Search

This study presents an analysis of sensorimotor rhythms using an advanced, optically-pumped magnetoencephalography (OPM-MEG) system - a novel and rapidly developing technology. We conducted real-movement and motor imagery experiments with nine participants across two distinct magnetically-shielded environments: one featuring an analog active suppression system and the other a digital implementation. Our findings demonstrate that, under optimal recording conditions, OPM sensors provide highly informative signals, suitable for use in practical motor imagery brain-computer interface (BCI) applications. We further examine the feasibility of a portable, low-sensor-count OPM-based BCI under varied experimental setups, highlighting its potential for real-time control of external devices via user intentions., Comment: 16 pages, 14 figures, 2 tables

Interpretation of chest computed tomography (CT) is time-consuming. Previous studies have measured the time-saving effect of using a deep-learning-based aid (DLA) for CT interpretation. We evaluated the joint impact of a multi-pathology DLA on the time and accuracy of radiologists' reading. 40 radiologists were randomly split into three experimental arms: control (10), who interpret studies without assistance; informed group (10), who were briefed about DLA pathologies, but performed readings without it; and the experimental group (20), who interpreted half studies with DLA, and half without. Every arm used the same 200 CT studies retrospectively collected from BIMCV-COVID19 dataset; each radiologist provided readings for 20 CT studies. We compared interpretation time, and accuracy of participants diagnostic report with respect to 12 pathological findings. Mean reading time per study was 15.6 minutes [SD 8.5] in the control arm, 13.2 minutes [SD 8.7] in the informed arm, 14.4 [SD 10.3] in the experimental arm without DLA, and 11.4 minutes [SD 7.8] in the experimental arm with DLA. Mean sensitivity and specificity were 41.5 [SD 30.4], 86.8 [SD 28.3] in the control arm; 53.5 [SD 22.7], 92.3 [SD 9.4] in the informed non-assisted arm; 63.2 [SD 16.4], 92.3 [SD 8.2] in the experimental arm without DLA; and 91.6 [SD 7.2], 89.9 [SD 6.0] in the experimental arm with DLA. DLA speed up interpretation time per study by 2.9 minutes (CI95 [1.7, 4.3], p<0.0005), increased sensitivity by 28.4 (CI95 [23.4, 33.4], p<0.0005), and decreased specificity by 2.4 (CI95 [0.6, 4.3], p=0.13). Of 20 radiologists in the experimental arm, 16 have improved reading time and sensitivity, two improved their time with a marginal drop in sensitivity, and two participants improved sensitivity with increased time. Overall, DLA introduction decreased reading time by 20.6%., Comment: 17 pages, 6 figures, 8 tables

Protein design requires a deep understanding of the inherent complexities of the protein universe. While many efforts lean towards conditional generation or focus on specific families of proteins, the foundational task of unconditional generation remains underexplored and undervalued. Here, we explore this pivotal domain, introducing DiMA, a model that leverages continuous diffusion on embeddings derived from the protein language model, ESM-2, to generate amino acid sequences. DiMA surpasses leading solutions, including autoregressive transformer-based and discrete diffusion models, and we quantitatively illustrate the impact of the design choices that lead to its superior performance. We extensively evaluate the quality, diversity, distribution similarity, and biological relevance of the generated sequences using multiple metrics across various modalities. Our approach consistently produces novel, diverse protein sequences that accurately reflect the inherent structural and functional diversity of the protein space. This work advances the field of protein design and sets the stage for conditional models by providing a robust framework for scalable and high-quality protein sequence generation.

On 24 February 2022, Russia invaded Ukraine, starting what is now known as the Russo-Ukrainian War, initiating an online discourse on social media. Twitter as one of the most popular SNs, with an open and democratic character, enables a transparent discussion among its large user base. Unfortunately, this often leads to Twitter's policy violations, propaganda, abusive actions, civil integrity violation, and consequently to user accounts' suspension and deletion. This study focuses on the Twitter suspension mechanism and the analysis of shared content and features of the user accounts that may lead to this. Toward this goal, we have obtained a dataset containing 107.7M tweets, originating from 9.8 million users, using Twitter API. We extract the categories of shared content of the suspended accounts and explain their characteristics, through the extraction of text embeddings in junction with cosine similarity clustering. Our results reveal scam campaigns taking advantage of trending topics regarding the Russia-Ukrainian conflict for Bitcoin and Ethereum fraud, spam, and advertisement campaigns. Additionally, we apply a machine learning methodology including a SHapley Additive explainability model to understand and explain how user accounts get suspended.

