BPCN: bilateral progressive compensation network for lung infection image segmentation.

Lung infection image segmentation is a key technology for autonomous understanding of the potential illness. However, current approaches usually lose the low-level details, which leads to a considerable accuracy decrease for lung infection areas with varied shapes and sizes. In this paper, we propose bilateral progressive compensation network (BPCN), a bilateral progressive compensation network to improve the accuracy of lung lesion segmentation through complementary learning of spatial and semantic features. The proposed BPCN are mainly composed of two deep branches. One branch is the multi-scale progressive fusion for main region features. The other branch is a flow-field based adaptive body-edge aggregation operations to explicitly learn detail features of lung infection areas which is supplement to region features. In addition, we propose a bilateral spatial-channel down-sampling to generate a hierarchical complementary feature which avoids losing discriminative features caused by pooling operations. Experimental results show that our proposed network outperforms state-of-the-art segmentation methods in lung infection segmentation on two public image datasets with or without a pseudo-label training strategy.

DeepMPF: deep learning framework for predicting drug-target interactions based on multi-modal representation with meta-path semantic analysis.

BACKGROUND: Drug-target interaction (DTI) prediction has become a crucial prerequisite in drug design and drug discovery. However, the traditional biological experiment is time-consuming and expensive, as there are abundant complex interactions present in the large size of genomic and chemical spaces. For alleviating this phenomenon, plenty of computational methods are conducted to effectively complement biological experiments and narrow the search spaces into a preferred candidate domain. Whereas, most of the previous approaches cannot fully consider association behavior semantic information based on several schemas to represent complex the structure of heterogeneous biological networks. Additionally, the prediction of DTI based on single modalities cannot satisfy the demand for prediction accuracy. METHODS: We propose a multi-modal representation framework of 'DeepMPF' based on meta-path semantic analysis, which effectively utilizes heterogeneous information to predict DTI. Specifically, we first construct protein-drug-disease heterogeneous networks composed of three entities. Then the feature information is obtained under three views, containing sequence modality, heterogeneous structure modality and similarity modality. We proposed six representative schemas of meta-path to preserve the high-order nonlinear structure and catch hidden structural information of the heterogeneous network. Finally, DeepMPF generates highly representative comprehensive feature descriptors and calculates the probability of interaction through joint learning. RESULTS: To evaluate the predictive performance of DeepMPF, comparison experiments are conducted on four gold datasets. Our method can obtain competitive performance in all datasets. We also explore the influence of the different feature embedding dimensions, learning strategies and classification methods. Meaningfully, the drug repositioning experiments on COVID-19 and HIV demonstrate DeepMPF can be applied to solve problems in reality and help drug discovery. The further analysis of molecular docking experiments enhances the credibility of the drug candidates predicted by DeepMPF. CONCLUSIONS: All the results demonstrate the effectively predictive capability of DeepMPF for drug-target interactions. It can be utilized as a useful tool to prescreen the most potential drug candidates for the protein. The web server of the DeepMPF predictor is freely available at http://120.77.11.78/DeepMPF/ , which can help relevant researchers to further study.

MMViT-Seg: A lightweight transformer and CNN fusion network for COVID-19 segmentation.

