Reinforcement Learning Your Way: Agent Characterization through Policy Regularization

The increased complexity of state-of-the-art reinforcement learning (RL) algorithms has resulted in an opacity that inhibits explainability and understanding. This has led to the development of several post hoc explainability methods that aim to extract information from learned policies, thus aiding explainability. These methods rely on empirical observations of the policy, and thus aim to generalize a characterization of agents’ behaviour. In this study, we have instead developed a method to imbue agents’ policies with a characteristic behaviour through regularization of their objective functions. Our method guides the agents’ behaviour during learning, which results in an intrinsic characterization; it connects the learning process with model explanation. We provide a formal argument and empirical evidence for the viability of our method. In future work, we intend to employ it to develop agents that optimize individual financial customers’ investment portfolios based on their spending personalities.

Using Quantitative Imaging for Personalized Medicine in Pancreatic Cancer: A Review of Radiomics and Deep Learning Applications

Simple Summary

With a five-year survival rate of only 3% for the majority of patients, pancreatic cancer is a global healthcare challenge. Radiomics and deep learning, two novel quantitative imaging methods that treat medical images as minable data instead of just pictures, have shown promise in advancing personalized management of pancreatic cancer through diagnosing precursor diseases, early detection, accurate diagnosis, and treatment personalization. Radiomics and deep learning methods aim to collect hidden information in medical images that is missed by conventional radiology practices through expanding the data search and comparing information across different patients. Both methods have been studied and applied in pancreatic cancer. In this review, we focus on the current progress of these two methods in pancreatic cancer and provide a comprehensive narrative review on the topic. With better regulation, enhanced workflow, and larger prospective patient datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through personalized precision medicine.

Abstract

As the most lethal major cancer, pancreatic cancer is a global healthcare challenge. Personalized medicine utilizing cutting-edge multi-omics data holds potential for major breakthroughs in tackling this critical problem. Radiomics and deep learning, two trendy quantitative imaging methods that take advantage of data science and modern medical imaging, have shown increasing promise in advancing the precision management of pancreatic cancer via diagnosing of precursor diseases, early detection, accurate diagnosis, and treatment personalization and optimization. Radiomics employs manually-crafted features, while deep learning applies computer-generated automatic features. These two methods aim to mine hidden information in medical images that is missed by conventional radiology and gain insights by systematically comparing the quantitative image information across different patients in order to characterize unique imaging phenotypes. Both methods have been studied and applied in various pancreatic cancer clinical applications. In this review, we begin with an introduction to the clinical problems and the technology. After providing technical overviews of the two methods, this review focuses on the current progress of clinical applications in precancerous lesion diagnosis, pancreatic cancer detection and diagnosis, prognosis prediction, treatment stratification, and radiogenomics. The limitations of current studies and methods are discussed, along with future directions. With better standardization and optimization of the workflow from image acquisition to analysis and with larger and especially prospective high-quality datasets, radiomics and deep learning methods could show real hope in the battle against pancreatic cancer through big data-based high-precision personalization.

[Usage of Artificial Intelligence in the Combat against the COVID-19 Pandemic]

The COVID-19 pandemic is a global health emergency of historic dimension. In this situation, researchers worldwide wanted to help manage the pandemic by using artificial intelligence (AI). This narrative review aims to describe the usage of AI in the combat against COVID-19. The addressed aspects encompass AI algorithms for analysis of thoracic X-rays or CTs, prediction models for severity and outcome of the disease, AI applications in development of new drugs and vaccines as well as forecasting models for spread of the virus. The review shows, which approaches were pursued, and which were successful.

Responsible Governance for a Food and Nutrition E-Infrastructure: Case Study of the Determinants and Intake Data Platform

The focus of the current paper is on a design of responsible governance of food consumer science e-infrastructure using the case study Determinants and Intake Data Platform (DI Data Platform). One of the key challenges for implementation of the DI Data Platform is how to develop responsible governance that observes the ethical and legal frameworks of big data research and innovation, whilst simultaneously capitalizing on huge opportunities offered by open science and the use of big data in food consumer science research. We address this challenge with a specific focus on four key governance considerations: data type and technology; data ownership and intellectual property; data privacy and security; and institutional arrangements for ethical governance. The paper concludes with a set of responsible research governance principles that can inform the implementation of DI Data Platform, and in particular: consider both individual and group privacy; monitor the power and control (e.g., between the scientist and the research participant) in the process of research; question the veracity of new knowledge based on big data analytics; understand the diverse interpretations of scientists' responsibility across different jurisdictions.

Improving Access to Behavioral Strategies to Improve Mental Well-being With an Entertaining Breakfast Show App: Feasibility Evaluation Study

Background

Although mental ill-health is more prevalent among people from lower socioeconomic groups, digital mental well-being innovations are often developed for people from higher socioeconomic groups, who already have resources to maintain good mental and physical health. To decrease health inequalities and ensure that available solutions are appealing and accessible to people with fewer resources, new approaches should be explored. We developed the app Wakey!, which focused on creating engaging mental health content that is accessible, particularly among lower socioeconomic groups in the United Kingdom.

Objective

The aim of this study is to assess engagement with the app, investigate initial effectiveness data for 6 well-being outcomes, and explore participants’ subjective experiences of using Wakey!

Methods

The app Wakey! was publicly launched on January 20, 2020, and was free to download from Apple Store and Google Play. The app provided its users with entertaining and educational content related to mental well-being. Concurrently, a single-arm mixed methods feasibility trial was carried out from January to April 2020 among people who had downloaded the app and created an account. The primary outcome was engagement, which was collected passively from data logs. Secondary outcome measures were 6 well-being outcomes collected from self-report questionnaires. Individual interviews with 19 app users were carried out in April 2020.

Results

In total, 5413 people fit the inclusion criteria and were included in the final sample—65.62% (3520/5364) women, 61.07% (3286/5381) aged between 25 and 44 years, 61.61% (2902/4710) in employment, 8.92% (420/4710) belonging to the lower socioeconomic group, and 8.09% (438/5413) were engaged users. There was no evidence of a difference in engagement regarding sociodemographic and socioeconomic characteristics. There was evidence that users with a higher average daily sleep score, who joined the study more recently, who had higher baseline self-report of sleep quality, and who found episodes more entertaining were more likely to be engaged users. Among 230 users who provided follow-up data, there was evidence of improvements on four of the six well-being outcomes: life satisfaction (P<.001), feeling that life is worthwhile (P=.01), ease of getting up in the morning (P<.001), and self-efficacy (P=.04). The app and its content were well received by those who were interviewed, and several people perceived a positive change in their mental well-being.

