Epidemiological investigation of an outbreak of human rhinovirus in a primary school in northern shaanxi

Objective To analyze the epidemiological characteristics of a Human rhinovirus outbreak in a primary school in northern Shaanxi, and to provide scientific evidence for the prevention and control. Methods On - site epidemiological investigation of an unexplained febrile aggregated outbreak reported in a primary school in northern Shaanxi on May 22, 2020. Nasopharyngeal swabs were collected from typical cases, and nucleic acid testing was performed to test for SARS COV 2, and 16 respiratory pathogens. Results A total of 37 cases were reported, including 1 adult teacher and 36 students, with the overall incidence rate of 1.75%, a male and female ratio of 3:1, and the incidence age mainly concentrated in 6 to 12 years old. The cases were mainly concentrated in 3 first-grade classes and 7 second-grade classes on the same floor, and the first grade cases accounted for 75.68% of the total number of cases. There was a statistically significant difference in the incidence rate of the cases in the classes (χ2 = 49.29, P<0.01). The clinical features of the cases were mainly fever (body temperature between 37.3 and 38.8°C), sore throat, runny nose, nasal congestion and cough, and some of which were accompanied by diarrhea and vomiting, and other gastrointestinal symptoms. Of the 33 nasopharyngeal swabs detected by laboratory, 14 were positive for Rhinovirus, and the positive rate was 42.42%. Conclusion This aggregated outbreak is caused by Rhinovirus infection. Primary and secondary schools in northern Shaanxi should be alert for aggregated unexplained fever due to Rhinovirus outbreaks during the epidemic season of respiratory infectious diseases. © 2023, Editorial Department of Medical Pest Control. All rights reserved.

Clinical and laboratory features among severe COVID⁃19 patients with anxiety and depression symptoms

Objective: To investigate the incidence rates of anxiety and depression among the COVID-19 patients and their association with clinical features and laboratory variables. Methods: A total of 371 COVID-19 patients were recruited from Wuhan Leishenshan Hospital from Jan 20 to May 10, 2020. The anxiety and depression were assessed by using the Hosptial Anxiety and Depression Score (HAD), the Self-rating Anxiety Scale (SAS), and Self-rating Depression Scale (SDS). The clinical features and laboratory variables were collected through electronic medical record. Statistical analyses were used to investigate the influence factors associated with anxiety and depression. Results: Among the 371 COVID-19 patients, the frequency of anxiety measured by HAD or SAS was 22. 91% and 24. 26%, respectively. The frequency of depression based on HAD or SDS was 16. 17% and 9. 43%, respectively. There were more female unmarried individuals in the anxiety or depression group. Anxiety or depression scores were significantly inversely correlated with the time for nucleic acid test turning negative. D-dimer and interleukin-6 (IL-6) were significantly elevated in the individuals with anxiety and depression. Statistically significant downregulations of lymphocyte counts, hemoglobin, and creatinine were found in anxiety and depression group. There was a negative association between creatinine and anxiety or depression scores. One unit upregulation of IL-6 and downregula-tion of lymphocyte counts could increase the hazard odds ratio of anxiety or depression by 10. 7% and 68. 9%, respectively. Conclusion: The COVID-19 patients with anxiety or depression symptoms had several different clinical features and laboratory findings in comparison with the patients without, which could lead to a poor prognosis of this disease. Clinicians should pay more attention to these indicators for anxiety or depression. Targeted psychological interventions should be implemented to minimize the negative impact of the psychological burden and to improve the quality life and disease outcome. © 2023 Editorial Board of Medical Journal of Wuhan University. All rights reserved.

An Effective COVID-19 CT Image Denoising Method Based on a Deep Convolutional Neural Network