BACKGROUND AND OBJECTIVE: COVID-19 is a serious threat to human health. Traditional convolutional neural networks (CNNs) can realize medical image segmentation, whilst transformers can be used to perform machine vision tasks, because they have a better ability to capture long-range relationships than CNNs. The combination of CNN and transformers to complete the task of semantic segmentation has attracted intense research. Currently, it is challenging to segment medical images on limited data sets like that on COVID-19. METHODS: This study proposes a lightweight transformer+CNN model, in which the encoder sub-network is a two-path design that enables both the global dependence of image features and the low layer spatial details to be effectively captured. Using CNN and MobileViT to jointly extract image features reduces the amount of computation and complexity of the model as well as improves the segmentation performance. So this model is titled Mini-MobileViT-Seg (MMViT-Seg). In addition, a multi query attention (MQA) module is proposed to fuse the multi-scale features from different levels of decoder sub-network, further improving the performance of the model. MQA can simultaneously fuse multi-input, multi-scale low-level feature maps and high-level feature maps as well as conduct end-to-end supervised learning guided by ground truth. RESULTS: The two-class infection labeling experiments were conducted based on three datasets. The final results show that the proposed model has the best performance and the minimum number of parameters among five popular semantic segmentation algorithms. In multi-class infection labeling results, the proposed model also achieved competitive performance. CONCLUSIONS: The proposed MMViT-Seg is tested on three COVID-19 segmentation datasets, with results showing that this model has better performance than other models. In addition, the proposed MQA module, which can effectively fuse multi-scale features of different levels further improves the segmentation accuracy.

Multi-scale Triplet Hashing for Medical Image Retrieval.

For medical image retrieval task, deep hashing algorithms are widely applied in large-scale datasets for auxiliary diagnosis due to the retrieval efficiency advantage of hash codes. Most of which focus on features learning, whilst neglecting the discriminate area of medical images and hierarchical similarity for deep features and hash codes. In this paper, we tackle these dilemmas with a new Multi-scale Triplet Hashing (MTH) algorithm, which can leverage multi-scale information, convolutional self-attention and hierarchical similarity to learn effective hash codes simultaneously. The MTH algorithm first designs multi-scale DenseBlock module to learn multi-scale information of medical images. Meanwhile, a convolutional self-attention mechanism is developed to perform information interaction of the channel domain, which can capture the discriminate area of medical images effectively. On top of the two paths, a novel loss function is proposed to not only conserve the category-level information of deep features and the semantic information of hash codes in the learning process, but also capture the hierarchical similarity for deep features and hash codes. Extensive experiments on the Curated X-ray Dataset, Skin Cancer MNIST Dataset and COVID-19 Radiography Dataset illustrate that the MTH algorithm can further enhance the effect of medical retrieval compared to other state-of-the-art medical image retrieval algorithms.

MedLexSp - a medical lexicon for Spanish medical natural language processing.

BACKGROUND: Medical lexicons enable the natural language processing (NLP) of health texts. Lexicons gather terms and concepts from thesauri and ontologies, and linguistic data for part-of-speech (PoS) tagging, lemmatization or natural language generation. To date, there is no such type of resource for Spanish. CONSTRUCTION AND CONTENT: This article describes an unified medical lexicon for Medical Natural Language Processing in Spanish. MedLexSp includes terms and inflected word forms with PoS information and Unified Medical Language System[Formula: see text] (UMLS) semantic types, groups and Concept Unique Identifiers (CUIs). To create it, we used NLP techniques and domain corpora (e.g. MedlinePlus). We also collected terms from the Dictionary of Medical Terms from the Spanish Royal Academy of Medicine, the Medical Subject Headings (MeSH), the Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT), the Medical Dictionary for Regulatory Activities Terminology (MedDRA), the International Classification of Diseases vs. 10, the Anatomical Therapeutic Chemical Classification, the National Cancer Institute (NCI) Dictionary, the Online Mendelian Inheritance in Man (OMIM) and OrphaData. Terms related to COVID-19 were assembled by applying a similarity-based approach with word embeddings trained on a large corpus. MedLexSp includes 100 887 lemmas, 302 543 inflected forms (conjugated verbs, and number/gender variants), and 42 958 UMLS CUIs. We report two use cases of MedLexSp. First, applying the lexicon to pre-annotate a corpus of 1200 texts related to clinical trials. Second, PoS tagging and lemmatizing texts about clinical cases. MedLexSp improved the scores for PoS tagging and lemmatization compared to the default Spacy and Stanza python libraries. CONCLUSIONS: The lexicon is distributed in a delimiter-separated value file; an XML file with the Lexical Markup Framework; a lemmatizer module for the Spacy and Stanza libraries; and complementary Lexical Record (LR) files. The embeddings and code to extract COVID-19 terms, and the Spacy and Stanza lemmatizers enriched with medical terms are provided in a public repository.