Conclusions

This study shows that the app Wakey! could potentially be engaging across different socioeconomic groups, and there is an indication that it could positively impact the mental well-being of those engaged with the app. However, this study was a pragmatic trial with a limited sample, and the selection bias was present in the qualitative and quantitative study. Further work is needed to make any generalizable conclusions.

Trial Registration

ClinicalTrials.gov NCT04287296; https://clinicaltrials.gov/ct2/show/NCT04287296

Graph Neural Networks for Charged Particle Tracking on FPGAs

The determination of charged particle trajectories in collisions at the CERN Large Hadron Collider (LHC) is an important but challenging problem, especially in the high interaction density conditions expected during the future high-luminosity phase of the LHC (HL-LHC). Graph neural networks (GNNs) are a type of geometric deep learning algorithm that has successfully been applied to this task by embedding tracker data as a graph—nodes represent hits, while edges represent possible track segments—and classifying the edges as true or fake track segments. However, their study in hardware- or software-based trigger applications has been limited due to their large computational cost. In this paper, we introduce an automated translation workflow, integrated into a broader tool called hls4ml, for converting GNNs into firmware for field-programmable gate arrays (FPGAs). We use this translation tool to implement GNNs for charged particle tracking, trained using the TrackML challenge dataset, on FPGAs with designs targeting different graph sizes, task complexites, and latency/throughput requirements. This work could enable the inclusion of charged particle tracking GNNs at the trigger level for HL-LHC experiments.

Automatic kidney segmentation using 2.5D ResUNet and 2.5D DenseUNet for malignant potential analysis in complex renal cyst based on CT images

Bosniak renal cyst classification has been widely used in determining the complexity of a renal cyst. However, it turns out that about half of patients undergoing surgery for Bosniak category III, take surgical risks that reward them with no clinical benefit at all. This is because their pathological results reveal that the cysts are actually benign not malignant. This problem inspires us to use recently popular deep learning techniques and study alternative analytics methods for precise binary classification (benign or malignant tumor) on Computerized Tomography (CT) images. To achieve our goal, two consecutive steps are required-segmenting kidney organs or lesions from CT images then classifying the segmented kidneys. In this paper, we propose a study of kidney segmentation using 2.5D ResUNet and 2.5D DenseUNet for efficiently extracting intra-slice and inter-slice features. Our models are trained and validated on the public data set from Kidney Tumor Segmentation (KiTS19) challenge in two different training environments. As a result, all experimental models achieve high mean kidney Dice scores of at least 95% on the KiTS19 validation set consisting of 60 patients. Apart from the KiTS19 data set, we also conduct separate experiments on abdomen CT images of four Thai patients. Based on the four Thai patients, our experimental models show a drop in performance, where the best mean kidney Dice score is 87.60%.

Improving Compound Activity Classification via Deep Transfer and Representation Learning

Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure-activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks is limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to their inactive compounds. Overall, TAc achieves the best performance with an average ROC-AUC of 0.801; it significantly improves the ROC-AUC of 83% of target tasks with an average task-wise performance improvement of 7.102%, compared to the best baseline dmpna. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks.

Predictive Maintenance for Remanufacturing Based on Hybrid-Driven Remaining Useful Life Prediction

Remanufacturing is an activity of the circular economy model whose purpose is to keep the high value of products and materials. As opposed to the currently employed linear economic model, remanufacturing targets the extension of products and reduces the unnecessary and wasteful use of resources. Remanufacturing, along with health status monitoring, constitutes a key element for lifetime extension and reuse of large industrial equipment. The major challenge is to determine if a machine is worth remanufacturing and when is the optimal time to perform remanufacturing. The present work proposes a new predictive maintenance framework for the remanufacturing process based on a combination of remaining useful life prediction and condition monitoring methods. A hybrid-driven approach was used to combine the advantages of the knowledge model and historical data. The proposed method has been verified on the realistic run-to-failure rolling bearing degradation dataset. The experimental results combined with visualization analysis have proven the effectiveness of the proposed method.

Application of deep learning for predicting the treatment performance of real municipal wastewater based on one-year operation of two anaerobic membrane bioreactors

In this study, data-driven deep learning methods were applied in order to model and predict the treatment of real municipal wastewater using anaerobic membrane bioreactors (AnMBRs). Based on the one-year operating data of two AnMBRs, six parameters related to the experimental conditions (temperature of reactor, temperature of environment, temperature of influent, influent pH, influent COD, and flux) and eight parameters for wastewater treatment evaluation (effluent pH, effluent COD, COD removal efficiency, biogas composition (CH₄, N₂, and CO₂), biogas production rate, and oxidation-reduction potential) were selected to establish the data sets. Three deep learning network structures were proposed to analyze and reproduce the relationship between the input parameters and output evaluation parameters. The statistical analysis showed that deep learning closely agrees with the AnMBR experimental results. The prediction accuracy rate of the proposed densely connected convolutional network (DenseNet) can reach up to 97.44%, and the single calculation time can be reduced to within 1 s, suggesting the high performance of AnMBR treatment prediction with deep learning methods.

The Effectiveness of Centralized Payment Network Advertisements on Digital Branding during the COVID-19 Crisis

Crises are always challenging for banking systems. In the case of COVID-19, centralized payment networks and FinTech companies’ websites have been affected by user behavior globally. As a result, there is ample opportunity for marketing managers and professionals to focus on big data from FinTech websites. This can contribute to a better understanding of the variables impacting their brand name and how to manage risk during crisis periods. This research is divided into three stages. The first stage presents the web analytics and the data retrieved from the FinTech platforms. The second stage illustrates the statistical analysis and the fuzzy cognitive mapping (FCM) performed. In the final stage, an agent-based model is outlined in order to simulate and forecast a company’s brand name visibility and user behavior. The results of this study suggest that, during crises, centralized payment networks (CPNs) and FinTech companies with high organic traffic tend to convert new visitors to actual “customers”.