Background: Faced with the global threat posed by SARS-CoV-2 (COVID-19), low-dose computed tomography (LDCT), as the primary diagnostic tool, is often accompanied by high levels of noise. This can easily interfere with the radiologist's assessment. Convolutional neural networks (CNN), as a method of deep learning, have been shown to have excellent effects in image denoising. Objective: The objective of the study was to use modified convolutional neural network algorithm to train the denoising model. The purpose was to make the model extract the highlighted features of the lesion region better and ensure its effectiveness in removing noise from COVID-19 lung CT images, preserving more important detail information of the images and reducing the adverse effects of denoising. Methods: We propose a CNN-based deformable convolutional denoising neural network (DCDNet). By combining deformable convolution methods with residual learning on the basis of CNN structure, more image detail features are retained in CT image denoising. Results: According to the noise reduction evaluation index of PSNR, SSIM and RMSE, DCDNet shows excellent denoising performance for COVID-19 CT images. From the visual effect of denoising, DCDNet can effectively remove image noise and preserve more detailed features of lung lesions. Conclusion: The experimental results indicate that the DCDNet-trained model is more suitable for image denoising of COVID-19 than traditional image denoising algorithms under the same training set. © 2023 Bentham Science Publishers.

Allocating scarce resources in the presence of private information and heterogeneous favoritism

Motivated by the challenge of allocating scarce resources from the federal government to different states during the COVID-19 pandemic, this paper studies optimal schemes for allocating scarce resources to agents with private demand information under different favoritism structures. Through an investigation of a mechanism design model that aims to induce agents to report their demands truthfully, we find the following results. First, when the principal purely cares about social welfare and when the principal has sufficient resources to satisfy all agents' demands, we find that the optimal allocation scheme is efficient in the sense that it is identical to the optimal scheme for the "benchmark” case when favoritism differentials and information asymmetry are both absent. Second, when rationing is needed due to resource scarcity, we show that heterogeneity in "event-independent” favoritism across agents will cause the principal to allocate more resources to agents with larger favoritism and less resources to others, resulting in inefficient allocations. Third, when agents possess heterogeneous "event-specific” favoritism due to the existence of outside options, the resulting allocation may boost all agents' expected utilities, including those agents who do not have any outside option. Finally, we show that the "allocation distortion” caused by both information asymmetry and heterogeneous favoritism can be reduced when "positive externality” is present (i.e., allocating resources to one agent can benefit other agents). © 2023 Production and Operations Management Society.

Towards Remote Auscultation with Commodity Earphones

Virtual visits (a.k.a., telehealth) have been promoted in response to the COVID pandemic since early 2020. Despite its convenience, the current virtual visit practice barely relies on video observation and talking. The specialist, however, cannot accurately assess the patient's health condition by listening to acoustic cardiopulmonary signals emanating from the patient's heart with a stethoscope. In this poster, we explore the feasibility of remote auscultation in virtual visits settings by reusing the patient's earphones as a stethoscope. The proposed hardware-software system captures the minute heartbeats from the patient's ear canal. It then offloads these noisy cardiac signals to the pairing device (e.g., a smartphone or a laptop) to reconstruct fine-grained Phonocardiogram (PCG) signals. By listening to the reconstructed PCG signals, the specialist can easily assess the patient's health condition and make the most informed diagnosis. We describe the design challenges and explain our technical roadmap. © 2022 Owner/Author.

"Just a virus” or politicized virus? Global media reporting of China on COVID-19

This study examines how China was covered and framed in global media reporting during the early stage of the coronavirus pandemic. Relying on a global multilingual COVID-19 online news narratives dataset, we propose multidimensional indicators to assess cross-country and cross-period variations in media discourses on China throughout the year of 2020. We derive and assess two hypotheses to explore factors accounting for the variations. The ideology-conflict hypothesis argues that the ideology distance from China determines the media attention and framing toward China in terms of COVID-19 reporting, while the crisis-mitigation hypothesis emphasizes that the domestic pandemic situation is associated with media discourses on China. Empirical analysis based on data compiled from various sources finds no evidence for the ideology-conflict hypothesis and moderate support for the crisis-mitigation hypothesis. Changes in the coronavirus situation and policy reactions are associated with changes in media coverage of China and the use of politicized terms over time. We conclude by discussing the implications of using online media data to understand the COVID-19 infodemic and its contribution to the emerging field of computational sociology. © 2022 Taylor & Francis Group, LLC.

Original Article The state of telehealth: 2 years into the COVID-19 pandemic-back to business as usual?

