HarDNet and Dual-Code Attention Mechanism based model for medical images segmentation

During the formation of medical images, they are easily disturbed by factors such as acquisition devices and tissue backgrounds, causing problems such as blurred image backgrounds and difficulty in differentiation. In this paper, we combine the HarDNet module and the multi-coding attention mechanism module to optimize the two stages of encoding and decoding to improve the model segmentation performance. In the encoding stage, the HarDNet module extracts medical image feature information to improve the segmentation network operation speed. In the decoding stage, the multi-coding attention module is used to extract both the position feature information and channel feature information of the image to improve the model segmentation effect. Finally, to improve the segmentation accuracy of small targets, the use of Cross Entropy and Dice combination function is proposed as the loss function of this algorithm. The algorithm has experimented on three different types of medical datasets, Kvasir-SEG, ISIC2018, and COVID-19CT. The values of JS were 0.7189, 0.7702, 0.9895, ACC were 0.8964, 0.9491, 0.9965, SENS were 0.7634, 0.8204, 0.9976, PRE were 0.9214, 0.9504, 0.9931. The experimental results showed that the model proposed in this paper achieved excellent segmentation results in all the above evaluation indexes, which can effectively assist doctors to diagnose related diseases quickly and improve the speed of diagnosis and patients’quality of life. Author

Love in the Time of Coronavirus: Five Poems

These five poems have been selected from Ho Fuk Yan's 2021 poetry anthology Love in the Time of Coronavirus. They were written in 2020, along with the development of the pandemic that started to affect everyone in the world. It is noteworthy that the poet does not simply want to record the current events, but rather aims to achieve a balance between what happens in reality and what happens in our consciousness. In other words, to record the pandemic and beyond. © 2023 Taylor & Francis Group, LLC.

Medical Image Segmentation Based on Transformer and HarDNet Structures

Medical image segmentation is a crucial way to assist doctors in the accurate diagnosis of diseases. However, the accuracy of medical image segmentation needs further improvement due to the problems of many noisy medical images and the high similarity between background and target regions. The current mainstream image segmentation networks, such as TransUnet, have achieved accurate image segmentation. Still, the encoders of such segmentation networks do not consider the local connection between adjacent chunks and lack the interaction of inter-channel information during the upsampling of the decoder. To address the above problems, this paper proposed a dual-encoder image segmentation network, including HarDNet68 and Transformer branch, which can extract the local features and global feature information of the input image, allowing the segmentation network to learn more image information, thus improving the effectiveness and accuracy of medical segmentation. In this paper, to realize the fusion of image feature information of different dimensions in two stages of encoding and decoding, we propose a feature adaptation fusion module to fuse the channel information of multi-level features and realize the information interaction between channels, and then improve the segmentation network accuracy. The experimental results on CVC-ClinicDB, ETIS-Larib, and COVID-19 CT datasets show that the proposed model performs better in four evaluation metrics, Dice, Iou, Prec, and Sens, and achieves better segmentation results in both internal filling and edge prediction of medical images. Accurate medical image segmentation can assist doctors in making a critical diagnosis of cancerous regions in advance, ensure cancer patients receive timely targeted treatment, and improve their survival quality. © 2013 IEEE.

Lung CT image segmentation algorithm based on improved U-net structure

Accurate segmentation of medical images can help doctors diagnose and treat diseases. In the face of the complex COVID-19 image, this paper proposes an improved U-net network segmentation model, which uses the residual network structure to deepen the network level, and adds the attention module to integrate different receptive field, global, local and spatial features to enhance the detail segmentation effect of the network. For the COVID-19 CT data set, the F1-Score, Accuracy, SE, SP and Precision of the U-Net network are 0.9176, 0.9578, 0.9669, 0.9487 and 0.8574 respectively. Compared with U-Net, our model proposed in this paper increased by 6.43%, 3.36%, 0.85%, 4.78% and 13.11% on F1-Score, Accuracy, SE, SP and Precision, respectively. The automatic and effective segmentation of COVID-19 lung CT image is realized. © 2022 IEEE.