From Generative Models to Generative Passages: A Computational Approach to (Neuro) Phenomenology

This paper presents a version of neurophenomenology based on generative modelling techniques developed in computational neuroscience and biology. Our approach can be described as computational phenomenology because it applies methods originally developed in computational modelling to provide a formal model of the descriptions of lived experience in the phenomenological tradition of philosophy (e.g., the work of Edmund Husserl, Maurice Merleau-Ponty, etc.). The first section presents a brief review of the overall project to naturalize phenomenology. The second section presents and evaluates philosophical objections to that project and situates our version of computational phenomenology with respect to these projects. The third section reviews the generative modelling framework. The final section presents our approach in detail. We conclude by discussing how our approach differs from previous attempts to use generative modelling to help understand consciousness. In summary, we describe a version of computational phenomenology which uses generative modelling to construct a computational model of the inferential or interpretive processes that best explain this or that kind of lived experience.

Mitochondria as the Target of Hepatotoxicity and Drug-Induced Liver Injury: Molecular Mechanisms and Detection Methods

One of the major mechanisms of drug-induced liver injury includes mitochondrial perturbation and dysfunction. This is not a surprise, given that mitochondria are essential organelles in most cells, which are responsible for energy homeostasis and the regulation of cellular metabolism. Drug-induced mitochondrial dysfunction can be influenced by various factors and conditions, such as genetic predisposition, the presence of metabolic disorders and obesity, viral infections, as well as drugs. Despite the fact that many methods have been developed for studying mitochondrial function, there is still a need for advanced and integrative models and approaches more closely resembling liver physiology, which would take into account predisposing factors. This could reduce the costs of drug development by the early prediction of potential mitochondrial toxicity during pre-clinical tests and, especially, prevent serious complications observed in clinical settings.

A Neural Algorithm for the Detection and Correction of Anomalies: Application to the Landing of an Airplane

The location of the plane is key during the landing operation. A set of sensors provides data to get the best estimation of plane localization. However, data can contain anomalies. To guarantee correct behavior of the sensors, anomalies must be detected. Then, either the faulty sensor is isolated or the detected anomaly is filtered. This article presents a new neural algorithm for the detection and correction of anomalies named NADCA. This algorithm uses a compact deep learning prediction model and has been evaluated using real and simulated anomalies in real landing signals. NADCA detects and corrects both fast-changing and slow-moving anomalies; it is robust regardless of the degree of oscillation of the signals and sensors with abnormal behavior do not need to be isolated. NADCA can detect and correct anomalies in real time regardless of sensor accuracy. Likewise, NADCA can deal with simultaneous anomalies in different sensors and avoid possible problems of coupling between signals. From a technical point of view, NADCA uses a new prediction method and a new approach to obtain a smoothed signal in real time. NADCA has been developed to detect and correct anomalies during the landing of an airplane, hence improving the information presented to the pilot. Nevertheless, NADCA is a general-purpose algorithm that could be useful in other contexts. NADCA evaluation has given an average F-score value of 0.97 for anomaly detection and an average root mean square error (RMSE) value of 2.10 for anomaly correction.

The Role of Artificial Intelligence in Early Cancer Diagnosis

Improving the proportion of patients diagnosed with early-stage cancer is a key priority of the World Health Organisation. In many tumour groups, screening programmes have led to improvements in survival, but patient selection and risk stratification are key challenges. In addition, there are concerns about limited diagnostic workforces, particularly in light of the COVID-19 pandemic, placing a strain on pathology and radiology services. In this review, we discuss how artificial intelligence algorithms could assist clinicians in (1) screening asymptomatic patients at risk of cancer, (2) investigating and triaging symptomatic patients, and (3) more effectively diagnosing cancer recurrence. We provide an overview of the main artificial intelligence approaches, including historical models such as logistic regression, as well as deep learning and neural networks, and highlight their early diagnosis applications. Many data types are suitable for computational analysis, including electronic healthcare records, diagnostic images, pathology slides and peripheral blood, and we provide examples of how these data can be utilised to diagnose cancer. We also discuss the potential clinical implications for artificial intelligence algorithms, including an overview of models currently used in clinical practice. Finally, we discuss the potential limitations and pitfalls, including ethical concerns, resource demands, data security and reporting standards.

Comparison of Text Mining Models for Food and Dietary Constituent Named-Entity Recognition

Biomedical Named-Entity Recognition (BioNER) has become an essential part of text mining due to the continuously increasing digital archives of biological and medical articles. While there are many well-performing BioNER tools for entities such as genes, proteins, diseases or species, there is very little research into food and dietary constituent named-entity recognition. For this reason, in this paper, we study seven BioNER models for food and dietary constituents recognition. Specifically, we study a dictionary-based model, a conditional random fields (CRF) model and a new hybrid model, called FooDCoNER (Food and Dietary Constituents Named-Entity Recognition), which we introduce combining the former two models. In addition, we study deep language models including BERT, BioBERT, RoBERTa and ELECTRA. As a result, we find that FooDCoNER does not only lead to the overall best results, comparable with the deep language models, but FooDCoNER is also much more efficient with respect to run time and sample size requirements of the training data. The latter has been identified via the study of learning curves. Overall, our results not only provide a new tool for food and dietary constituent NER but also shed light on the difference between classical machine learning models and recent deep language models.

An ultrastructural 3D reconstruction method for observing the arrangement of collagen fibrils and proteoglycans in the human aortic wall under mechanical load

An insight into changes of soft biological tissue ultrastructures under loading conditions is essential to understand their response to mechanical stimuli. Therefore, this study offers an approach to investigate the arrangement of collagen fibrils and proteoglycans (PGs), which are located within the mechanically loaded aortic wall. The human aortic samples were either fixed directly with glutaraldehyde in the load-free state or subjected to a planar biaxial extension test prior to fixation. The aortic ultrastructure was recorded using electron tomography. Collagen fibrils and PGs were segmented using convolutional neural networks, particularly the ESPNet model. The 3D ultrastructural reconstructions revealed a complex organization of collagen fibrils and PGs. In particular, we observed that not all PGs are attached to the collagen fibrils, but some fill the spaces between the fibrils with a clear distance to the collagen. The complex organization cannot be fully captured or can be severely misinterpreted in 2D. The approach developed opens up practical possibilities, including the quantification of the spatial relationship between collagen fibrils and PGs as a function of the mechanical load. Such quantification can also be used to compare tissues under different conditions, e.g., healthy and diseased, to improve or develop new material models. STATEMENT OF SIGNIFICANCE: The developed approach enables the 3D reconstruction of collagen fibrils and proteoglycans as they are embedded in the loaded human aortic wall. This methodological pipeline comprises the knowledge of arterial mechanics, imaging with transmission electron microscopy and electron tomography, segmentation of 3D image data sets with convolutional neural networks and finally offers a unique insight into the ultrastructural changes in the aortic tissue caused by mechanical stimuli.

