UNASSIGNED: Radiography plays an important role in medical care, and accurate positioning is essential for providing optimal quality images. Radiographs with insufficient diagnostic value are rejected, and retakes are required. However, determining the suitability of retaking radiographs is a qualitative evaluation.
UNASSIGNED: To evaluate skull radiograph accuracy automatically using an unsupervised learning-based autoencoder (AE) and a variational autoencoder (VAE). In this study, we eliminated visual qualitative evaluation and used unsupervised learning to identify skull radiography retakes from the quantitative evaluation.
UNASSIGNED: Five skull phantoms were imaged on radiographs, and 1,680 images were acquired. These images correspond to two categories: normal images captured at appropriate positions and images captured at inappropriate positions. This study verified the discriminatory ability of skull radiographs using anomaly detection methods.
UNASSIGNED: The areas under the curves for AE and VAE were 0.7060 and 0.6707, respectively, in receiver operating characteristic analysis. Our proposed method showed a higher discrimination ability than those of previous studies which had an accuracy of 52%.
UNASSIGNED: Our findings suggest that the proposed method has high classification accuracy in determining the suitability of retaking skull radiographs. Automation of optimal image consideration, whether or not to retake radiographs, contributes to improving operational efficiency in busy X-ray imaging operations.

Bone marrow edema-like lesions (BMEL) in the knee have been linked to the symptoms and progression of osteoarthritis (OA), a highly prevalent disease with profound public health implications. Manual and semi-automatic segmentations of BMELs in magnetic resonance images (MRI) have been used to quantify the significance of BMELs. However, their utilization is hampered by the labor-intensive and time-consuming nature of the process as well as by annotator bias, especially since BMELs exhibit various sizes and irregular shapes with diffuse signal that lead to poor intra- and inter-rater reliability. In this study, we propose a novel unsupervised method for fully automated segmentation of BMELs that leverages conditional diffusion models, multiple MRI sequences that have different contrast of BMELs, and anomaly detection that do not rely on costly and error-prone annotations. We also analyze BMEL segmentation annotations from multiple experts, reporting intra-/inter-rater variability and setting better benchmarks for BMEL segmentation performance.

Hyperspectral images include information from a wide range of spectral bands deemed valuable for computer vision applications in various domains such as agriculture, surveillance, and reconnaissance. Anomaly detection in hyperspectral images has proven to be a crucial component of change and abnormality identification, enabling improved decision-making across various applications. These abnormalities/anomalies can be detected using background estimation techniques that do not require the prior knowledge of outliers. However, each hyperspectral anomaly detection (HS-AD) algorithm models the background differently. These different assumptions may fail to consider all the background constraints in various scenarios. We have developed a new approach called Greedy Ensemble Anomaly Detection (GE-AD) to address this shortcoming. It includes a greedy search algorithm to systematically determine the suitable base models from HS-AD algorithms and hyperspectral unmixing for the first stage of a stacking ensemble and employs a supervised classifier in the second stage of a stacking ensemble. It helps researchers with limited knowledge of the suitability of the HS-AD algorithms for the application scenarios to select the best methods automatically. Our evaluation shows that the proposed method achieves a higher average F1-macro score with statistical significance compared to the other individual methods used in the ensemble. This is validated on multiple datasets, including the Airport-Beach-Urban (ABU) dataset, the San Diego dataset, the Salinas dataset, the Hydice Urban dataset, and the Arizona dataset. The evaluation using the airport scenes from the ABU dataset shows that GE-AD achieves a 14.97% higher average F1-macro score than our previous method (HUE-AD), at least 17.19% higher than the individual methods used in the ensemble, and at least 28.53% higher than the other state-of-the-art ensemble anomaly detection algorithms. As using the combination of greedy algorithm and stacking ensemble to automatically select suitable base models and associated weights have not been widely explored in hyperspectral anomaly detection, we believe that our work will expand the knowledge in this research area and contribute to the wider application of this approach.