Outcomes of Extremely Prolonged (> 50 Days) Venovenous Extracorporeal Membrane Oxygenation Support: A Single Center Experience

The COVID-19 pandemic drove a sustained increase in the volume and duration of venovenous extracorporeal membrane oxygenation (VV-ECMO), accelerating a decade long trend. While current clinical consensus recommends a maximal support duration of 14-21 days, the observed change in practice may warrant revisiting this notion. To guide this, we describe our institution's experience with prolonged VV-ECMO support. We performed a retrospective cohort analysis of patients who received VV-ECMO support at a large academic medical center between 2018-2022 using medical records. This study is a descriptive report of patients who received prolonged VV-ECMO support, defined as >50 continuous days on circuit. Of the 130 patients who received VV-ECMO during the study period, 12 (9.2%) had a support duration of >50 days, 11 of whom suffered from adult respiratory distress syndrome (ARDS) secondary to COVID-19, while 1 patient with prior bilateral lung transplant suffered from ARDS secondary to bacterial pneumonia. The median duration of VV-ECMO support was 94 days [IQR: 69.5, 128], with a maximum support of 180 days. Median time from intubation to cannulation was 5 days [IQR: 2, 14]. On-circuit mobilization was performed in 9 patients (75%). Successful weaning of VV-ECMO support occurred in 8 patients (67%), with 6 (50%) bridged to lung transplantation and 2 (17%) bridged to recovery. A total of 7 patients (58%) were discharged from the hospital: 3 to home and 4 to a rehabilitation center. ECMO complications included cannulation site bleeding in 10 patients (83%), gastrointestinal bleeding in 4 patients (33%), oxygenator failure in 7 patients (58%), and required circuit exchanges in 9 patients (75%) (Figure 1). Extremely prolonged VV-ECMO support allows for successful recovery or optimization of lung transplant candidacy in a select group of patients at a high-volume institution, further supporting the expanded utilization of VV-ECMO. [ABSTRACT FROM AUTHOR] Copyright of Journal of Heart & Lung Transplantation is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

COVID-19 Epidemic Forecast using Machine Learning Regression Techniques

The COVID-19 Coronavirus (SARS-CoV-2), has caused destruction all around the world, since December 2019. It is still managing to grow at an unprecedented scale. It was declared as a health emergency for the entire globe by the World Health Organization (WHO) in January 2022. The virus continues to impact the lives of millions of people. An early detection system warning about the repercussions of the virus at a county level can be favorable for the residents as well and aid the government to enforce appropriate safety measures. This research aims at modeling such a warning system which predicts the positivity rate of COVID-19 for a geographical location. The proposed solution uses supervised machine learning techniques such as Random Forest, Linear Regression, Naive Bayes, and Gradient Boosting Regression. The prediction is made based on the analysis of the past data in each time frame with temporal input such as the population of the area, number of tests conducted, number of positive tests, reported cases in that area among others. The Gradient Boosting algorithm outperforms all the other algorithms used in this research. Machine learning based recommendation system for COVID-19 spread can help the public and government to take necessary precautions for suppressing its effect. The proposed modeling approach provides a reliable tool to predict COVID-19 transmission with an accuracy of 99.4%. © 2022 IEEE.

COVID-19 Epidemic Forecast using Machine Learning Regression Techniques

The COVID-19 Coronavirus (SARS-CoV-2), has caused destruction all around the world, since December 2019. It is still managing to grow at an unprecedented scale. It was declared as a health emergency for the entire globe by the World Health Organization (WHO) in January 2022. The virus continues to impact the lives of millions of people. An early detection system warning about the repercussions of the virus at a county level can be favorable for the residents as well and aid the government to enforce appropriate safety measures. This research aims at modeling such a warning system which predicts the positivity rate of COVID-19 for a geographical location. The proposed solution uses supervised machine learning techniques such as Random Forest, Linear Regression, Naive Bayes, and Gradient Boosting Regression. The prediction is made based on the analysis of the past data in each time frame with temporal input such as the population of the area, number of tests conducted, number of positive tests, reported cases in that area among others. The Gradient Boosting algorithm outperforms all the other algorithms used in this research. Machine learning based recommendation system for COVID-19 spread can help the public and government to take necessary precautions for suppressing its effect. The proposed modeling approach provides a reliable tool to predict COVID-19 transmission with an accuracy of 99.4%. © 2022 IEEE.

Research on Service Design for COVID-19 Nucleic Acid Test Needs of the Public

Taking the whole city nucleic acid test process in Nanjing as the starting point, this paper explores the main characteristics of the existing nucleic acid test process. Then it analyzes the main process of nucleic acid test and the user needs of community residents, volunteers and medical staff in nucleic acid detection. Based on this, a new design idea is proposed to optimize the nucleic acid test process for the public. Using the design methods of service blueprint and stakeholder analysis, this paper finally puts forward a set of service design process based on the combination of online mobile application terminal and offline self-service nucleic acid detection equipment. By optimizing the nucleic acid test service process, we can alleviate the shortage of medical manpower resources and cross infection between doctors and patients under the outbreak of COVID-19. At the same time, we also help users achieve a safe, fast and efficient nucleic acid detection process experience. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Research on Difficulties and Countermeasures of China's Energy Industry under the Situation of Normalized Epidemic Prevention and Control

The COVID-19 pandemic has had a profound impact on international economic and energy development, Until now, the epidemic has not completely retreated, and prevention and control of the epidemic has become a new normal. Starting from the analysis of the impact of COVID-19 on the upper, middle and lower reaches of the energy industry chain, this paper explores the dilemma faced by China's energy development under the situation of normalized epidemic prevention and control, and puts forward effective countermeasures, which have important strategic significance for ensuring the sustainable development of China's energy and the coordination and stability of economic society. © 2022 by Aussino Academic Publishing House.