The Effect of Uncertainty on Pain Decisions for Self and Others

Background

Estimating others’ pain is a challenging inferential process, associated with a high degree of uncertainty. While much is known about uncertainty’s effect on self‐regarding actions, its impact on other‐regarding decisions for pain have yet to be characterized.

Aim

The present study exploited models of probabilistic decision‐making to investigate how uncertainty influences the valuation and assessment of another’s pain.

Materials & Methods

We engaged 63 dyads (43 strangers and 20 romantic couples) in a task where individual choices affected the pain delivered to either oneself (the agent) or the other member of the dyad. At each trial, agents were presented with cues predicting a given pain intensity with an associated probability of occurrence. Agents either chose a sure (mild decrease of pain) or risky (50% chance of avoiding pain altogether) management option, before bidding on their choice. A heat stimulation was then issued to the target (self or other). Decision‐makers were then asked to rate the pain administered to the target.

Results

We found that the higher the expected pain, the more risk‐averse agents became, in line with findings in value‐based decision‐making. Furthermore, agents gambled less on another individual’s pain (especially strangers) and placed higher bids on pain relief than they did for themselves. Most critically, the uncertainty associated with expected pain dampened ratings made for strangers’ pain. This contrasted with the effect on an agent’s own pain, for which risk had a marginal hyperalgesic effect.

Discussion & Conclusion

Overall, our results suggested that risk selectively affects decision‐making on a stranger’s suffering, both at the level of assessment and treatment selection, by (1) leading to underestimation, (2) privileging sure options and (3) altruistically allocating more money to insure the treatment’s success.

Significance

Uncertainty biases decision‐making but it is unclear if it affects choice behavior on pain for others. In examining this question, we found individuals were generally risk‐seeking when faced with looming pain, but more so for self; and assigned higher monetary values and subjective ratings on another’s pain. However, uncertainty dampened agents’ assessment of a stranger’s pain, suggesting latent variables may contradict overt altruism. This bias may underlie pain underestimation in clinical settings.

Multiscale Model of Antiviral Timing, Potency, and Heterogeneity Effects on an Epithelial Tissue Patch Infected by SARS-CoV-2

We extend our established agent-based multiscale computational model of infection of lung tissue by SARS-CoV-2 to include pharmacokinetic and pharmacodynamic models of remdesivir. We model remdesivir treatment for COVID-19; however, our methods are general to other viral infections and antiviral therapies. We investigate the effects of drug potency, drug dosing frequency, treatment initiation delay, antiviral half-life, and variability in cellular uptake and metabolism of remdesivir and its active metabolite on treatment outcomes in a simulated patch of infected epithelial tissue. Non-spatial deterministic population models which treat all cells of a given class as identical can clarify how treatment dosage and timing influence treatment efficacy. However, they do not reveal how cell-to-cell variability affects treatment outcomes. Our simulations suggest that for a given treatment regime, including cell-to-cell variation in drug uptake, permeability and metabolism increase the likelihood of uncontrolled infection as the cells with the lowest internal levels of antiviral act as super-spreaders within the tissue. The model predicts substantial variability in infection outcomes between similar tissue patches for different treatment options. In models with cellular metabolic variability, antiviral doses have to be increased significantly (>50% depending on simulation parameters) to achieve the same treatment results as with the homogeneous cellular metabolism.

Review of Multi-Criteria Decision-Making Methods in Finance Using Explainable Artificial Intelligence

The influence of Artificial Intelligence is growing, as is the need to make it as explainable as possible. Explainability is one of the main obstacles that AI faces today on the way to more practical implementation. In practise, companies need to use models that balance interpretability and accuracy to make more effective decisions, especially in the field of finance. The main advantages of the multi-criteria decision-making principle (MCDM) in financial decision-making are the ability to structure complex evaluation tasks that allow for well-founded financial decisions, the application of quantitative and qualitative criteria in the analysis process, the possibility of transparency of evaluation and the introduction of improved, universal and practical academic methods to the financial decision-making process. This article presents a review and classification of multi-criteria decision-making methods that help to achieve the goal of forthcoming research: to create artificial intelligence-based methods that are explainable, transparent, and interpretable for most investment decision-makers.

A Seed-Guided Latent Dirichlet Allocation Approach to Predict the Personality of Online Users Using the PEN Model

There is a growing interest in topic modeling to decipher the valuable information embedded in natural texts. However, there are no studies training an unsupervised model to automatically categorize the social networks (SN) messages according to personality traits. Most of the existing literature relied on the Big 5 framework and psychological reports to recognize the personality of users. Furthermore, collecting datasets for other personality themes is an inherent problem that requires unprecedented time and human efforts, and it is bounded with privacy constraints. Alternatively, this study hypothesized that a small set of seed words is enough to decipher the psycholinguistics states encoded in texts, and the auxiliary knowledge could synergize the unsupervised model to categorize the messages according to human traits. Therefore, this study devised a dataless model called Seed-guided Latent Dirichlet Allocation (SLDA) to categorize the SN messages according to the PEN model that comprised Psychoticism, Extraversion, and Neuroticism traits. The intrinsic evaluations were conducted to determine the performance and disclose the nature of texts generated by SLDA, especially in the context of Psychoticism. The extrinsic evaluations were conducted using several machine learning classifiers to posit how well the topic model has identified latent semantic structure that persists over time in the training documents. The findings have shown that SLDA outperformed other models by attaining a coherence score up to 0.78, whereas the machine learning classifiers can achieve precision up to 0.993. We also will be shared the corpus generated by SLDA for further empirical studies.

Personality-targeted persuasive gamified systems: exploring the impact of application domain on the effectiveness of behaviour change strategies

Persuasive gamified systems for health are interventions that promote behaviour change using various persuasive strategies. While research has shown that these strategies are effective at motivating behaviour change, there is little knowledge on whether and how the effectiveness of these strategies vary across multiple domains for people of distinct personality traits. To bridge this gap, we conducted a quantitative study with 568 participants to investigate (a) whether the effectiveness of the persuasive strategies implemented vary within each domain (b) whether the effectiveness of various strategies vary across two distinct domains, (c) how people belonging to different personality traits respond to these strategies, and (d) if people high in a personality trait would be influenced by a persuasive strategy within one domain and not in the other. Our results show that there are significant differences in the effectiveness of various strategies across domains and that people's personality plays a significant role in the perceived persuasiveness of different strategies both within and across distinct domains. The Reward strategy (which involves incentivizing users for achieving specific milestones towards the desired behaviour) and the Competition strategy (which involves allowing users to compete with each other to perform the desired behaviour) were effective for promoting healthy eating but not for smoking cessation for people high in Conscientiousness. We provide design suggestions for developing persuasive gamified interventions for health targeting distinct domains and tailored to individuals depending on their personalities.