Introduction: Telemedicine (TM) was underutilized prior to the COVID-19 pandemic presumably due to nonstandardized reimbursement routes and a perceived lack of need. Early experience with the pandemic necessitated this form of medical care, although durability of consistent delivery remains in question. We quantify the utilization patterns of TM over the past 2 years over multiple waves of the pandemic across various service lines in a large rural health system. Materials: Data of TM utilization were prospectively collected between March 2020-January 2022. Rates of adoption among the various surgical and non-surgical services disciplines were compared. Subgroup analyses between different surgical subspecialties and within the urologic subspecialties was performed. Results: 3.5 million visits were recorded;3.14 million (90%) on-site and 349,989 (10%) TM;254,919 (73%) video-assisted and 95,070 (27%) were telephonic. Throughout the pandemic, non-surgical services utilized TM to a greater extent than surgical services (mean% 12 vs 6). Significant variation in the utilization among surgical services was reported, with Urology representing a high utilizer (15%);Among Urologic subspecialties utilization, Endourology (28%) was highest and Pediatric Urology (5%) was lowest. Following an initial spike in TM utilization during the pandemic, rates have declined and plateaued at 5-7% of all visits over the past 6-months. Conclusion: TM utilization in this large health system has remained under 10% following the initial surge in 2020. Non-surgical services preferentially use TM more than surgical domains. Certain subspecialties utilize TM more than others, possible due to patient population, practice patterns and medical conditions. Barriers to adoption are essential to determine the relatively low volume of use across this health system.

Influence of different air distribution on ventilation effectiveness in negative pressure hospital wards

Hospital ward is one of non-negligible potential places to occur cross-infection among patients and health workers. Air-borne transmission was regarded as the main infection route of the SARS-CoV-2. Preventing the air-borne transmission should be a significant measure, which could effectively mitigate the risk of the virus infection. Based on those consideration, in this study, the influence of different types of air distribution on ventilation effectiveness was modeled through Computational Fluid Dynamics (CFD) simulations. Several typical negative pressure wards same as the ward in Wuhan Thunder God Mountain hospital and conformed to the Chinese National Health Commission (NHC) guidelines were modelled. We simulated the influence of different locations of air supply inlets, analysed the influence of the buffer door and compared the contaminant concentration on different entry route for health workers. The results show that the air distribution required by NHC guidelines could retain a directional airflow from the bed-zone to the toilet, which also has a better accessibility of supply air, and health workers are safer to avoid standing closed to the air exhaust outlet in the downstream area of pollutants during ward rounds. © The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (http://creativecommons.org/licenses/by/4.0/)

A prospective trial of177Lu-EB-PSMA-617 Radioligand Therapy in patients with metastatic castrationresistantprostatecancer

Aim/Introduction: This study is designed to assess the therapeutic response and safety of the approximately 2.0 GBq177Lu-EB-PSMA-617 radioligand therapy (RLT) in patients with metastatic castrationresistant prostate cancer (mCRPC). Material(s) and Method(s): With institutional review board approval and informed consent, 45 patients with mCRPC underwent screening68Ga-PSMA and 18F-FDG PET/CT to confirm high PSMA expression. 30 patients were eligible for treatment and they received up to 3 cycles of intravenous177Lu- EB-PSMA-617 RLT with a mean dosage of 2.0 GBq (range: 1.8-2.2 GBq)/cycle, at 8-10 weekly intervals. The primary endpoint was PSA response according to Prostate Cancer Clinical Trial Working Group criteria and toxicity according to CTCAE. Result(s): After the 1st cycle of therapy, decline in the PSA value from baseline was observed in 21 (70.0%) patients. Of them, 10 (33.3%) patients reached PSA decline of 50% or more. Then, 22 patients accepted 2nd cycle of therapy, 15 (68.2%) patients showed a PSA value decline from baseline and 12 (54.5%) patients revealed PSA decline of 50% or more. Due to disease progression and the COVID-19 pandemic, however, only 11 patients accepted 3rd cycles of177Lu-EB-PSMA-617 RLT as schedule. Of them, 8 (72.7%) demonstrated PSA decline, and 5 (45.5%) patients achieved PSA decline of 50% or more. Among the 30 patients with median 2-cycle treatments, 13 (43.3%) patients achieved PR, 8 (26.7%) patients showed SD and 9 (30.0%) patients exhibited PD, and PSA progression occurred in 30 patients with median PSA progression-free survival of 3.2 months (95% CI 1.8-4.9). The most common toxic effects related to177Lu-EB-PSMA-617 were grade 1 dry mouth recorded in 12 (40.0%) patients, grade 1 and 2 transient fatigue in 11 (36.7%) patients. Grade 3 anemia, leucopenia or thrombocytopenia occurred in 9 (30.0%) patients and there were no G4 myelosuppression events. Conclusion(s): Our findings show that RLT with approximately 2.0 GBq177Lu-EB-PSMA-617 has good responses and acceptable toxic effects in men with mCRPC.