Twitter, as one of the most popular social networks, provides a platform for communication and online discourse. Unfortunately, it has also become a target for bots and fake accounts, resulting in the spread of false information and manipulation. This paper introduces a semi-automatic machine learning pipeline (SAMLP) designed to address the challenges correlated with machine learning model development. Through this pipeline, we develop a comprehensive bot detection model named BotArtist, based on user profile features. SAMLP leverages nine distinct publicly available datasets to train the BotArtist model. To assess BotArtist's performance against current state-of-the-art solutions, we select 35 existing Twitter bot detection methods, each utilizing a diverse range of features. Our comparative evaluation of BotArtist and these existing methods, conducted across nine public datasets under standardized conditions, reveals that the proposed model outperforms existing solutions by almost 10%, in terms of F1-score, achieving an average score of 83.19 and 68.5 over specific and general approaches respectively. As a result of this research, we provide a dataset of the extracted features combined with BotArtist predictions over the 10.929.533 Twitter user profiles, collected via Twitter API during the 2022 Russo-Ukrainian War, over a 16-month period. This dataset was created in collaboration with [Shevtsov et al., 2022a] where the original authors share anonymized tweets on the discussion of the Russo-Ukrainian war with a total amount of 127.275.386 tweets. The combination of the existing text dataset and the provided labeled bot and human profiles will allow for the future development of a more advanced bot detection large language model in the post-Twitter API era.

We present SuperConga, an open-source framework for simulating equilibrium properties of unconventional and ballistic singlet superconductors, confined to two-dimensional (2D) mesoscopic grains in a perpendicular external magnetic field, at arbitrary low temperature. It aims at being both fast and easy to use, enabling research without access to a computer cluster, and visualization in real-time with OpenGL. The core is written in C++ and CUDA, exploiting the embarrassingly parallel nature of the quasiclassical theory of superconductivity by utilizing the parallel computational power of modern GPUs. The framework self-consistently computes both the superconducting order-parameter and the induced vector potential, and finds the current density, free energy, induced flux density, local density of states, as well as the magnetic moment. A user-friendly Python frontend is provided, enabling simulation parameters to be defined via intuitive configuration files, or via the command-line interface, without requiring a deep understanding of implementation details. For example, complicated geometries can be created with relative ease. The framework ships with simple tools for analyzing and visualizing the results, including an interactive plotter for spectroscopy. An overview of the theory is presented, as well as examples showcasing the framework's capabilities and ease of use. The framework is free to download from https://gitlab.com/superconga/superconga, which also links to the extensive user manual, containing even more examples, tutorials and guides., Comment: Accepted version. Review-style article, 31 pages and link to software at https://gitlab.com/superconga/superconga

On 24 February 2022, Russia invaded Ukraine, also known now as Russo-Ukrainian War. We have initiated an ongoing dataset acquisition from Twitter API. Until the day this paper was written the dataset has reached the amount of 57.3 million tweets, originating from 7.7 million users. We apply an initial volume and sentiment analysis, while the dataset can be used to further exploratory investigation towards topic analysis, hate speech, propaganda recognition, or even show potential malicious entities like botnets.

Twitter is one of the most popular social networks attracting millions of users, while a considerable proportion of online discourse is captured. It provides a simple usage framework with short messages and an efficient application programming interface (API) enabling the research community to study and analyze several aspects of this social network. However, the Twitter usage simplicity can lead to malicious handling by various bots. The malicious handling phenomenon expands in online discourse, especially during the electoral periods, where except the legitimate bots used for dissemination and communication purposes, the goal is to manipulate the public opinion and the electorate towards a certain direction, specific ideology, or political party. This paper focuses on the design of a novel system for identifying Twitter bots based on labeled Twitter data. To this end, a supervised machine learning (ML) framework is adopted using an Extreme Gradient Boosting (XGBoost) algorithm, where the hyper-parameters are tuned via cross-validation. Our study also deploys Shapley Additive Explanations (SHAP) for explaining the ML model predictions by calculating feature importance, using the game theoretic-based Shapley values. Experimental evaluation on distinct Twitter datasets demonstrate the superiority of our approach, in terms of bot detection accuracy, when compared against a recent state-of-the-art Twitter bot detection method.

A very large number of people use Online Social Networks daily. Such platforms thus become attractive targets for agents that seek to gain access to the attention of large audiences, and influence perceptions or opinions. Botnets, collections of automated accounts controlled by a single agent, are a common mechanism for exerting maximum influence. Botnets may be used to better infiltrate the social graph over time and to create an illusion of community behavior, amplifying their message and increasing persuasion. This paper investigates Twitter botnets, their behavior, their interaction with user communities and their evolution over time. We analyzed a dense crawl of a subset of Twitter traffic, amounting to nearly all interactions by Greek-speaking Twitter users for a period of 36 months. We detected over a million events where seemingly unrelated accounts tweeted nearly identical content at nearly the same time. We filtered these concurrent content injection events and detected a set of 1,850 accounts that repeatedly exhibit this pattern of behavior, suggesting that they are fully or in part controlled and orchestrated by the same software. We found botnets that appear for brief intervals and disappear, as well as botnets that evolve and grow, spanning the duration of our dataset. We analyze statistical differences between bot accounts and human users, as well as botnet interaction with user communities and Twitter trending topics.