MolData, a molecular benchmark for disease and target based machine learning

Deep learning’s automatic feature extraction has been a revolutionary addition to computational drug discovery, infusing both the capabilities of learning abstract features and discovering complex molecular patterns via learning from molecular data. Since biological and chemical knowledge are necessary for overcoming the challenges of data curation, balancing, training, and evaluation, it is important for databases to contain information regarding the exact target and disease of each bioassay. The existing depositories such as PubChem or ChEMBL offer the screening data for millions of molecules against a variety of cells and targets, however, their bioassays contain complex biological descriptions which can hinder their usage by the machine learning community. In this work, a comprehensive disease and target-based dataset is collected from PubChem in order to facilitate and accelerate molecular machine learning for better drug discovery. MolData is one the largest efforts to date for democratizing the molecular machine learning, with roughly 170 million drug screening results from 1.4 million unique molecules assigned to specific diseases and targets. It also provides 30 unique categories of targets and diseases. Correlation analysis of the MolData bioassays unveils valuable information for drug repurposing for multiple diseases including cancer, metabolic disorders, and infectious diseases. Finally, we provide a benchmark of more than 30 models trained on each category using multitask learning. MolData aims to pave the way for computational drug discovery and accelerate the advancement of molecular artificial intelligence in a practical manner. The MolData benchmark data is available at https://GitHub.com/Transilico/MolData as well as within the additional files.

Why quality assurance is necessary in gynecologic radiation oncology

Quality assurance (QA) in radiation oncology involves all checks and processes that ensure that radiotherapy is delivered in an optimal and intended manner. QA is essential for the accurate delivery of brachytherapy and external beam radiotherapy in patients diagnosed with gynecologic malignancies. Inadequate QA can adversely impact clinical outcomes and reduce the reliability of clinical trials. This review highlights the importance of QA in gynecologic radiation oncology and explores the pertinent issues related to its implementation.

Quality management in radiotherapy treatment delivery

Radiation Oncology continues to rely on accurate delivery of radiation, in particular where patients can benefit from more modulated and hypofractioned treatments that can deliver higher dose to the target while optimising dose to normal structures. These deliveries are more complex, and the treatment units are more computerised, leading to a re-evaluation of quality assurance (QA) to test a larger range of options with more stringent criteria without becoming too time and resource consuming. This review explores how modern approaches of risk management and automation can be used to develop and maintain an effective and efficient QA programme. It considers various tools to control and guide radiation delivery including image guidance and motion management. Links with typical maintenance and repair activities are discussed, as well as patient-specific quality control activities. It is demonstrated that a quality management programme applied to treatment delivery can have an impact on individual patients but also on the quality of treatment techniques and future planning. Developing and customising a QA programme for treatment delivery is an important part of radiotherapy. Using modern multidisciplinary approaches can make this also a useful tool for department management.

Beyond English: Considering Language and Culture in Psychological Text Analysis

The paper discusses the role of language and culture in the context of quantitative text analysis in psychological research. It reviews current automatic text analysis methods and approaches from the perspective of the unique challenges that can arise when going beyond the default English language. Special attention is paid to closed-vocabulary approaches and related methods (and Linguistic Inquiry and Word Count in particular), both from the perspective of cross-cultural research where the analytic process inherently consists of comparing phenomena across cultures and languages and the perspective of generalizability beyond the language and the cultural focus of the original investigation. We highlight the need for a more universal and flexible theoretical and methodological grounding of current research, which includes the linguistic, cultural, and situational specifics of communication, and we provide suggestions for procedures that can be implemented in future studies and facilitate psychological text analysis across languages and cultures.

Prediction of Endometrial Carcinoma Using the Combination of Electronic Health Records and an Ensemble Machine Learning Method

Endometrial carcinoma (EC) is a common cause of cancer death in women, and having an early accurate prediction model to identify this disease is crucial. The aim of this study was to develop a new machine learning (ML) model-based diagnostic prediction model for EC. We collected data from consecutive patients between November 2012 and January 2021 at tertiary hospitals in central China. Inclusion criteria included women undergoing endometrial biopsy, dilation and curettage, or hysterectomy. A total of 9 features, including patient demographics, vital signs, and laboratory and ultrasound results, were selected in the final analysis. This new model was combined with three top optimal ML methods, namely, logistic regression, gradient-boosted decision tree, and random forest. A total of 1,922 patients were eligible for final analysis and modeling. The ensemble model, called TJHPEC, was validated in an internal validation cohort and two external validation cohorts. The results showed that the AUC values were 0.9346, 0.8341, and 0.8649 for the prediction of total EC and 0.9347, 0.8073, and 0.871 for prediction of stage I EC. Nine clinical features were confirmed to be highly related to the prediction of EC in TJHPEC. In conclusion, our new model may be accurate for identifying EC, especially in the early stage, in the general population of central China.

Nucleic Acid-Based COVID-19 Therapy Targeting Cytokine Storms: Strategies to Quell the Storm

Coronavirus disease 2019 (COVID-19) has shaken the world and triggered drastic changes in our lifestyle to control it. Despite the non-typical efforts, COVID-19 still thrives and plagues humanity worldwide. The unparalleled degree of infection has been met with an exceptional degree of research to counteract it. Many drugs and therapeutic technologies have been repurposed and discovered, but no groundbreaking antiviral agent has been introduced yet to eradicate COVID-19 and restore normalcy. As lethality is directly correlated with the severity of disease, hospitalized severe cases are of the greatest importance to reduce, especially the cytokine storm phenomenon. This severe inflammatory phenomenon characterized by elevated levels of inflammatory mediators can be targeted to relieve symptoms and save the infected patients. One of the promising therapeutic strategies to combat COVID-19 is nucleic acid-based therapeutic approaches, including microRNAs (miRNAs). This work is an up-to-date review aimed to comprehensively discuss the current nucleic acid-based therapeutics against COVID-19 and their mechanisms of action, taking into consideration the emerging SARS-CoV-2 variants of concern, as well as providing potential future directions. miRNAs can be used to run interference with the expression of viral proteins, while endogenous miRNAs can be targeted as well, offering a versatile platform to control SARS-CoV-2 infection. By targeting these miRNAs, the COVID-19-induced cytokine storm can be suppressed. Therefore, nucleic acid-based therapeutics (miRNAs included) have a latent ability to break the COVID-19 infection in general and quell the cytokine storm in particular.