Reviving the economy while saving lives: a deep reinforcement learning approach for smart POI reopening

With the gradual improvements in COVID-19 metrics and the accelerated immunization progress, countries around the world have began to focus on reviving the economy while continuously strengthening epidemic control. POInt-of-Interest (POI) reopening, as a necessity for restoring human mobilities, has become a crucial step to recouple economic recovery and public health management. In contrast to the lock-down policy, POI reopening demands a dynamic trade-off between epidemic interventions and economic costs. In the urban scenario, there exist three key challenges in developing effective POI reopening strategies as follows. (1) During the POI reopening process, there are multiple urban factors affecting the epidemic transmission, which are difficult to simultaneously incorporate and balance in a single reopening strategy;(2) the effects of POI reopening on both economic recovery and epidemic control are long-term, which are hard to capture by static models;and (3) the dual objectives of minimizing infections and maintaining POIs' visits are conflicting, making it difficult to achieve a flexible and scalable trade-off. To tackle the above challenges, we propose Reopener, a deep reinforcement learning (RL) framework for smart POI reopening. First, we utilize a bipartite graph neural network to automatically encode all urban factors that would affect the epidemic prevention and POI visit restriction. Second, we employ a RL-based deep policy network to enable flexible updates in restrictions on POIs along with the trend of epidemic. Third, we design a novel reward function to guide the RL agent to learn smartly, thus comprehensively trading off infections and visit sustainability of POIs. Extensive experimental results demonstrate that Reopener outperforms all baseline methods with remarkable improvements, by reducing the overall economic cost by at least 6.42%. Reopener can effectively suppress infections and support a phase-based POI reopening process, which provides valuable insights for strategy design in post-COVID-19 economic recovery. © 2022 Owner/Author.

The state of telehealth: 2 years into the COVID-19 pandemic - back to business as usual?

Introduction: Telemedicine (TM) was underutilized prior to the COVID-19 pandemic presumably due to non-standardized reimbursement routes and a perceived lack of need. Early experience with the pandemic necessitated this form of medical care, although durability of consistent delivery remains in question. We quantify the utilization patterns of TM over the past 2 years over multiple waves of the pandemic across various service lines in a large rural health system. Materials: Data of TM utilization were prospectively collected between March 2020-January 2022. Rates of adoption among the various surgical and non-surgical services disciplines were compared. Subgroup analyses between different surgical subspecialties and within the urologic subspecialties was performed. Results: 3.5 million visits were recorded;3.14 million (90%) on-site and 349,989 (10%) TM;254,919 (73%) video-assisted and 95,070 (27%) were telephonic. Throughout the pandemic, non-surgical services utilized TM to a greater extent than surgical services (mean% 12 vs 6). Significant variation in the utilization among surgical services was reported, with Urology representing a high utilizer (15%);Among Urologic subspecialties utilization, Endourology (28%) was highest and Pediatric Urology (5%) was lowest. Following an initial spike in TM utilization during the pandemic, rates have declined and plateaued at 5-7% of all visits over the past 6-months. Conclusion: TM utilization in this large health system has remained under 10% following the initial surge in 2020. Non-surgical services preferentially use TM more than surgical domains. Certain subspecialties utilize TM more than others, possible due to patient population, practice patterns and medical conditions. Barriers to adoption are essential to determine the relatively low volume of use across this health system.

[Effects of vaccines on the viral negative conversion of children with COVID-19].

