitimate means of surveillance, can improve the success rate of surveillance by sending interference signals to suspicious receivers, which is important for crime prevention and public safety. In this paper, we investigate the joint optimization of performance of both ISAC and active surveillance. Specifically, we formulate a bilevel optimization problem where the upper-level objective aims to maximize the probability of successful eavesdropping while the lower-level objective aims to optimize the localization performance of the radar on suspicious transmitters. By employing the Rayleigh quotient, introducing a decoupling strategy, and adding penalty terms, we propose an algorithm to solve the bilevel problem where the lower-level objective is convex. With the help of the proposed algorithm, we obtain the optimal solution of the analog transmit beamforming matrix and the digital beamforming vector. Performance analysis and discussion of key insights, such as the trade-off between eavesdropping success probability and radar localization accuracy, are also provided. Finally, comprehensive simulation results validate the effectiveness of our proposed algorithm in enhancing both the eavesdropping success probability and the accuracy of radar localization. Full article

We present a case with unusual findings on nuclear imaging after mild SARS-CoV-2 infection. During evaluation for an incidentaloma, 18F-Fluorodeoxyglucose Positron Emission Tomography–Computed Tomography imaging showed activity in the thyroid gland, in the lower thoracic spinal column, in portal lymph nodes, and in the terminal ileum and surrounding lymph nodes, all suspicious for metastatic cancer. The patient underwent extensive invasive and non-invasive diagnostic procedures, including biopsies of all the suspicious foci, only showing a small low-grade thyroid cancer that would often be followed and not immediately operated on. Three months later, the findings had either disappeared or were considered reactive. The patient later recalled having had mild COVID-19 seven days prior to the PET/CT. Full article

This study conducts a systematic literature review following the PRISMA framework and the guidelines of Kitchenham and Charters to analyze the application of Internet of Things (IoT) technologies and deep learning models in monitoring violent actions and criminal activities in smart cities. A total of 45 studies published between 2010 and 2024 were selected, revealing that most research, primarily from India and China, focuses on cybersecurity in IoT networks (76%), while fewer studies address the surveillance of physical violence and crime-related events (17%). Advanced neural network models, such as Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and hybrid approaches, have demonstrated high accuracy rates, averaging over 97.44%, in detecting suspicious behaviors. These models perform well in identifying anomalies in IoT security; however, they have primarily been tested in simulation environments (91% of analyzed studies), most of which incorporate real-world data. From a legal perspective, existing proposals mainly emphasize security and privacy. This study contributes to the development of smart cities by promoting IoT-based security methodologies that enhance surveillance and crime prevention in cities in developing countries. Full article

In the era of increasing digitalisation, organisations face the critical challenge of detecting anomalies in large volumes of data, which may indicate suspicious activities. To address this challenge, audit engagements are conducted regularly, and internal auditors and purchasing specialists seek innovative methods to streamline these processes. This study introduces a methodology to prioritise the investigation of anomalies identified in two large real-world purchase datasets. The primary objective is to enhance the effectiveness of companies’ control efforts and improve the efficiency of anomaly detection tasks. The approach begins with a comprehensive exploratory data analysis, followed by the application of unsupervised machine learning techniques to identify anomalies. A univariate analysis is performed using the z-Score index and the DBSCAN algorithm, while multivariate analysis employs k-Means clustering and Isolation Forest algorithms. Additionally, the Silhouette index is used to evaluate the quality of the clustering, ensuring each method produces a prioritised list of candidate transactions for further review. To refine this process, an ensemble prioritisation framework is developed, integrating multiple methods. Furthermore, explainability tools such as SHAP are utilised to provide actionable insights and support specialists in interpreting the results. This methodology aims to empower organisations to detect anomalies more effectively and streamline the audit process. Full article

Pentavalent antimonials are the first line for leishmaniasis treatment, although they induce many adverse side effects and treatment failure and parasite resistance have been detected. Cutaneous leishmaniasis is the main clinical manifestation of the disease in Oaxaca State, Mexico; however, its presence is under-registered, and information about the Leishmania species that circulate and cause the disease in the region is limited. In this study, the presence of Leishmania was analyzed in 24 skin smears and 2 biopsies from lesions suspicious for leishmaniasis in inhabitants of the Tehuantepec Isthmus and Papaloapan Basin regions, Oaxaca State. By ITS1-PCR, the species of clinical isolates were identified. Moreover, the susceptibility of clinical isolates to leishmanicidal drugs was assessed. Skin smears were negative for the presence of Leishmania spp.; meanwhile, parasite amastigotes were observed in tissue biopsies; however, by ITS1-PCR, 46% of the samples were determined to be positive for the parasite. Six clinical isolates were identified as L. mexicana and had lower susceptibility to Miltefosine and Amphotericin B than the L. mexicana reference strain. No leishmanicidal activity of Glucantime was detected. Further studies with increased patient sample sizes and genotypic studies will describe in detail parasite susceptibility to reference drugs in the region. Full article