Cubical Homology-Based Machine Learning: An Application in Image Classification

Persistent homology is a powerful tool in topological data analysis (TDA) to compute, study, and encode efficiently multi-scale topological features and is being increasingly used in digital image classification. The topological features represent a number of connected components, cycles, and voids that describe the shape of data. Persistent homology extracts the birth and death of these topological features through a filtration process. The lifespan of these features can be represented using persistent diagrams (topological signatures). Cubical homology is a more efficient method for extracting topological features from a 2D image and uses a collection of cubes to compute the homology, which fits the digital image structure of grids. In this research, we propose a cubical homology-based algorithm for extracting topological features from 2D images to generate their topological signatures. Additionally, we propose a novel score measure, which measures the significance of each of the sub-simplices in terms of persistence. In addition, gray-level co-occurrence matrix (GLCM) and contrast limited adapting histogram equalization (CLAHE) are used as supplementary methods for extracting features. Supervised machine learning models are trained on selected image datasets to study the efficacy of the extracted topological features. Among the eight tested models with six published image datasets of varying pixel sizes, classes, and distributions, our experiments demonstrate that cubical homology-based machine learning with the deep residual network (ResNet 1D) and Light Gradient Boosting Machine (lightGBM) shows promise with the extracted topological features.

Semi-automated approach for generation of biological networks on drug-induced cholestasis, steatosis, hepatitis, and cirrhosis

Drug-induced liver injury (DILI) is one of the leading reasons for discontinuation of a new drug development project. Diverse machine learning or deep learning models have been developed to predict DILI. However, these models have not provided an adequate understanding of the mechanisms leading to DILI. The development of safer drugs requires novel computational approaches that enable the prompt understanding of the mechanism of DILI. In this study, the mechanisms leading to the development of cholestasis, steatosis, hepatitis, and cirrhosis were explored using a semi-automated approach for data gathering and associations. Diverse data from ToxCast, Comparative Toxicogenomic Database (CTD), Reactome, and Open TG-GATEs on reference molecules leading to the development of the respective diseases were extracted. The data were used to create biological networks of the four diseases. As expected, the four networks had several common pathways, and a joint DILI network was assembled. Such biological networks could be used in drug discovery to identify possible molecules of concern as they provide a better understanding of the disease-specific key events. The events can be target-tested to provide indications for potential DILI effects.

Long-COVID diagnosis: From diagnostic to advanced AI-driven models

SARS-COV 2 is recognized to be responsible for a multi-organ syndrome. In most patients, symptoms are mild. However, in certain subjects, COVID-19 tends to progress more severely. Most of the patients infected with SARS-COV2 fully recovered within some weeks. In a considerable number of patients, like many other viral infections, various long-lasting symptoms have been described, now defined as "long COVID-19 syndrome". Given the high number of contagious over the world, it is necessary to understand and comprehend this emerging pathology to enable early diagnosis and improve patents outcomes. In this scenario, AI-based models can be applied in long-COVID-19 patients to assist clinicians and at the same time, to reduce the considerable impact on the care and rehabilitation unit. The purpose of this manuscript is to review different aspects of long-COVID-19 syndrome from clinical presentation to diagnosis, highlighting the considerable impact that AI can have.

Stakeholders' perspectives on the future of artificial intelligence in radiology: a scoping review

OBJECTIVES

Artificial intelligence (AI) has the potential to impact clinical practice and healthcare delivery. AI is of particular significance in radiology due to its use in automatic analysis of image characteristics. This scoping review examines stakeholder perspectives on AI use in radiology, the benefits, risks, and challenges to its integration.

METHODS

A search was conducted from 1960 to November 2019 in EMBASE, PubMed/MEDLINE, Web of Science, Cochrane Library, CINAHL, and grey literature. Publications reflecting stakeholder attitudes toward AI were included with no restrictions.

RESULTS

Commentaries (n = 32), surveys (n = 13), presentation abstracts (n = 8), narrative reviews (n = 8), and a social media study (n = 1) were included from 62 eligible publications. These represent the views of radiologists, surgeons, medical students, patients, computer scientists, and the general public. Seven themes were identified (predicted impact, potential replacement, trust in AI, knowledge of AI, education, economic considerations, and medicolegal implications). Stakeholders anticipate a significant impact on radiology, though replacement of radiologists is unlikely in the near future. Knowledge of AI is limited for non-computer scientists and further education is desired. Many expressed the need for collaboration between radiologists and AI specialists to successfully improve patient care.

CONCLUSIONS

Stakeholder views generally suggest that AI can improve the practice of radiology and consider the replacement of radiologists unlikely. Most stakeholders identified the need for education and training on AI, as well as collaborative efforts to improve AI implementation. Further research is needed to gain perspectives from non-Western countries, non-radiologist stakeholders, on economic considerations, and medicolegal implications.

KEY POINTS

Stakeholders generally expressed that AI alone cannot be used to replace radiologists. The scope of practice is expected to shift with AI use affecting areas from image interpretation to patient care. Patients and the general public do not know how to address potential errors made by AI systems while radiologists believe that they should be "in-the-loop" in terms of responsibility. Ethical accountability strategies must be developed across governance levels. Students, residents, and radiologists believe that there is a lack in AI education during medical school and residency. The radiology community should work with IT specialists to ensure that AI technology benefits their work and centres patients.

