OBJECTIVE: This paper presents the results from a competition challenging participants to develop entity linking models using a subset of annotated MIMIC-IV-Note data and the SNOMED CT Terminology. MATERIALS AND METHODS: As a basis for this work, a large set of 74 808 annotations was curated across 272 discharge notes spanning 6624 unique clinical concepts. Submissions were evaluated using the mean Intersection-over-Union metric, evaluated at the character level with the 3 best performing solutions awarded a cash prize. RESULTS: The winning solutions employed contrasting approaches: a dictionary-based method, an encoder-based method, and a decoder-based method. DISCUSSION: Our analysis reveals that concept frequency in training data significantly impacts model performance, with rare concepts proving particularly challenging. High concept entropy and annotation ambiguity were also associated with decreased performance. CONCLUSION: Findings from this work suggest that future projects should focus on improving entity linking for rare concepts and developing methods to better leverage contextual information when training examples are scarce.

Recent progress in generative models has made it easier for a wide audience to edit and create image content, raising concerns about the proliferation of deepfakes, especially in healthcare. Despite the availability of numerous techniques for detecting manipulated images captured by conventional cameras, their applicability to medical images is limited. This limitation stems from the distinctive forensic characteristics of medical images, a result of their imaging process. In this work, we propose a novel anomaly detector for medical imagery based on diffusion models. Normally, diffusion models are used to generate images. However, we show how a similar process can be used to detect synthetic content by making a model reverse the diffusion on a suspected image. We evaluate our method on the task of detecting fake tumors injected and removed from CT and MRI scans. Our method significantly outperforms other state-of-the-art unsupervised detectors with an increased AUC of 0.9 from 0.79 for injection and of 0.96 from 0.91 for removal on average. We also explore our hypothesis using AI explainability tools and publish both our code and new medical deepfake datasets to encourage further research into this domain.

Out-of-distribution (OOD) detection has attracted a large amount of attention from the machine learning research community in recent years due to its importance in deployed systems. Most of the previous studies focused on the detection of OOD samples in the multiclass classification task. However, OOD detection in the multi-label classification task, a more common real-world use case, remains an underexplored domain. In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task. Object detection models have an inherent ability to distinguish between objects of interest (in-distribution data) and irrelevant objects (OOD data) in images that contain multiple objects belonging to different class categories. These abilities allow us to convert a regular object detection model into an image classifier with inherent OOD detection capabilities with just minor changes. We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets.

Adversarial transferability in blackbox scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target model. Until now, the prevalent method to ascertain success has been trial and error—testing crafted samples directly on the victim model. This approach, however, risks detection with every attempt, forcing attackers to either perfect their first try or face exposure. Our article introduces a ranking strategy that refines the transfer attack process, enabling the attacker to estimate the likelihood of success without repeated trials on the victim’s system. By leveraging a set of diverse surrogate models, our method can predict transferability of adversarial examples. This strategy can be used to either select the best sample to use in an attack or the best perturbation to apply to a specific sample. Using our strategy, we were able to raise the transferability of adversarial examples from a mere 20%—akin to random selection—up to near upper-bound levels, with some scenarios even witnessing a 100% success rate. This substantial improvement not only sheds light on the shared susceptibilities across diverse architectures but also demonstrates that attackers can forego the detectable trial-and-error tactics raising increasing the threat of surrogate-based attacks.

Gestational Diabetes Mellitus (GDM), a serious complication during pregnancy which is defined by abnormal glucose regulation, is commonly treated by diabetic diet and lifestyle changes. While recent findings place the microbiome as a natural mediator between diet interventions and diverse disease states, its role in GDM is still unknown. Here, based on observation data from healthy pregnant control group and GDM patients, we developed a new network approach using patterns of co-abundance of microorganism to construct microbial networks that represent human-specific information about gut microbiota in different groups. By calculating network similarity in different groups, we analyze the gut microbiome from 27 GDM subjects collected before and after two weeks of diet therapy compared with 30 control subjects to identify the health condition of microbial community balance in GDM subjects. Although the microbial communities remain similar after the diet phase, we find that the structure of their inter-species co-abundance network is significantly altered, which is reflected in that the ecological balance of GDM patients was not "healthier" after the diet intervention. In addition, we devised a method for individualized network analysis of the microbiome, thereby a pattern is found that GDM individuals whose microbial networks are with large deviations from the GDM group are usually accompanied by their abnormal glucose regulation. This approach may help the development of individualized diagnosis strategies and microbiome-based therapies in the future.

Deep learning-based facial recognition systems have experienced increased media attention due to exhibiting unfair behavior. Large enterprises, such as IBM, shut down their facial recognition and age prediction systems as a consequence. Age prediction is an especially difficult application with the issue of fairness remaining an open research problem (e.g., predicting age for different ethnicity equally accurate). One of the main causes of unfair behavior in age prediction methods lies in the distribution and diversity of the training data. In this work, we present two novel approaches for dataset curation and data augmentation in order to increase fairness through balanced feature curation and increase diversity through distribution aware augmentation. To achieve this, we introduce out-of-distribution detection to the facial recognition domain which is used to select the data most relevant to the deep neural network’s (DNN) task when balancing the data among age, ethnicity, and gender. Our approach shows promising results. Our best-trained DNN model outperformed all academic and industrial baselines in terms of fairness by up to 4.92 times and also enhanced the DNN’s ability to generalize outperforming Amazon AWS and Microsoft Azure public cloud systems by 31.88% and 10.95%, respectively.