A moving ground-target recognition system can monitor suspicious activities of pedestrians and vehicles in key areas. Currently, most target recognition systems are based on devices such as fiber optics, radar, and vibration sensors. A system based on vibration sensors has the advantages of small size, low power consumption, strong concealment, easy installation, and low power consumption. However, existing recognition algorithms generally suffer from problems such as the inability to recognize long-distance moving targets and adapt to new environments, as well as low recognition accuracy. Here, we demonstrate that applying transfer learning to recognition algorithms can adapt to new environments and improve accuracy. We proposed a new moving ground-target recognition algorithm based on CNN and domain adaptation. We used convolutional neural networks (CNNS) to extract depth features from target vibration signals to identify target types. We used transfer learning to make the algorithm more adaptable to environmental changes. Our results show that the proposed moving ground-target recognition algorithm can identify target types, improve accuracy, and adapt to a new environment with good performance. We anticipate that our algorithm will be the starting point for more complex recognition algorithms. For example, target recognition algorithms based on multi-modal fusion and transfer learning can better meet actual needs. Full article

Objectives: This study aimed to compare ultrasound (US) findings between automated and handheld breast ultrasound (ABUS and HHUS, respectively) in small breast cancers, based on the breast imaging reporting and data system (BI-RADS) category. Methods: We included 51 women (mean age: 52 years; range: 39–66 years) with breast cancer (invasive or DCIS), all of whom underwent both ABUS and HHUS. Patients with tumors measuring ≤1 cm on either modality were enrolled. Two breast radiologists retrospectively evaluated multiple imaging features, including shape, orientation, margin, echo pattern, and posterior characteristics and assigned BI-RADS categories. Lesion sizes were compared between US and pathological findings. Statistical analyses were performed using Bowker’s test of symmetry, a paired t-test, and a cumulative link mixed model. Results: ABUS assigned lower BI-RADS categories than HHUS while still maintaining malignancy suspicion in categories 4A or higher (54.8% consistent with HHUS; 37.3% downcategorized in ABUS, p = 0.005). While ABUS demonstrated less aggressive margins in some cases (61.3% consistent with HHUS; 25.8% showing fewer suspicious margins in ABUS), this difference was not statistically significant (p = 0.221). Similarly, ABUS exhibited slightly greater height–width ratios compared to HHUS (median, interquartile range: 0.98, 0.7–1.12 vs. 0.86, 0.74–1.10, p = 0.166). No significant differences were observed in other US findings or tumor sizes between the two modalities (all p > 0.05). Conclusions: Small breast cancers exhibited suspicious US features on both ABUS and HHUS, yet they were assigned lower BI-RADS assessment categories on ABUS compared to HHUS. Therefore, when conducting breast cancer screening with ABUS, it is important to remain attentive to even subtle suspicious findings, and active consideration for biopsy may be warranted. Full article

As data center networks grow in scale and complexity, the active inband network telemetry (AINT) system collects a broader range of network status metrics to provide comprehensive visibility for AINT-related network applications, but it also leads to higher measurement costs. To address this issue, we introduce the Flexible Attention-shifting Network Telemetry (FANT), which dynamically focuses on critical links in each measurement cycle. Specifically, FANT employs a metric categorization strategy that divides all measurement metrics into two categories: basic measurements, which are lightweight but cover fewer metrics, and detailed measurements, which are comprehensive but incur higher overhead. Based on the analysis of the previous cycle’s measurements, FANT identifies which links are suspicious and then activates certain probe traces through an attention-shifting mechanism to collect detailed measurements of these links in the current cycle. To further save bandwidth, we model the attention-shifting process and apply heuristic algorithms to solve it. Our experiments show that FANT effectively supports the operation of ANT network applications. In a fat-tree topology with 30 pods, FANT significantly reduces bandwidth usage to 42.6% of the state-of-the-art solution. For scenarios requiring rapid computation, FANT can accelerate algorithm execution ${10}^5$× by setting acceleration factors, with only a 6.4% performance loss. Full article