Objective: To explore the effect of vaccination on viral negative conversion of children with COVID-19. Methods: A retrospective cohort study was conducted. A cohort of 189 children aged 3-14 years with COVID-19 admitted to Renji Hospital (South branch) of Shanghai Jiao Tong University School of Medicine from April 7th to May 19th 2022 was enrolled in the study. According to the vaccination status, the infected children were divided into an unvaccinated group and a vaccinated group. Age, gender, severity, clinical manifestations, and laboratory tests, etc. were compared between groups, by rank sum test or chi-square test. The effects of vaccination on viral negative conversion were analyzed by a Cox mixed-effects regression model. Additionally, a questionnaire survey was conducted among the parents of unvaccinated children to analyze the reasons for not being vaccinated. Results: A total of 189 children aged 3-14 years were enrolled, including 95 males (50.3%) and 94 females (49.7%), aged 5.7 (4.1,8.6) years. There were 117 cases (61.9%) in the unvaccinated group and 72 cases (38.1%) in the vaccinated group. The age of the vaccinated group was higher than that of the unvaccinated group (8.8 (6.8, 10.6) vs. 4.5 (3.6, 5.9) years, Z=9.45, P<0.001). No significant differences were found in clinical manifestations, disease severity, and laboratory results between groups (all P>0.05), except for the occurrence rate of cough symptoms, which was significantly higher in the vaccinated group than in the non-vaccinated group (68.1% (49/72) vs. 50.4% (59/117),χ2=5.67, P=0.017). The Kaplan-Meier survival curve and Cox mixed-effects regression model showed that the time to the viral negative conversion was significantly shorter in the vaccinated group compared with the unvaccinated group (8 (7, 10) vs. 11 (9, 12) d, Z=5.20, P<0.001; adjusted HR=2.19 (95%CI 1.62-2.97)). For questionnaire survey on the reasons for not receiving a vaccination, 115 questionnaires were distributed and 112 valid questionnaires (97.4%) were collected. The main reasons for not being vaccinated were that parents thought that their children were not in the range of appropriate age for vaccination (51 cases, 45.5%) and children were in special physical conditions (47 cases, 42.0%). Conclusion: Vaccination can effectively shorten the negative conversion time of children with COVID-19 and targeted programs should be developed to increase eligible children's vaccination rate for SARS-CoV-2 vaccination.

Stacking based prediction of COVID-19 Pandemic by integrating infectious disease dynamics model and traditional machine learning

Accurate prediction of 2019 novel coronavirus diseases (COVID-19) has been playing an important role in making more effective prevention and control policies during pandemic crises. The aim of this paper was to develop an innovative stacking based prediction of COVID-19 pandemic cumulative confirmed cases (StackCPPred) by integrating infectious disease dynamics model and traditional machine learning. Based on population migration characteristics, five feature indicators were first extracted from the population flow data in the early stage of this epidemic, which were collected from the National Health Commission of the People's Republic of China. Then, stacking based ensemble learning (SEL) model was established for COVID-19 prediction using traditional machine learning, including the multiple linear regression (MLR) and the tree regression model (XGBoost and LightGBM). By introducing the variable "death state", an improved Susceptible-Infected-Recovered (ISIR) model was established. Finally, a hybrid model, StackCPPred was proposed by incorporating the ISIR model outputs and the five feature indicators into the SEL model. Real data on population movements and daily cumulative number of newly confirmed cases across the country from January 23 to February 6 were used to validate our model. The results positively proved that the proposed StackCPPred model outperformed the existing models for COVID-19 prediction, as quantified by the root mean square error (RMSE), the root mean square logarithmic error (RMSLE) and the coefficient of determination (R2) (g1/41841 persons, g1/40.1 and >0.9, respectively). Furthermore, this study confirms the validity and usefulness of the StackCPPred model for COVID-19 prediction. © 2022 ACM.

On Understanding the Influence of Controllable Factors with a Feature Attribution Algorithm: a Medical Case Study

Feature attribution XAI algorithms enable their users to gain insight into the underlying patterns of large datasets through their feature importance calculation. Existing feature attribution algorithms treat all features in a dataset homogeneously, which may lead to misinterpretation of consequences of changing feature values. In this work, we consider partitioning features into controllable and uncontrollable parts and propose the Controllable fActor Feature Attribution (CAFA) approach to compute the relative importance of controllable features. We carried out experiments applying CAFA to two existing datasets and our own COVID-19 non-pharmaceutical control measures dataset. Experimental results show that with CAFA, we are able to exclude influences from uncontrollable features in our explanation while keeping the full dataset for prediction. © 2022 IEEE.