COVID-19: A systematic review and update on prevention, diagnosis, and treatment

Since the rapid onset of the COVID-19 or SARS-CoV-2 pandemic in the world in 2019, extensive studies have been conducted to unveil the behavior and emission pattern of the virus in order to determine the best ways to diagnosis of virus and thereof formulate effective drugs or vaccines to combat the disease. The emergence of novel diagnostic and therapeutic techniques considering the multiplicity of reports from one side and contradictions in assessments from the other side necessitates instantaneous updates on the progress of clinical investigations. There is also growing public anxiety from time to time mutation of COVID-19, as reflected in considerable mortality and transmission, respectively, from delta and Omicron variants. We comprehensively review and summarize different aspects of prevention, diagnosis, and treatment of COVID-19. First, biological characteristics of COVID-19 were explained from diagnosis standpoint. Thereafter, the preclinical animal models of COVID-19 were discussed to frame the symptoms and clinical effects of COVID-19 from patient to patient with treatment strategies and in-silico/computational biology. Finally, the opportunities and challenges of nanoscience/nanotechnology in identification, diagnosis, and treatment of COVID-19 were discussed. This review covers almost all SARS-CoV-2-related topics extensively to deepen the understanding of the latest achievements (last updated on January 11, 2022).

Application of evidence-based methods to construct mechanism-driven chemical assessment frameworks

The workshop titled “Application of evidence-based methods to construct mechanism-driven chemical assessment frameworks” was co-organized by the Evidence-based Toxicology Collaboration and the European Food Safety Authority (EFSA) and hosted by EFSA at its headquarters in Parma, Italy on October 2 and 3, 2019. The goal was to explore integration of systematic review with mechanistic evidence evaluation. Participants were invited to work on concrete products to advance the exploration of how evidence-based approaches can support the development and application of adverse outcome pathways (AOP) in chemical risk assessment. The workshop discussions were centered around three related themes: 1) assessing certainty in AOPs, 2) literature-based AOP development, and 3) integrating certainty in AOPs and non-animal evidence into decision frameworks. Several challenges, mostly related to methodology, were identified and largely determined the workshop recommendations. The workshop recommendations included the comparison and potential alignment of processes used to develop AOP and systematic review methodology, including the translation of vocabulary of evidence-based methods to AOP and vice versa, the development and improvement of evidence mapping and text mining methods and tools, as well as a call for a fundamental change in chemical risk and uncertainty assessment methodology if to be conducted based on AOPs and new approach methodologies (NAM). The usefulness of evidence-based approaches for mechanism-based chemical risk assessments was stressed, particularly the potential contribution of the rigor and transparency inherent to such approaches in building stakeholders’ trust for implementation of NAM evidence and AOPs into chemical risk assessment.

Cheap robust learning of data anomalies with analytically solvable entropic outlier sparsification

Entropic outlier sparsification (EOS) is proposed as a cheap and robust computational strategy for learning in the presence of data anomalies and outliers. EOS dwells on the derived analytic solution of the (weighted) expected loss minimization problem subject to Shannon entropy regularization. An identified closed-form solution is proven to impose additional costs that depend linearly on statistics size and are independent of data dimension. Obtained analytic results also explain why the mixtures of spherically symmetric Gaussians—used heuristically in many popular data analysis algorithms—represent an optimal and least-biased choice for the nonparametric probability distributions when working with squared Euclidean distances. The performance of EOS is compared to a range of commonly used tools on synthetic problems and on partially mislabeled supervised classification problems from biomedicine. Applying EOS for coinference of data anomalies during learning is shown to allow reaching an accuracy of 97%±2% when predicting patient mortality after heart failure, statistically significantly outperforming predictive performance of common learning tools for the same data.

Interpretable tree-based ensemble model for predicting beach water quality

Tree-based machine learning models based on environmental features offer low-cost and timely solutions for predicting microbial fecal contamination in beach water to inform the public of the health risk. However, many of these models are black boxes that are difficult for humans to understand, which may cause severe consequences such as unexplained decisions and failure in accountability. To develop interpretable predictive models for beach water quality, we evaluate five tree-based models, namely classification tree, random forest, CatBoost, XGBoost, and LightGBM, and employ a state-of-the-art explanation method SHAP to explain the models. When tested on the Escherichia coli (E. coli) concentration data collected from three beach sites along Lake Erie shores, LightGBM, followed by XGBoost, achieves the highest averaged precision and recall scores. For all three sites, both models suggest lake turbidity as the most important predictor, and elucidate the crucial role of accurate local data of wave height and rainfall in the model development. Local SHAP values further reveal the robustness of the importance of lake turbidity as its SHAP value increases nearly monotonically with its value and is minimally affected by other environmental factors. Moreover, we found an intriguing interaction between lake turbidity and day-of-year. This work suggests that the combination of LightGBM and SHAP has a promising potential to develop interpretable models for predicting microbial water quality in freshwater lakes.

Dehumanization: trends, insights, and challenges

Despite our many differences, one superordinate category we all belong to is 'humans'. To strip away or overlook others' humanity, then, is to mark them as 'other' and, typically, 'less than'. We review growing evidence revealing how and why we subtly disregard the humanity of those around us. We then highlight new research suggesting that we continue to blatantly dehumanize certain groups, overtly likening them to animals, with important implications for intergroup hostility. We discuss advances in understanding the experience of being dehumanized and novel interventions to mitigate dehumanization, address the conceptual boundaries of dehumanization, and consider recent accounts challenging the importance of dehumanization and its role in intergroup violence. Finally, we present an agenda of outstanding questions to propel dehumanization research forward.

Modelling Covid-19 infections in Zambia using data mining techniques

The outbreak of Covid-19 pandemic has been declared a global health crisis by the World Health Organization since its emergence. Several researchers have proposed a number of techniques to understand how the pandemic affects the populations. Reported among these techniques are data mining models which have been successfully applied in a wide range of situations before the advent of Covid-19 pandemic. In this work, the researchers have applied a number of existing data mining methods (classifiers) available in the Waikato Environment for Knowledge Analysis (WEKA) machine learning library. WEKA was used to gain a better understanding on how the epidemic spread within Zambia. The classifiers used are J48 decision tree, Multilayer Perceptron and Naïve Bayes among others. The predictions of these techniques are compared against simpler classifiers and those reported in related works.

The application of artificial intelligence in hepatology: A systematic review

The integration of human and artificial intelligence (AI) in medicine has only recently begun but it has already become obvious that intelligent systems can dramatically improve the management of liver diseases. Big data made it possible to envisage transformative developments of the use of AI for diagnosing, predicting prognosis and treating liver diseases, but there is still a lot of work to do. If we want to achieve the 21^st century digital revolution, there is an urgent need for specific national and international rules, and to adhere to bioethical parameters when collecting data. Avoiding misleading results is essential for the effective use of AI. A crucial question is whether it is possible to sustain, technically and morally, the process of integration between man and machine. We present a systematic review on the applications of AI to hepatology, highlighting the current challenges and crucial issues related to the use of such technologies.