The accurate and timely detection of cyber threats is critical to keeping our online economy and data safe. A key technique in early detection is the classification of unusual patterns of network behaviour, often hidden as low-frequency events within complex time-series packet flows. One of the ways in which such anomalies can be detected is to analyse the information entropy of the payload within individual packets, since changes in entropy can often indicate suspicious activity—such as whether session encryption has been compromised, or whether a plaintext channel has been co-opted as a covert channel. To decide whether activity is anomalous, we need to compare real-time entropy values with baseline values, and while the analysis of entropy in packet data is not particularly new, to the best of our knowledge, there are no published baselines for payload entropy across commonly used network services. We offer two contributions: (1) we analyse several large packet datasets to establish baseline payload information entropy values for standard network services, and (2) we present an efficient method for engineering entropy metrics from packet flows from real-time and offline packet data. Such entropy metrics can be included within feature subsets, thus making the feature set richer for subsequent analysis and machine learning applications. Full article

Background/Objectives: This study aimed to investigate the actual situation of individuals with unknown health conditions (UHCs) and those indifferent to health (IH) among old-old adults (OOAs) aged 75 years and above using the National Health Insurance Database (KDB) system. Methods: A total of 102 individuals with no history of medical examinations were selected from the KDB system in a city in Japan. Data were collected through home visit interviews and blood pressure monitors distributed by public health nurses (PHNs) from Community Comprehensive Support Centers (CCSCs). The collected data included personal attributes, health concern levels, and responses to a 15-item OOA questionnaire. Semi-structured interviews were conducted with seven PHNs. The control group consisted of 76 users of the “Kayoinoba” service (Kayoinoba users: KUs). Results: Of the 83 individuals who could be interviewed, 50 (49.0%) were classified as UHCs and 11 (10.8%) were classified as IH, including 5 from the low health concern group and 6 who refused to participate. In the word cloud generated from the PHNs’ interviews, the words and phrases “community welfare commissioner”, “community development”, “blood pressure monitor”, “troublesome”, “suspicious”, and “young” were highlighted. In the comparison of health assessments between UHCs and KUs, “body weight loss” and “cognitive function” were more prevalent among KUs, and “smoking” and “social participation” were more prevalent among UHCs. Conclusions: The home visit activities of CCSCs utilizing the KDB system may contribute to an understanding of the actual situation of UHCs, including IHs, among OOAs. UHCs (including patients with IH status) had a higher proportion of risk factors related to smoking and lower social participation than KUs. Full article

One of the tasks of security analysts is to detect security vulnerabilities and ongoing attacks. There is already a large number of software tools that can help to collect security-relevant data, such as event logs, security settings, application manifests, and even the (decompiled) source code of potentially malicious applications. The analyst must study these data, evaluate them, and properly identify and classify suspicious activities and applications. Fast advances in the area of Artificial Intelligence have produced large language models that can perform a variety of tasks, including generating text summaries and reports. In this article, we study the potential black-box use of LLM chatbots as a support tool for security analysts. We provide two case studies: the first is concerned with the identification of vulnerabilities in Android applications, and the second one is concerned with the analysis of security logs. We show how LLM chatbots can help security analysts in their work, but point out specific limitations and security concerns related to this approach. Full article

The number of connected IoT devices is increasing significantly due to their many benefits, including automation, improved efficiency and quality of life, and reducing waste. However, these devices have several vulnerabilities that have led to the rapid growth in the number of attacks. Therefore, several machine learning-based intrusion detection system (IDS) tools have been developed to detect intrusions and suspicious activity to and from a host (HIDS—Host IDS) or, in general, within the traffic of a network (NIDS—Network IDS). The proposed work performs a comparative analysis and an ablative study among recent machine learning-based NIDSs to develop a benchmark of the different proposed strategies. The proposed work compares both shallow learning algorithms, such as decision trees, random forests, Naïve Bayes, logistic regression, XGBoost, and support vector machines, and deep learning algorithms, such as DNNs, CNNs, and LSTM, whose approach is relatively new in the literature. Also, the ensembles are tested. The algorithms are evaluated on the KDD-99, NSL-KDD, UNSW-NB15, IoT-23, and UNB-CIC IoT 2023 datasets. The results show that the NIDS tools based on deep learning approaches achieve better performance in detecting network anomalies than shallow learning approaches, and ensembles outperform all the other models. Full article