Many organization consider insider threat for data theft to be one of the most severe threats. An insider may also leak sensitive information without malicious intent (as a result of social engineering) Data leakage prevention (DLP) systems attempt to prevent intentional or accidental disclosure of sensitive information by monitoring the content or the context in which the information is transferred, for example, in a file system, an email server, instant messengers. We present a context-sensitive DLP system, called Efficient DLP-Visor. We implemented DLP-visor as a thin hypervisor capable of intercepting system calls in Windows operating systems equipped with Kernel Patch Protection. By intercepting system calls that govern the file system, inter-process communications, networking, system register and system clipboard, DLP-Visor guarantees that sensitive information can never leave a predefined set of directories. The performance overhead of Efficient DLP-Visor (7.2%) allows its deployment in real-world applications. Efficient DLP-visor logs were improved for better detection and logging of a DLP event. On idle time Efficient DLP-visor deletes most of the data log while maintaining the important data of leaks and attack.

Deep neural networks (DNNs) perform well at classifying inputs associated with the classes they have been trained on, which are known as in-distribution inputs. However, out-of-distribution (OOD) inputs pose a great challenge to DNNs and consequently represent a major risk when DNNs are implemented in safety-critical systems. Extensive research has been performed in the domain of OOD detection. However, current state-of-the-art methods for OOD detection suffer from at least one of the following limitations: (1) increased inference time - this limits existing methods' applicability to many real-world applications, and (2) the need for OOD training data - such data can be difficult to acquire and may not be representative enough, thus limiting the ability of the OOD detector to generalize. In this paper, we propose FOOD - Fast Out-Of-Distribution detector - an extended DNN classifier capable of efficiently detecting OOD samples with minimal inference time overhead. Our architecture features a DNN with a final Gaussian layer combined with the log likelihood ratio statistical test and an additional output neuron for OOD detection. Instead of using real OOD data, we use a novel method to craft artificial OOD samples from in-distribution data, which are used to train our OOD detector neuron. We evaluate FOOD's detection performance on the SVHN, CIFAR-10, and CIFAR-100 datasets. Our results demonstrate that in addition to achieving state-of-the-art performance, FOOD is fast and applicable to real-world applications.

The flourishing of machine learning use for cognitive tasks has driven an increased demand for large annotated training datasets. In the medical imaging domain, such datasets are scarce, and the process of labeling them is costly, error prone and requires high expertise. Unsupervised learning is therefore an attractive approach for analyzing unlabeled medical images. In this paper we describe an unsupervised analysis method, consisting of feature learning by Stacked Auto-Encoders, K-means clustering for building a data model, and encoding of new images using the model. We utilize this method for image-level and patch-level analysis of breast mammograms. At the image-level, we demonstrate that our cluster-based image encoding is able to identify outlier images such as images with implants or non-standard acquisition views. At the patch-level, we show that image signatures using patch clustering can be used for unsupervised semantic segmentation of breast tissues, as well as for separating mammograms with high and low breast density. We evaluate our suggested methods on large datasets and discuss potential applications for data curation, machine-guided annotation and automatic interpretation of medical images.

Specific supraventricular tachycardia (SVT) classification using surface ECG is considered a challenging task, since the atrial electrical activity (AEA) waves, which are a crucial element for obtaining diagnosis, are frequently hidden. In this paper, we present a fully automated SVT classification method that embeds our recently developed hidden AEA detector in a clinically based tree scheme. The process begins with initial noise removal and QRS detection. Then, ventricular features are extracted. According to these features, an initial AEA-wave search window is defined and a single AEA-wave is detected. Using a synthetic Gaussian signal and a linear combination of 12-lead ECG signals, all AEA-waves are detected. In accord with the atrial and ventricular information found, classification to atrial fibrillation, atrial flutter, atrioventricular nodal reentry tachycardia, atrioventricular reentry tachycardia, or sinus rhythm is performed in the framework of a clinically oriented decision tree. A study was performed to evaluate the classification from 68 patients (26 were used for the classifier's design, 42 were used for its validation). Average sensitivity of 83.21% [95% confidence interval (CI): 79.33-86.49%], average specificity of 95.80% (95% CI: 94.73-96.67%), and average accuracy of 93.29% (95% CI: 92.13-94.28%) were achieved compared to the definite diagnosis. In conclusion, the presented method may serve as a valuable decision support tool, allowing accurate detection of SVTs using noninvasive means.

In the near future, the majority of personal computers are expected to have several processing units. This is referred to as core multiprocessing (CMP). Furthermore, each of the computation units will be capable of running multiple hardware threads. To benefit from the additional processing power, application developers should multithread their software. This paper studies the scalability (expected speedup factor) of multimedia applications and provides guidelines for proper utilization of these new multi-core platforms. In particular, we discuss the decomposition method, load balancing, synchronization primitives, interaction with the operating system and hardware issues such as cache hierarchy and memory bandwidth. Our results are based on analysis of several state-of-the-art applications, including H.264 video encoding, panoramic image stitching and dense optical-flow estimation. We demonstrate how to multithread them properly, and report scalability results on several next-generation multi-core platforms