Precise Mobility Intervention for Epidemic Control Using Unobservable Information via Deep Reinforcement Learning

To control the outbreak of COVID-19, efficient individual mobility intervention for EPidemic Control (EPC) strategies are of great importance, which cut off the contact among people at epidemic risks and reduce infections by intervening the mobility of individuals. Reinforcement Learning (RL) is powerful for decision making, however, there are two major challenges in developing an RL-based EPC strategy: (1) the unobservable information about asymptomatic infections in the incubation period makes it difficult for RL's decision-making, and (2) the delayed rewards for RL causes the deficiency of RL learning. Since the results of EPC are reflected in both daily infections (including unobservable asymptomatic infections) and long-term cumulative cases of COVID-19, it is quite daunting to design an RL model for precise mobility intervention. In this paper, we propose a Variational hiErarcHICal reinforcement Learning method for Epidemic control via individual-level mobility intervention, namely Vehicle. To tackle the above challenges, Vehicle first exploits an information rebuilding module that consists of a contact-risk bipartite graph neural network and a variational LSTM to restore the unobservable information. The contact-risk bipartite graph neural network estimates the possibility of an individual being an asymptomatic infection and the risk of this individual spreading the epidemic, as the current state of RL. Then, the Variational LSTM further encodes the state sequence to model the latency of epidemic spreading caused by unobservable asymptomatic infections. Finally, a Hierarchical Reinforcement Learning framework is employed to train Vehicle, which contains dual-level agents to solve the delayed reward problem. Extensive experimental results demonstrate that Vehicle can effectively control the spread of the epidemic. Vehicle outperforms the state-of-the-art baseline methods with remarkably high-precision mobility interventions on both symptomatic and asymptomatic infections. © 2022 Owner/Author.

Redirection of anti-virus immunity towards anti-tumor immunity using nanoparticle-induced immune tolerance for oncolytic adenovirus therapy

Recent clinical observations that some coronavirus infections induced complete remissions in lymphoma patients emphasized again the potential of cancer virotherapy. Infection of cancer cells with oncolytic viruses reshapes the tumor microenvironment by activating anti-viral and anti-tumor immunity. A phase 1 clinical trial using oncolytic adenovirus Delta-24-RGD (DNX-2401) to treat recurrent malignant gliomas demonstrated activation of CD8+ T-cells and significant clinical benefits for a subset of patients. However, both anti-virus and anti-tumor immune responses are contingent on the activation of respective clones of CD8+ T-cells, which compete for clonal expansion. Thus, overexpansion of T-cells against viral antigens reduces the frequency of subdominant clones against tumor antigens. We hypothesized that inducing immune tolerance for viral antigens will decrease anti-viral immunity and in turn derepress anti-tumor immunity, resulting in enhanced efficacy of cancer virotherapy. In this work, we used nanoparticles encapsulating adenoviral antigens E1A, E1B and hexon that distributed to liver resident macrophages (P<0.0001) and induced peripheral immune tolerance. Functional experiments to restimulate immune cells with viral or tumor antigens showed that injection of nanoparticles induced virus-specific immune tolerance and redirected the focus of the immune response towards tumor peptides as measured by interferon-gamma secretion (P<0.0001). Co-culture experiments also showed increased activation of immune cells against fixed tumor cells after nanoparticle treatment (P<0.0001). Reduction of virus-specific T-cells and concurrent expansion of tumor-specific T-cell clones were further confirmed with E1A or OVA tetramers (P<0.05). Flow cytometry analysis suggested increased anti-tumor responses were due to differences in T-cell clones and not due to other immune populations including natural killer cells or myeloid-derived suppressor cells (P=0.3). Importantly, virotherapy in combination with nanoparticle-induced immune tolerance towards viral antigens in tumor-bearing mice increased the overall survival and doubled the percentage of long-term survivors compared to virus treatment alone. Our data should propel the development of a future clinical trial aiming to maximize the potential of anti-tumor immunity during cancer virotherapies.

Genera of phytopathogenic fungi: GOPHY 4.