How a managed service for colon capsule endoscopy works in an overstretched healthcare system

Lower gastrointestinal diagnostics have been facing significant capacity constraints, which the COVID-19 pandemic has exacerbated due to significant reductions in endoscopy procedures. Colon Capsule Endoscopy (CCE) provides a safe, viable solution to offset ongoing demand and could be a valuable tool for the recovery of endoscopy services post-COVID. NHS Scotland has already begun a country-wide rollout of CCE as a managed service, and NHS England have committed to a pilot scheme of 11,000 capsules via hospital-based delivery. Here, we outline a proven method of CCE delivery that ensures the CCE and results are delivered in an efficient, clinically robust manner with high patient acceptability levels through a managed service. Delivering CCE without a managed service is likely to be slower, more costly, and less effective, limiting the many benefits of CCE as an addition to the standard diagnostic pathway for bowel cancer.

Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models

Type 2 diabetes mellitus (T2DM) often results in high morbidity and mortality. In addition, T2DM presents a substantial financial burden for individuals and their families, health systems, and societies. According to studies and reports, globally, the incidence and prevalence of T2DM are increasing rapidly. Several models have been built to predict T2DM onset in the future or detect undiagnosed T2DM in patients. Additional to the performance of such models, their interpretability is crucial for health experts, especially in personalized clinical prediction models. Data collected over 42 months from health check-up examinations and prescribed drugs data repositories of four primary healthcare providers were used in this study. We propose a framework consisting of LogicRegression based feature extraction and Least Absolute Shrinkage and Selection operator based prediction modeling for undiagnosed T2DM prediction. Performance of the models was measured using Area under the ROC curve (AUC) with corresponding confidence intervals. Results show that using LogicRegression based feature extraction resulted in simpler models, which are easier for healthcare experts to interpret, especially in cases with many binary features. Models developed using the proposed framework resulted in an AUC of 0.818 (95% Confidence Interval (CI): 0.812−0.823) that was comparable to more complex models (i.e., models with a larger number of features), where all features were included in prediction model development with the AUC of 0.816 (95% CI: 0.810−0.822). However, the difference in the number of used features was significant. This study proposes a framework for building interpretable models in healthcare that can contribute to higher trust in prediction models from healthcare experts.

Financial Risk Management and Explainable, Trustworthy, Responsible AI

This perspective paper is based on several sessions by the members of the Round Table AI at FIRM¹, with input from a number of external and international speakers. Its particular focus lies on the management of the model risk of productive models in banks and other financial institutions. The models in view range from simple rules-based approaches to Artificial Intelligence (AI) or Machine learning (ML) models with a high level of sophistication. The typical applications of those models are related to predictions and decision making around the value chain of credit risk (including accounting side under IFRS9 or related national GAAP approaches), insurance risk or other financial risk types. We expect more models of higher complexity in the space of anti-money laundering, fraud detection and transaction monitoring as well as a rise of AI/ML models as alternatives to current methods in solving some of the more intricate stochastic differential equations needed for the pricing and/or valuation of derivatives. The same type of model is also successful in areas unrelated to risk management, such as sales optimization, customer lifetime value considerations, robo-advisory, and other fields of applications. The paper refers to recent related publications from central banks, financial supervisors and regulators as well as other relevant sources and working groups. It aims to give practical advice for establishing a risk-based governance and testing framework for the mentioned model types and discusses the use of recent technologies, approaches, and platforms to support the establishment of responsible, trustworthy, explainable, auditable, and manageable AI/ML in production. In view of the recent EU publication on AI, also referred to as the EU Artificial Intelligence Act (AIA), we also see a certain added value for this paper as an instigator of further thinking outside of the financial services sector, in particular where “High Risk” models according to the mentioned EU consultation are concerned.

A Data-Efficient Framework for the Identification of Vaginitis Based on Deep Learning

Vaginitis is a gynecological disease affecting the health of millions of women all over the world. The traditional diagnosis of vaginitis is based on manual microscopy, which is time-consuming and tedious. The deep learning method offers a fast and reliable solution for an automatic early diagnosis of vaginitis. However, deep neural networks require massive well-annotated data. Manual annotation of microscopic images is highly cost extensive because it not only is a time-consuming process but also needs highly trained people (doctors, pathologists, or technicians). Most existing active learning approaches are not applicable in microscopic images due to the nature of complex backgrounds and numerous formed elements. To address the problem of high cost of labeling microscopic images, we present a data-efficient framework for the identification of vaginitis based on transfer learning and active learning strategies. The proposed informative sample selection strategy selected the minimal training subset, and then the pretrained convolutional neural network (CNN) was fine-tuned on the selected subset. The experiment results show that the proposed pipeline can save 37.5% annotation cost while maintaining competitive performance. The proposed promising novel framework can significantly save the annotation cost and has the potential of extending widely to other microscopic imaging applications, such as blood microscopic image analysis.

COVID-rate: an automated framework for segmentation of COVID-19 lesions from chest CT images

Novel Coronavirus disease (COVID-19) is a highly contagious respiratory infection that has had devastating effects on the world. Recently, new COVID-19 variants are emerging making the situation more challenging and threatening. Evaluation and quantification of COVID-19 lung abnormalities based on chest Computed Tomography (CT) images can help determining the disease stage, efficiently allocating limited healthcare resources, and making informed treatment decisions. During pandemic era, however, visual assessment and quantification of COVID-19 lung lesions by expert radiologists become expensive and prone to error, which raises an urgent quest to develop practical autonomous solutions. In this context, first, the paper introduces an open-access COVID-19 CT segmentation dataset containing 433 CT images from 82 patients that have been annotated by an expert radiologist. Second, a Deep Neural Network (DNN)-based framework is proposed, referred to as the [Formula: see text], that autonomously segments lung abnormalities associated with COVID-19 from chest CT images. Performance of the proposed [Formula: see text] framework is evaluated through several experiments based on the introduced and external datasets. Third, an unsupervised enhancement approach is introduced that can reduce the gap between the training set and test set and improve the model generalization. The enhanced results show a dice score of 0.8069 and specificity and sensitivity of 0.9969 and 0.8354, respectively. Furthermore, the results indicate that the [Formula: see text] model can efficiently segment COVID-19 lesions in both 2D CT images and whole lung volumes. Results on the external dataset illustrate generalization capabilities of the [Formula: see text] model to CT images obtained from a different scanner.