Semantic Segmentation of Gastric Polyps in Endoscopic Images Based on Convolutional Neural Networks and an Integrated Evaluation Approach.

Convolutional neural networks (CNNs) have received increased attention in endoscopic images due to their outstanding advantages. Clinically, some gastric polyps are related to gastric cancer, and accurate identification and timely removal are critical. CNN-based semantic segmentation can delineate each polyp region precisely, which is beneficial to endoscopists in the diagnosis and treatment of gastric polyps. At present, just a few studies have used CNN to automatically diagnose gastric polyps, and studies on their semantic segmentation are lacking. Therefore, we contribute pioneering research on gastric polyp segmentation in endoscopic images based on CNN. Seven classical semantic segmentation models, including U-Net, UNet++, DeepLabv3, DeepLabv3+, Pyramid Attention Network (PAN), LinkNet, and Muti-scale Attention Net (MA-Net), with the encoders of ResNet50, MobineNetV2, or EfficientNet-B1, are constructed and compared based on the collected dataset. The integrated evaluation approach to ascertaining the optimal CNN model combining both subjective considerations and objective information is proposed since the selection from several CNN models is difficult in a complex problem with conflicting multiple criteria. UNet++ with the MobineNet v2 encoder obtains the best scores in the proposed integrated evaluation method and is selected to build the automated polyp-segmentation system. This study discovered that the semantic segmentation model has a high clinical value in the diagnosis of gastric polyps, and the integrated evaluation approach can provide an impartial and objective tool for the selection of numerous models. Our study can further advance the development of endoscopic gastrointestinal disease identification techniques, and the proposed evaluation technique has implications for mathematical model-based selection methods for clinical technologies.

- Invited Review - Reproductive technologies needed for the generation of precise gene-edited pigs in the pathways from laboratory to farm.

Gene editing (GE) offers a new breeding technique (NBT) of sustainable value to animal agriculture. There are 3 GE working sites covering 5 feasible pathways to generate GE pigs along with the crucial intervals of GE/genotyping, microinjection/electroporation, induced pluripotent stem cells, somatic cell nuclear transfer, cryopreservation, and nonsurgical embryo transfer. The extension of NBT in the new era of pig breeding depends on the synergistic effect of GE and reproductive biotechnologies; the outcome relies not only on scientific due diligence and operational excellence but also on the feasibility of application on farms to improve sustainability.

Deep learning based radiomics for gastrointestinal cancer diagnosis and treatment: A minireview.

Gastrointestinal (GI) cancers are the major cause of cancer-related mortality globally. Medical imaging is an important auxiliary means for the diagnosis, assessment and prognostic prediction of GI cancers. Radiomics is an emerging and effective technology to decipher the encoded information within medical images, and traditional machine learning is the most commonly used tool. Recent advances in deep learning technology have further promoted the development of radiomics. In the field of GI cancer, although there are several surveys on radiomics, there is no specific review on the application of deep-learning-based radiomics (DLR). In this review, a search was conducted on Web of Science, PubMed, and Google Scholar with an emphasis on the application of DLR for GI cancers, including esophageal, gastric, liver, pancreatic, and colorectal cancers. Besides, the challenges and recommendations based on the findings of the review are comprehensively analyzed to advance DLR.

A review of epidemiology and public health control measures of COVID-19 variants in Hong Kong, December 2020 to June 2021.

Background: The emergence of coronavirus disease 2019 (COVID-19) variants posed considerable threats to the global public health. We reviewed the epidemiology of variant cases and control measures implemented in Hong Kong. Methods: The epidemiological characteristics and the temporal trend of the COVID-19 variant cases and local clusters in Hong Kong, and the corresponding public health control measures were reviewed. Results: Between December 2020 and June 2021, 393 variant cases were reported, including 153, 59 and 79 cases of Alpha, Beta and Delta variants with no Gamma variant. The vast majority (378, 96.2%) were imported cases. Since early June 2021, Delta variant had taken over Alpha as the dominant strain. Public health control measures, including risk-stratified quarantine and testing requirements for inbound travellers, banning of flights from extremely high-risk areas, enhanced contact tracing and quarantine, were implemented. Among the 3 clusters involving local transmissions, 2 were linked to imported cases while the source of the remaining one was unknown. Discussion: Amid the global surges of COVID-19 variants, Hong Kong had continued to limit and prevent the occurrence of community-wide outbreak. Ongoing control strategies should be constantly reviewed and adjusted in response to the global and local COVID-19 situation.

Activated macrophages of CD 163 gene edited pigs generated by direct cytoplasmic microinjection with CRISPR gRNA/Cas9 mRNA are resistant to PRRS virus assault.

Porcine reproductive and respiratory syndrome virus (PRRSV) infects placental and lung macrophages, causing a global epidemic with economic loss. Attempts to develop an effective vaccine to control the disease have not been effective. Currently, developing PRRSV disease-resistant pigs via a gene editing (GE) strategy to mutate the PRRSV receptor or to delete the binding domain on the macrophage appears promising. In this study, we used the strategy of Edinburg University to construct two guide RNAs (gRNAs) located on the proximal front and post sites of exon 7. Directive microinjection of two gRNAs and Cas9 mRNA into the cytoplasm of pronuclear zygotes efficiently generated four piglets confirmed as CD163 knockout (KO) and/or CD163 exon 7 deleted (CD163ΔE7). In four GE piglets, three pigs carried two chromosome CD163 KO or ΔE7. Peripheral blood mononuclear cells (PBMCs) from three GE and wild-type (WT) pigs were activated into macrophages for in vitro transfection. The results showed that the activated macrophages from all GE pigs were significantly more viable than those from WT pig. Current results suggest that we have successfully generated PRRSV-resistant pigs, although in vivo challenge is needed to validate that the pigs are PRRSV resistant.