Emergence of Covid-19 as a Novel Concept Shifts Existing Semantic Spaces.

Conceptual knowledge is dynamic, fluid, and flexible, changing as a function of contextual factors at multiple scales. The Covid-19 pandemic can be considered a large-scale, global context that has fundamentally altered most people's experiences with the world. It has also introduced a new concept, COVID (or COVID-19), into our collective knowledgebase. What are the implications of this introduction for how existing conceptual knowledge is structured? Our collective emotional and social experiences with the world have been profoundly impacted by the Covid-19 pandemic, and experience-based perspectives on concept representation suggest that emotional and social experiences are critical components of conceptual knowledge. Such changes in collective experience should, then, have downstream consequences on knowledge of emotion- and social-related concepts. Using a naturally occurring dataset derived from the social media platform Twitter, we show that semantic spaces for concepts related to our emotional experiences with Covid-19 (i.e., emotional concepts like FEAR)-but not for unrelated concepts (i.e., animals like CAT)-show quantifiable shifts as a function of the emergence of COVID-19 as a concept and its associated emotional and social experiences, shifts which persist 6 months after the onset of the pandemic. The findings support a dynamic view of conceptual knowledge wherein shared experiences affect conceptual structure.

LitCovid ensemble learning for COVID-19 multi-label classification.

The Coronavirus Disease 2019 (COVID-19) pandemic has shifted the focus of research worldwide, and more than 10 000 new articles per month have concentrated on COVID-19-related topics. Considering this rapidly growing literature, the efficient and precise extraction of the main topics of COVID-19-relevant articles is of great importance. The manual curation of this information for biomedical literature is labor-intensive and time-consuming, and as such the procedure is insufficient and difficult to maintain. In response to these complications, the BioCreative VII community has proposed a challenging task, LitCovid Track, calling for a global effort to automatically extract semantic topics for COVID-19 literature. This article describes our work on the BioCreative VII LitCovid Track. We proposed the LitCovid Ensemble Learning (LCEL) method for the tasks and integrated multiple biomedical pretrained models to address the COVID-19 multi-label classification problem. Specifically, seven different transformer-based pretrained models were ensembled for the initialization and fine-tuning processes independently. To enhance the representation abilities of the deep neural models, diverse additional biomedical knowledge was utilized to facilitate the fruitfulness of the semantic expressions. Simple yet effective data augmentation was also leveraged to address the learning deficiency during the training phase. In addition, given the imbalanced label distribution of the challenging task, a novel asymmetric loss function was applied to the LCEL model, which explicitly adjusted the negative-positive importance by assigning different exponential decay factors and helped the model focus on the positive samples. After the training phase, an ensemble bagging strategy was adopted to merge the outputs from each model for final predictions. The experimental results show the effectiveness of our proposed approach, as LCEL obtains the state-of-the-art performance on the LitCovid dataset. Database URL: https://github.com/JHnlp/LCEL.

Semantic Sentiment Classification for COVID-19 Tweets Using Universal Sentence Encoder.

The spread of data on the web has increased in the last twenty years. One of the reasons is the appearance of social media. The data on social sites describe many real-life events in our daily lives. In the period of the COVID-19 pandemic, a lot of people and media organizations were writing and documenting their health status and the latest news about the coronavirus on social media. Using these tweets (sentiments) about the coronavirus and analyzing them in a computational model can help decision makers in measuring public opinion and yielding remarkable findings. In this research article, we introduce a deep learning sentiment analysis model based on Universal Sentence Encoder. The dataset used in this research was collected from Twitter, and it was classified as positive, neutral, and negative. The sentence embedding model determines the meaning of word sequences instead of individual words. The model divides the dataset into training and testing and depends on the sentence similarity in detecting sentiment class. The obtained accuracy results reached 78.062%, and this result outperforms many traditional ML classifiers based on TF-IDF applied on the same dataset and another model based on the CNN classifier.