Detecting unusual patterns in graph data is a crucial task in data mining. However, existing methods face challenges in consistently achieving satisfactory performance and often lack interpretability, which hinders our understanding of anomaly detection decisions. In this paper, we propose a novel approach to graph anomaly detection that leverages the power of interpretability to enhance performance. Specifically, our method extracts an attention map derived from gradients of graph neural networks, which serves as a basis for scoring anomalies. Notably, our approach is flexible and can be used in various anomaly detection settings. In addition, we conduct theoretical analysis using synthetic data to validate our method and gain insights into its decision-making process. To demonstrate the effectiveness of our method, we extensively evaluate our approach against state-of-the-art graph anomaly detection techniques on real-world graph classification and wireless network datasets. The results consistently demonstrate the superior performance of our method compared to the baselines.

Arrhythmia is a major cardiac abnormality in fetuses. Therefore, early diagnosis of arrhythmia is clinically crucial. Pulsed-wave Doppler ultrasound is a commonly used diagnostic tool for fetal arrhythmia. Its key step for diagnosis involves identifying adjacent measurable cardiac cycles (MCCs). As cardiac activity is complex and the experience of sonographers is often varied, automation can improve user-independence and diagnostic-validity. However, arrhythmias pose several challenges for automation because of complex waveform variations, which can cause major localization bias and missed or false detection of MCCs. Filtering out non-MCC anomalies is difficult because of large intra-class and small inter-class variations between MCCs and non-MCCs caused by agnostic morphological waveform variations. Moreover, rare arrhythmia cases are insufficient for classification algorithms to adequately learn discriminative features. Using only normal cases for training, we propose a novel hierarchical online contrastive anomaly detection (HOCAD) framework for arrhythmia diagnosis during test time. The contribution of this study is three-fold. First, we develop a coarse-to-fine framework inspired by hierarchical diagnostic logic, which can refine localization and avoid missed detection of MCCs. Second, we propose an online learning-based contrastive anomaly detection with two new anomaly scores, which can adaptively filter out non-MCC anomalies on a single image during testing. With these complementary efforts, we precisely determine MCCs for correct measurements and diagnosis. Third, to the best of our knowledge, this is the first reported study investigating intelligent diagnosis of fetal arrhythmia on a large-scale and multi-center ultrasound dataset. Extensive experiments on 3850 cases, including 266 cases covering three typical types of arrhythmias, demonstrate the effectiveness of the proposed framework.

The detection of seismic activity precursors as part of an alarm system will provide opportunities for minimization of the social and economic impact caused by earthquakes. It has long been envisaged, and a growing body of empirical evidence suggests that the Earth\'s electromagnetic field could contain precursors to seismic events. The ability to capture and monitor electromagnetic field activity has increased in the past years as more sensors and methodologies emerge. Missions such as Swarm have enabled researchers to access near-continuous observations of electromagnetic activity at second intervals, allowing for more detailed studies on weather and earthquakes. In this paper, we present an approach designed to detect anomalies in electromagnetic field data from Swarm satellites. This works towards developing a continuous and effective monitoring system of seismic activities based on SWARM measurements. We develop an enhanced form of a probabilistic model based on the Martingale theories that allow for testing the null hypothesis to indicate abnormal changes in electromagnetic field activity. We evaluate this enhanced approach in two experiments. Firstly, we perform a quantitative comparison on well-understood and popular benchmark datasets alongside the conventional approach. We find that the enhanced version produces more accurate anomaly detection overall. Secondly, we use three case studies of seismic activity (namely, earthquakes in Mexico, Greece, and Croatia) to assess our approach and the results show that our method can detect anomalous phenomena in the electromagnetic data.

Deep learning has shown significant advantages in Automatic Dependent Surveillance-Broadcast (ADS-B) anomaly detection, but it is known for its susceptibility to adversarial examples which make anomaly detection models non-robust. In this study, we propose Time Neighborhood Accumulation Iteration Fast Gradient Sign Method (TNAI-FGSM) adversarial attacks which fully take into account the temporal correlation of an ADS-B time series, stabilize the update directions of adversarial samples, and escape from poor local optimum during the process of iterating. The experimental results show that TNAI-FGSM adversarial attacks can successfully attack ADS-B anomaly detection models and improve the transferability of ADS-B adversarial examples. Moreover, the TNAI-FGSM is superior to two well-known adversarial attacks called the Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM). To the best of our understanding, we demonstrate, for the first time, the vulnerability of deep-learning-based ADS-B time series unsupervised anomaly detection models to adversarial examples, which is a crucial step in safety-critical and cost-critical Air Traffic Management (ATM).