We systematically evaluate a Deep Learning (DL) method in a 3D medical image segmentation task. Our segmentation method is integrated into the radiosurgery treatment process and directly impacts the clinical workflow. With our method, we address the relative drawbacks of manual segmentation: high inter-rater contouring variability and high time consumption of the contouring process. The main extension over the existing evaluations is the careful and detailed analysis that could be further generalized on other medical image segmentation tasks. Firstly, we analyze the changes in the inter-rater detection agreement. We show that the segmentation model reduces the ratio of detection disagreements from 0.162 to 0.085 (p < 0.05). Secondly, we show that the model improves the inter-rater contouring agreement from 0.845 to 0.871 surface Dice Score (p < 0.05). Thirdly, we show that the model accelerates the delineation process in between 1.6 and 2.0 times (p < 0.05). Finally, we design the setup of the clinical experiment to either exclude or estimate the evaluation biases, thus preserve the significance of the results. Besides the clinical evaluation, we also summarize the intuitions and practical ideas for building an efficient DL-based model for 3D medical image segmentation.

The presidential elections in the United States on 3 November 2020 have caused extensive discussions on social media. A part of the content on US elections is organic, coming from users discussing their opinions of the candidates, political positions, or relevant content presented on television. Another significant part of the content generated originates from organized campaigns, both official and by astroturfing. In this study, we obtain approximately 17.5M tweets containing 3M users, based on prevalent hashtags related to US election 2020, as well as the related YouTube links, contained in the Twitter dataset, likes, dislikes and comments of the videos and conduct volume, sentiment and graph analysis on the communities formed. Particularly, we study the daily traffic per prevalent hashtags, plot the retweet graph from July to September 2020, show how its main connected component becomes denser in the period closer to the elections and highlight the two main entities ('Biden' and 'Trump'). Additionally, we gather the related YouTube links contained in the previous dataset and perform sentiment analysis. The results on sentiment analysis on the Twitter corpus and the YouTube metadata gathered, show the positive and negative sentiment for the two entities throughout this period. The results of sentiment analysis indicate that 45.7% express positive sentiment towards Trump in Twitter and 33.8% positive sentiment towards Biden, while 14.55% of users express positive sentiment in YouTube metadata gathered towards Trump and 8.7% positive sentiment towards Biden. Our analysis fill the gap between the connection of offline events and their consequences in social media by monitoring important events in real world and measuring public volume and sentiment before and after the event in social media.

Target imbalance affects the performance of recent deep learning methods in many medical image segmentation tasks. It is a twofold problem: class imbalance - positive class (lesion) size compared to negative class (non-lesion) size; lesion size imbalance - large lesions overshadows small ones (in the case of multiple lesions per image). While the former was addressed in multiple works, the latter lacks investigation. We propose a loss reweighting approach to increase the ability of the network to detect small lesions. During the learning process, we assign a weight to every image voxel. The assigned weights are inversely proportional to the lesion volume, thus smaller lesions get larger weights. We report the benefit from our method for well-known loss functions, including Dice Loss, Focal Loss, and Asymmetric Similarity Loss. Additionally, we compare our results with other reweighting techniques: Weighted Cross-Entropy and Generalized Dice Loss. Our experiments show that inverse weighting considerably increases the detection quality, while preserves the delineation quality on a state-of-the-art level. We publish a complete experimental pipeline for two publicly available datasets of CT images: LiTS and LUNA16 (https://github.com/neuro-ml/inverse_weighting). We also show results on a private database of MR images for the task of multiple brain metastases delineation., Comment: Accepted to MICCAI 2020

The current COVID-19 pandemic overloads healthcare systems, including radiology departments. Though several deep learning approaches were developed to assist in CT analysis, nobody considered study triage directly as a computer science problem. We describe two basic setups: Identification of COVID-19 to prioritize studies of potentially infected patients to isolate them as early as possible; Severity quantification to highlight studies of severe patients and direct them to a hospital or provide emergency medical care. We formalize these tasks as binary classification and estimation of affected lung percentage. Though similar problems were well-studied separately, we show that existing methods provide reasonable quality only for one of these setups. We employ a multitask approach to consolidate both triage approaches and propose a convolutional neural network to combine all available labels within a single model. In contrast with the most popular multitask approaches, we add classification layers to the most spatially detailed upper part of U-Net instead of the bottom, less detailed latent representation. We train our model on approximately 2000 publicly available CT studies and test it with a carefully designed set consisting of 32 COVID-19 studies, 30 cases with bacterial pneumonia, 31 healthy patients, and 30 patients with other lung pathologies to emulate a typical patient flow in an out-patient hospital. The proposed multitask model outperforms the latent-based one and achieves ROC AUC scores ranging from 0.87+-01 (bacterial pneumonia) to 0.97+-01 (healthy controls) for Identification of COVID-19 and 0.97+-01 Spearman Correlation for Severity quantification. We release all the code and create a public leaderboard, where other community members can test their models on our test dataset.

Stereotactic radiosurgery is a minimally-invasive treatment option for a large number of patients with intracranial tumors. As part of the therapy treatment, accurate delineation of brain tumors is of great importance. However, slice-by-slice manual segmentation on T1c MRI could be time-consuming (especially for multiple metastases) and subjective. In our work, we compared several deep convolutional networks architectures and training procedures and evaluated the best model in a radiation therapy department for three types of brain tumors: meningiomas, schwannomas and multiple brain metastases. The developed semiautomatic segmentation system accelerates the contouring process by 2.2 times on average and increases inter-rater agreement from 92.0% to 96.5%.