This paper is the fourth contribution in the Genera of Phytopathogenic Fungi (GOPHY) series. The series provides morphological descriptions and information about the pathology, distribution, hosts and disease symptoms, as well as DNA barcodes for the taxa covered. Moreover, 12 whole-genome sequences for the type or new species in the treated genera are provided. The fourth paper in the GOPHY series covers 19 genera of phytopathogenic fungi and their relatives, including Ascochyta, Cadophora, Celoporthe, Cercospora, Coleophoma, Cytospora, Dendrostoma, Didymella, Endothia, Heterophaeomoniella, Leptosphaerulina, Melampsora, Nigrospora, Pezicula, Phaeomoniella, Pseudocercospora, Pteridopassalora, Zymoseptoria, and one genus of oomycetes, Phytophthora. This study includes two new genera, 30 new species, five new combinations, and 43 typifications of older names. Taxonomic novelties: New genera: Heterophaeomoniella L. Mostert, C.F.J. Spies, Halleen & Gramaje, Pteridopassalora C. Nakash. & Crous; New species: Ascochyta flava Qian Chen & L. Cai, Cadophora domestica L. Mostert, R. van der Merwe, Halleen & Gramaje, Cadophora rotunda L. Mostert, R. van der Merwe, Halleen & Gramaje, Cadophora vinacea J.R. Úrbez-Torres, D.T. O'Gorman & Gramaje, Cadophora vivarii L. Mostert, Havenga, Halleen & Gramaje, Celoporthe foliorum H. Suzuki, Marinc. & M.J. Wingf., Cercospora alyssopsidis M. Bakhshi, Zare & Crous, Dendrostoma elaeocarpi C.M. Tian & Q. Yang, Didymella chlamydospora Qian Chen & L. Cai, Didymella gei Qian Chen & L. Cai, Didymella ligulariae Qian Chen & L. Cai, Didymella qilianensis Qian Chen & L. Cai, Didymella uniseptata Qian Chen & L. Cai, Endothia cerciana W. Wang. & S.F. Chen, Leptosphaerulina miscanthi Qian Chen & L. Cai, Nigrospora covidalis M. Raza, Qian Chen & L. Cai, Nigrospora globospora M. Raza, Qian Chen & L. Cai, Nigrospora philosophiae-doctoris M. Raza, Qian Chen & L. Cai, Phytophthora transitoria I. Milenkovic, T. Májek & T. Jung, Phytophthora panamensis T. Jung, Y. Balci, K. Broders & I. Milenkovic, Phytophthora variabilis T. Jung, M. Horta Jung & I. Milenkovic, Pseudocercospora delonicicola C. Nakash., L. Suhaizan & I. Nurul Faziha, Pseudocercospora farfugii C. Nakash., I. Araki, & Ai Ito, Pseudocercospora hardenbergiae Crous & C. Nakash., Pseudocercospora kenyirana C. Nakash., L. Suhaizan & I. Nurul Faziha, Pseudocercospora perrottetiae Crous, C. Nakash. & C.Y. Chen, Pseudocercospora platyceriicola C. Nakash., Y. Hatt, L. Suhaizan & I. Nurul Faziha, Pseudocercospora stemonicola C. Nakash., Y. Hatt., L. Suhaizan & I. Nurul Faziha, Pseudocercospora terengganuensis C. Nakash., Y. Hatt., L. Suhaizan & I. Nurul Faziha, Pseudocercospora xenopunicae Crous & C. Nakash.; New combinations: Heterophaeomoniella pinifoliorum (Hyang B. Lee et al.) L. Mostert, C.F.J. Spies, Halleen & Gramaje, Pseudocercospora pruni-grayanae (Sawada) C. Nakash. & Motohashi., Pseudocercospora togashiana (K. Ito & Tak. Kobay.) C. Nakash. & Tak. Kobay., Pteridopassalora nephrolepidicola (Crous & R.G. Shivas) C. Nakash. & Crous, Pteridopassalora lygodii (Goh & W.H. Hsieh) C. Nakash. & Crous; Typification: Epitypification: Botrytis infestans Mont., Cercospora abeliae Katsuki, Cercospora ceratoniae Pat. & Trab., Cercospora cladrastidis Jacz., Cercospora cryptomeriicola Sawada, Cercospora dalbergiae S.H. Sun, Cercospora ebulicola W. Yamam., Cercospora formosana W. Yamam., Cercospora fukuii W. Yamam., Cercospora glochidionis Sawada, Cercospora ixorana J.M. Yen & Lim, Cercospora liquidambaricola J.M. Yen, Cercospora pancratii Ellis & Everh., Cercospora pini-densiflorae Hori & Nambu, Cercospora profusa Syd. & P. Syd., Cercospora pyracanthae Katsuki, Cercospora horiana Togashi & Katsuki, Cercospora tabernaemontanae Syd. & P. Syd., Cercospora trinidadensis F. Stevens & Solheim, Melampsora laricis-urbanianae Tak. Matsumoto, Melampsora salicis-cupularis Wang, Phaeoisariopsis pruni-grayanae Sawada, Pseudocercospora angiopteridis Goh & W.H. Hsieh, Pseudocercospora basitruncata Crous, Pseudocercospora boehmeriigena U. Braun, Pseudocercospora coprosmae U. Braun & C.F. Hill, Pseudocercospora cratevicola C. Nakash. & U. Braun, Pseudocercospora cymbidiicola U. Braun & C.F. Hill, Pseudocercospora dodonaeae Boesew., Pseudocercospora euphorbiacearum U. Braun, Pseudocercospora lygodii Goh & W.H. Hsieh, Pseudocercospora metrosideri U. Braun, Pseudocercospora paraexosporioides C. Nakash. & U. Braun, Pseudocercospora symploci Katsuki & Tak. Kobay. ex U. Braun & Crous, Septogloeum punctatum Wakef.; Neotypification: Cercospora aleuritis I. Miyake; Lectotypification: Cercospora dalbergiae S.H. Sun, Cercospora formosana W. Yamam., Cercospora fukuii W. Yamam., Cercospora glochidionis Sawada, Cercospora profusa Syd. & P. Syd., Melampsora laricis-urbanianae Tak. Matsumoto, Phaeoisariopsis pruni-grayanae Sawada, Pseudocercospora symploci Katsuki & Tak. Kobay. ex U. Braun & Crous. Citation: Chen Q, Bakhshi M, Balci Y, Broders KD, Cheewangkoon R, Chen SF, Fan XL, Gramaje D, Halleen F, Horta Jung M, Jiang N, Jung T, Májek T, Marincowitz S, Milenkovic T, Mostert L, Nakashima C, Nurul Faziha I, Pan M, Raza M, Scanu B, Spies CFJ, Suhaizan L, Suzuki H, Tian CM, Tomsovský M, Úrbez-Torres JR, Wang W, Wingfield BD, Wingfield MJ, Yang Q, Yang X, Zare R, Zhao P, Groenewald JZ, Cai L, Crous PW (2022). Genera of phytopathogenic fungi: GOPHY 4. Studies in Mycology 101: 417-564. doi: 10.3114/sim.2022.101.06.