The recent advancements in autonomous driving come with the associated cybersecurity issue of compromising networks of autonomous vehicles (AVs), motivating the use of AI models for detecting anomalies on these networks. In this context, the usage of explainable AI (XAI) for explaining the behavior of these anomaly detection AI models is crucial. This work introduces a comprehensive framework to assess black-box XAI techniques for anomaly detection within AVs, facilitating the examination of both global and local XAI methods to elucidate the decisions made by XAI techniques that explain the behavior of AI models classifying anomalous AV behavior. By considering six evaluation metrics (descriptive accuracy, sparsity, stability, efficiency, robustness, and completeness), the framework evaluates two well-known black-box XAI techniques, SHAP and LIME, involving applying XAI techniques to identify primary features crucial for anomaly classification, followed by extensive experiments assessing SHAP and LIME across the six metrics using two prevalent autonomous driving datasets, VeReMi and Sensor. This study advances the deployment of black-box XAI methods for real-world anomaly detection in autonomous driving systems, contributing valuable insights into the strengths and limitations of current black-box XAI methods within this critical domain.

As an enhanced version of standard CAN, the Controller Area Network with Flexible Data (CAN-FD) rate is vulnerable to attacks due to its lack of information security measures. However, although anomaly detection is an effective method to prevent attacks, the accuracy of detection needs further improvement. In this paper, we propose a novel intrusion detection model for the CAN-FD bus, comprising two sub-models: Anomaly Data Detection Model (ADDM) for spotting anomalies and Anomaly Classification Detection Model (ACDM) for identifying and classifying anomaly types. ADDM employs Long Short-Term Memory (LSTM) layers to capture the long-range dependencies and temporal patterns within CAN-FD frame data, thus identifying frames that deviate from established norms. ACDM is enhanced with the attention mechanism that weights LSTM outputs, further improving the identification of sequence-based relationships and facilitating multi-attack classification. The method is evaluated on two datasets: a real-vehicle dataset including frames designed by us based on known attack patterns, and the CAN-FD Intrusion Dataset, developed by the Hacking and Countermeasure Research Lab. Our method offers broader applicability and more refined classification in anomaly detection. Compared with existing advanced LSTM-based and CNN-LSTM-based methods, our method exhibits superior performance in detection, achieving an improvement in accuracy of 1.44% and 1.01%, respectively.

Background: To design a novel anomaly detection and localization approach using artificial intelligence methods using optical coherence tomography (OCT) scans for retinal diseases. Methods: High-resolution OCT scans from the publicly available Kaggle dataset and a local dataset were used by four state-of-the-art self-supervised frameworks. The backbone model of all the frameworks was a pre-trained convolutional neural network (CNN), which enabled the extraction of meaningful features from OCT images. Anomalous images included choroidal neovascularization (CNV), diabetic macular edema (DME), and the presence of drusen. Anomaly detectors were evaluated by commonly accepted performance metrics, including area under the receiver operating characteristic curve, F1 score, and accuracy. Results: A total of 25,315 high-resolution retinal OCT slabs were used for training. Test and validation sets consisted of 968 and 4000 slabs, respectively. The best performing across all anomaly detectors had an area under the receiver operating characteristic of 0.99. All frameworks were shown to achieve high performance and generalize well for the different retinal diseases. Heat maps were generated to visualize the quality of the frameworks\' ability to localize anomalous areas of the image. Conclusions: This study shows that with the use of pre-trained feature extractors, the frameworks tested can generalize to the domain of retinal OCT scans and achieve high image-level ROC-AUC scores. The localization results of these frameworks are promising and successfully capture areas that indicate the presence of retinal pathology. Moreover, such frameworks have the potential to uncover new biomarkers that are difficult for the human eye to detect. Frameworks for anomaly detection and localization can potentially be integrated into clinical decision support and automatic screening systems that will aid ophthalmologists in patient diagnosis, follow-up, and treatment design. This work establishes a solid basis for further development of automated anomaly detection frameworks for clinical use.