Semantic interoperability: ontological unpacking of a viral conceptual model.

BACKGROUND: Genomics and virology are unquestionably important, but complex, domains being investigated by a large number of scientists. The need to facilitate and support work within these domains requires sharing of databases, although it is often difficult to do so because of the different ways in which data is represented across the databases. To foster semantic interoperability, models are needed that provide a deep understanding and interpretation of the concepts in a domain, so that the data can be consistently interpreted among researchers. RESULTS: In this research, we propose the use of conceptual models to support semantic interoperability among databases and assess their ontological clarity to support their effective use. This modeling effort is illustrated by its application to the Viral Conceptual Model (VCM) that captures and represents the sequencing of viruses, inspired by the need to understand the genomic aspects of the virus responsible for COVID-19. For achieving semantic clarity on the VCM, we leverage the "ontological unpacking" method, a process of ontological analysis that reveals the ontological foundation of the information that is represented in a conceptual model. This is accomplished by applying the stereotypes of the OntoUML ontology-driven conceptual modeling language.As a result, we propose a new OntoVCM, an ontologically grounded model, based on the initial VCM, but with guaranteed interoperability among the data sources that employ it. CONCLUSIONS: We propose and illustrate how the unpacking of the Viral Conceptual Model resolves several issues related to semantic interoperability, the importance of which is recognized by the "I" in FAIR principles. The research addresses conceptual uncertainty within the domain of SARS-CoV-2 data and knowledge.The method employed provides the basis for further analyses of complex models currently used in life science applications, but lacking ontological grounding, subsequently hindering the interoperability needed for scientists to progress their research.

Calibrated bagging deep learning for image semantic segmentation: A case study on COVID-19 chest X-ray image.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes coronavirus disease 2019 (COVID-19). Imaging tests such as chest X-ray (CXR) and computed tomography (CT) can provide useful information to clinical staff for facilitating a diagnosis of COVID-19 in a more efficient and comprehensive manner. As a breakthrough of artificial intelligence (AI), deep learning has been applied to perform COVID-19 infection region segmentation and disease classification by analyzing CXR and CT data. However, prediction uncertainty of deep learning models for these tasks, which is very important to safety-critical applications like medical image processing, has not been comprehensively investigated. In this work, we propose a novel ensemble deep learning model through integrating bagging deep learning and model calibration to not only enhance segmentation performance, but also reduce prediction uncertainty. The proposed method has been validated on a large dataset that is associated with CXR image segmentation. Experimental results demonstrate that the proposed method can improve the segmentation performance, as well as decrease prediction uncertainty.

Predicting Emerging Themes in Rapidly Expanding COVID-19 Literature With Unsupervised Word Embeddings and Machine Learning: Evidence-Based Study.

BACKGROUND: Evidence from peer-reviewed literature is the cornerstone for designing responses to global threats such as COVID-19. In massive and rapidly growing corpuses, such as COVID-19 publications, assimilating and synthesizing information is challenging. Leveraging a robust computational pipeline that evaluates multiple aspects, such as network topological features, communities, and their temporal trends, can make this process more efficient. OBJECTIVE: We aimed to show that new knowledge can be captured and tracked using the temporal change in the underlying unsupervised word embeddings of the literature. Further imminent themes can be predicted using machine learning on the evolving associations between words. METHODS: Frequently occurring medical entities were extracted from the abstracts of more than 150,000 COVID-19 articles published on the World Health Organization database, collected on a monthly interval starting from February 2020. Word embeddings trained on each month's literature were used to construct networks of entities with cosine similarities as edge weights. Topological features of the subsequent month's network were forecasted based on prior patterns, and new links were predicted using supervised machine learning. Community detection and alluvial diagrams were used to track biomedical themes that evolved over the months. RESULTS: We found that thromboembolic complications were detected as an emerging theme as early as August 2020. A shift toward the symptoms of long COVID complications was observed during March 2021, and neurological complications gained significance in June 2021. A prospective validation of the link prediction models achieved an area under the receiver operating characteristic curve of 0.87. Predictive modeling revealed predisposing conditions, symptoms, cross-infection, and neurological complications as dominant research themes in COVID-19 publications based on the patterns observed in previous months. CONCLUSIONS: Machine learning-based prediction of emerging links can contribute toward steering research by capturing themes represented by groups of medical entities, based on patterns of semantic relationships over time.