Automatic detection of multiple types of pneumonia: Open dataset and a multi-scale attention network.

The quick and precise identification of COVID-19 pneumonia, non-COVID-19 viral pneumonia, bacterial pneumonia, mycoplasma pneumonia, and normal lung on chest CT images play a crucial role in timely quarantine and medical treatment. However, manual identification is subject to potential misinterpretations and time-consumption issues owing the visual similarities of pneumonia lesions. In this study, we propose a novel multi-scale attention network (MSANet) based on a bag of advanced deep learning techniques for the automatic classification of COVID-19 and multiple types of pneumonia. The proposed method can automatically pay attention to discriminative information and multi-scale features of pneumonia lesions for better classification. The experimental results show that the proposed MSANet can achieve an overall precision of 97.31%, recall of 96.18%, F1-score of 96.71%, accuracy of 97.46%, and macro-average area under the receiver operating characteristic curve (AUC) of 0.9981 to distinguish between multiple classes of pneumonia. These promising results indicate that the proposed method can significantly assist physicians and radiologists in medical diagnosis. The dataset is publicly available at https://doi.org/10.17632/rf8x3wp6ss.1.

The epidemiology of COVID-19 cases and the successful containment strategy in Hong Kong-January to May 2020.

BACKGROUND: Hong Kong, a Special Administrative Region of China, recorded its first confirmed coronavirus disease 2019 (COVID-19) case on 23 January 2020. We reviewed the case epidemiology and the various public health measures implemented from January to May 2020. METHODS: The epidemiological and clinical characteristics of the cases recorded in different phases of the epidemic were described and compared, and the effectiveness of the public health measures implemented were reviewed using the changes in the daily number of confirmed cases and the interval from symptom onset to hospital admission. RESULTS: Between January and May 2020, 1084 confirmed COVID-19 cases were reported, about 70% of which had a history of travel during the incubation period. The case fatality ratio was 0.4%. The local epidemic progressed through four phases: (1) preparedness and imported infection from mainland China, (2) local transmission, (3) imported infection from overseas countries associated with local transmission, and (4) controlled imported infection with limited local transmission, with an eventual reduction of the daily case number and minimization of the onset-to-admission interval. Various public health measures, including enhanced surveillance, border control, and social distancing, were introduced in phases in response to the prevailing local and global situations. DISCUSSION: The overall containment strategy in Hong Kong led to a stabilization of the number of cases and the absence of a community-wide outbreak during the 4.5 m after the first case was reported. This strategy of containment might serve as an example for future planning of preparedness and response against novel infectious agents.

A superspreading event involving a cluster of 14 coronavirus disease 2019 (COVID-19) infections from a family gathering in Hong Kong Special Administrative Region SAR (China).

OBJECTIVE: An outbreak of coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was first reported in Wuhan, China, in December 2019, with subsequent spread around the world. Hong Kong Special Administrative Region SAR (China) recorded its first confirmed cases on 23 January 2020. In this report, we describe a family cluster of 12 confirmed cases, with two additional confirmed cases from secondary transmission. METHODS: We reported the epidemiological, clinical and laboratory findings of the family cluster, as well as the public health measures instituted. RESULTS: All 12 confirmed COVID-19 cases were among the 19 attendees of a three-hour Chinese New Year family dinner consisting of hotpot and barbecue dishes. Environmental sampling of the gathering venue was negative. Two additional confirmed cases, who were co-workers of two confirmed cases, were later identified, indicating secondary transmission. Contact tracing, quarantine and environmental disinfection were instituted to contain further spread. DISCUSSION: Our findings were highly suggestive of a superspreading event during the family gathering. The source was likely one of the cases during the pre-symptomatic phase. The event attested to the high infectivity of SARS-CoV-2 through human-to-human transmission from social activities and argued for the necessity of social distancing in curtailing the disease spread.

Investigation and control of a measles outbreak at the Hong Kong International Airport, 2019

Introduction@#Hong Kong SAR (China) achieved measles elimination status in 2016, and the incidence of measles infection had been low over the past few years. However, the Centre for Health Protection (CHP) at the Department of Health was notified on 22 March 2019 of an outbreak of three cases of measles infection among workers at the Hong Kong International Airport (HKIA).@*Methods@#We reviewed notifications of measles received by CHP from 1 January to 17 May 2019. We defined a confirmed case of measles as having laboratory evidence of measles infection. All confirmed cases among airport workers or those with epidemiological information suggesting they had been infected by contact with airport workers were included in the review. We described the epidemiological features and reviewed the control measures against the outbreak.@*Results@#We identified 33 cases, 29 of which were among airport workers. They comprised 22 men and 11 women, aged 20–49 years (median 25 years). The majority of people with confirmed measles presented with fever and rash. All required hospitalization. None developed complications. Control measures, including enhanced environmental hygiene and improved ventilation at HKIA and vaccinations for the airport community, were implemented.@*Discussion@#Early recognition of the outbreak and prompt control measures, especially targeted vaccination of the exposed population, effectively controlled the outbreak in just two weeks.

Border collision bifurcations, snap-back repellers, and chaos.

The normal form for codimension 1 border collision bifurcations of fixed points of discrete time piecewise smooth dynamical systems is considered in the unstable case. We show that in appropriate parameter regions there is a snap-back repeller immediately after the bifurcation, and hence that the bifurcation creates chaos. Although the chaotic solutions are repellers they may explain observations, and this is illustrated through an example.