RetinaFaceMask: A Single Stage Face Mask Detector for Assisting Control of the COVID-19 Pandemic

Coronavirus 2019 has made a significant impact on the world. One effective strategy to prevent infection for people is to wear masks in public places. Certain public service providers require clients to use their services only if they properly wear masks. There are, however, only a few research studies on automatic face mask detection. In this paper, we proposed RetinaFaceMask, the first high-performance single stage face mask detector. First, to solve the issue that existing studies did not distinguish between correct and incorrect mask wearing states, we established a new dataset containing these annotations. Second, we proposed a context attention module to focus on learning discriminated features associated with face mask wearing states. Third, we transferred the knowledge from the face detection task, inspired by how humans improve their ability via learning from similar tasks. Ablation studies showed the advantages of the proposed model. Experimental findings on both the public and new datasets demonstrated the state-of-the-art performance of our model. © 2021 IEEE.

ExMed: An AI Tool for Experimenting Explainable AI Techniques on Medical Data Analytics

Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) algorithms have been widely discussed by the Explainable AI (XAI) community but their application to wider domains are rare, potentially due to the lack of easy-to-use tools built around these methods. In this paper, we present ExMed, a tool that enables XAI data analytics for domain experts without requiring explicit programming skills. It supports data analytics with multiple feature attribution algorithms for explaining machine learning classifications and regressions. We illustrate its domain of applications on two real world medical case studies, with the first one analysing COVID-19 control measure effectiveness and the second one estimating lung cancer patient life expectancy from the artificial Simulacrum health dataset. We conclude that ExMed can provide researchers and domain experts with a tool that both concatenates flexibility and transferability of medical sub-domains and reveal deep insights from data. © 2021 IEEE.