How Has COVID-19 Impacted Our Language Use?

The COVID-19 pandemic has led to severe consequences for people's mental health. The pandemic has also influenced our language use, shaping our word formation habits. The overuse of new metaphorical meanings has received particular attention from the media. Here, we wanted to investigate whether these metaphors have led to the formation of new semantic associations in memory. A sample of 120 university students was asked to decide whether a target word was or was not related to a prime stimulus. Responses for pandemic pairs in which the target referred to the newly acquired metaphorical meaning of the prime (i.e., "trench"-"hospital") were compared to pre-existing semantically related pairs (i.e., "trench"-"soldier") and neutral pairs (i.e., "trench"-"response"). Results revealed greater accuracy and faster response times for pandemic pairs than for semantic pairs and for semantic pairs compared to neutral ones. These findings suggest that the newly learned pandemic associations have created stronger semantic links in our memory compared to the pre-existing ones. Thus, this work confirms the adaptive nature of human language, and it underlines how the overuse of metaphors evoking dramatic images has been, in part, responsible for many psychological disorders still reported among people nowadays.

Valence norms for 3,600 English words collected during the COVID-19 pandemic: Effects of age and the pandemic.

The topic of affective development over the lifespan is at the forefront of psychological science. One of the intriguing findings in this area is superior emotion regulation and increased positivity in older rather than younger adults. This paper aims to contribute to the empirical base of studies on the role of affect in cognition. We report a new dataset of valence (positivity) ratings to 3,600 English words collected from North American and British English-speaking younger (below 65 years of age) and older adults (65 years of age and older) during the COVID-19 pandemic. This dataset represents a broad range of valence and a rich selection of semantic categories. Our analyses of the new data pitted against comparable pre-pandemic (2013) data from younger counterparts reveal differences in the overall distribution of valence related both to age and the psychological fallout of the pandemic. Thus, we found at the group level that older participants produced higher valence ratings overall than their younger counterparts before and especially during the pandemic. Moreover, valence ratings saw a super-linear increase after the age of 65. Together, these findings provide new evidence for emotion regulation throughout adulthood, including a novel demonstration of greater emotional resilience in older adults to the stressors of the pandemic.

Emotional-Health-Oriented Urban Design: A Novel Collaborative Deep Learning Framework for Real-Time Landscape Assessment by Integrating Facial Expression Recognition and Pixel-Level Semantic Segmentation.

Emotional responses are significant for understanding public perceptions of urban green space (UGS) and can be used to inform proposals for optimal urban design strategies to enhance public emotional health in the times of COVID-19. However, most empirical studies fail to consider emotion-oriented landscape assessments under dynamic perspectives despite the fact that individually observed sceneries alter with angle. To close this gap, a real-time sentimental-based landscape assessment framework is developed, integrating facial expression recognition with semantic segmentation of changing landscapes. Furthermore, a case study using panoramic videos converted from Google Street View images to simulate changing scenes was used to test the viability of this framework, resulting in five million big data points. The result of this study shows that through the collaboration of deep learning algorithms, finer visual variables were classified, subtle emotional responses were tracked, and better regression results for valence and arousal were obtained. Among all the predictors, the proportion of grass was the most significant predictor for emotional perception. The proposed framework is adaptable and human-centric, and it enables the instantaneous emotional perception of the built environment by the general public as a feedback survey tool to aid urban planners in creating UGS that promote emotional well-being.

Climate change, vaccines, GMO: The N400 effect as a marker of attitudes toward scientific issues.

While the psychological predictors of antiscience beliefs have been extensively studied, neural underpinnings of the antiscience beliefs have received relatively little interest. The aim of the current study is to investigate whether attitudes towards the scientific issues are reflected in the N400 potential. Thirty-one individuals were asked to judge whether six different issues presented as primes (vaccines, medicines, nuclear energy, solar energy, genetically-modified organisms (GMO), natural farming) are well-described by ten positive and ten negative target words. EEG was recorded during the task. Furthermore, participants were asked to rate their own expertise in each of the six topics. Both positive and negative target words related to GMO elicited larger N400, than targets associated with vaccines and natural farming. The results of the current study show that N400 may be an indicator of the ambiguous attitude toward scientific issues.

COVID-19 Semantic Pneumonia Segmentation and Classification Using Artificial Intelligence.

Coronavirus 2019 (COVID-19) has become a pandemic. The seriousness of COVID-19 can be realized from the number of victims worldwide and large number of deaths. This paper presents an efficient deep semantic segmentation network (DeepLabv3Plus). Initially, the dynamic adaptive histogram equalization is utilized to enhance the images. Data augmentation techniques are then used to augment the enhanced images. The second stage builds a custom convolutional neural network model using several pretrained ImageNet models and compares them to repeatedly trim the best-performing models to reduce complexity and improve memory efficiency. Several experiments were done using different techniques and parameters. Furthermore, the proposed model achieved an average accuracy of 99.6% and an area under the curve of 0.996 in the COVID-19 detection. This paper will discuss how to train a customized smart convolutional neural network using various parameters on a set of chest X-rays with an accuracy of 99.6%.

Tracking mutational semantics of SARS-CoV-2 genomes.

Natural language processing (NLP) algorithms process linguistic data in order to discover the associated word semantics and develop models that can describe or even predict the latent meanings of the data. The applications of NLP become multi-fold while dealing with dynamic or temporally evolving datasets (e.g., historical literature). Biological datasets of genome-sequences are interesting since they are sequential as well as dynamic. Here we describe how SARS-CoV-2 genomes and mutations thereof can be processed using fundamental algorithms in NLP to reveal the characteristics and evolution of the virus. We demonstrate applicability of NLP in not only probing the temporal mutational signatures through dynamic topic modelling, but also in tracing the mutation-associations through tracing of semantic drift in genomic mutation records. Our approach also yields promising results in unfolding the mutational relevance to patient health status, thereby identifying putative signatures linked to known/highly speculated mutations of concern.

Deformable attention (DANet) for semantic image segmentation.

Deep learning based medical image segmentation is currently a widely researched topic. Attention mechanism used with deep networks significantly benefit semantic segmen-tation tasks. The recent criss-cross-attention module captures global self-attention while remaining memory and time efficient. However, capturing attention from only the pertinent non-local locations can cardinally boost the accuracy of semantic segmentation networks. We propose a new Deformable Attention Network (DANet) that enables a more accurate contextual information computation in a similarly efficient way. Our novel technique is based on learning the deformation of the query, key and value attention feature maps in a continuous way. A deep segmentation network with this attention mechanism is able to capture attention from germane non-local locations. This boosts the segmentation performance of COVID-19 lesion segmentation compared to criss-cross attention within aU-Net. Our validation experiments show that the performance gain of the recursively applied deformable attention blocks comes from their ability to capture dynamic and precise (wider) attention context. DANet achieves Dice scores of 60.17% for COVID-19 lesions segmentation and improves the accuracy by 4.4% points compared to a baseline U-Net.