DEVELOPMENT OF AN OROPHARYNGEAL SWAB ASSEMBLY

Oropharyngeal (OP) swabbing is a clinical specimen collection method to diagnose the presence of viral infection in the respiratory tract. During the Covid-19 pandemic, OP swab sampling plays an important role in the disease diagnosis. With its advantages in direct visualization of the swab site and less training requirement on medical professionals, OP swab is massively used for COVID-19 specimen collection in many countries. However, patients may demonstrate less tolerance for the OP swabbing by gagging or closing their mouths, which puts the swab tip in contact with the oral palate or tongue and results in defective sampling. Gagging and other involuntary reactions increase the risk to medical workers who are in direct contact with the patients. To solve these issues, this research presents a novel OP swab assembly which can assist adult patients to collect OP swab specimen by themselves or facilitate adults to collect specimens for their children or disable family members. The OP swab assembly has features to mitigate discomforts in the swab procedures as so to reduce involuntary reactions, minimizing specimen contamination. It also has features to keep the mouth open and constrain the motion of the swab tip in the effective sampling area, furtherly ensuring the high quality of the specimen. Experiments were conducted on a standard adult human skull mannequin by using the presented OP swab assembly. The results demonstrated the feasibility and effectiveness of self-collection for OP swabs using the presented assembly and method.

A framework for a multimodal intensive care curriculum for anesthesiologists during COVID-19

INTRODUCTION: As need outstrips intensivist supply, anesthesiologists are a natural fit to step in and serve in COVID ICU care teams. We describe an educational package designed to improve anesthesiologists' self-efficacy and willingness to work in the COVID ICU. METHODS: Over 7 days, 4 ICU trained anesthesiologists from our 958-bed quaternary care facility created a distance learning, online platform for the affiliated private practice anesthesia group. The program was developed using an iterative process with input from the anesthesiologists. The multimodal format included 13 lectures as well as 3 online interactive video sessions. Each lecture included a bulleted summary document, a PowerPoint presentation and a recorded video lecture. Material was presented using a flipped classroom approach with online material distributed first, followed by interactive sessions moderated by specialists from pulmonary, anesthesia and emergency critical care. At the end of the curriculum, a survey was sent to the 27 attending anesthesiologists identified as the initial backup staffing cohort. RESULTS: 11 out of 27 surveys were completed. 1 of the 11 did not access the content. Of the remaining 10, 90% reported that the material conferred additional benefit beyond that provided by other online COVID educational resources. All reported that the material made them feel more comfortable with recognizing major issues associated with caring for the COVID ICU patient, 80% reported a reduction in stress level and 80% felt that it improved their willingness to take care of COVID ICU patients. CONCLUSIONS: Our group was successful in quickly creating effective online COVID ICU educational materials using a combination of low tech mediums. These materials supported distance learning for a group of attending anesthesiologists from a large private practice group working in a large academic medical center. While national resources are available, our experience highlights that local resources represent an important supplement. The fact that our program was successfully implemented quickly at a large academic medical center but targeted private practice anesthesiologists, was low tech and used only materials readily available to many highlights its applicability to hospitals throughout the nation.

CHILDHOOD-ONSET INTERSTITIAL LUNG DISEASE: A RARE CASE OF IDIOPATHIC, NONSPECIFIC INTERSTITIAL PNEUMONIA IN A TEENAGER

SESSION TITLE: Fellows Diffuse Lung Disease SESSION TYPE: Fellow Case Reports PRESENTED ON: October 18-21, 2020 INTRODUCTION: Childhood interstitial lung disease (chILD) is remarkably rare with a reported prevalence from 0.13 per 100,000 children under 17 years to 16.2 per 100,000 children under 15 years of age (1). Here we present a case of a teenager with idiopathic nonspecific interstitial pneumonia (NSIP). CASE PRESENTATION: A 15-year old previously healthy female presented with a three-week history of dry cough, fever, malaise and shortness of breath which progressed to dyspnea on exertion despite a course of outpatient antibiotics. She had no environmental exposures, history of smoking or vaping nor family history of pulmonary pathology. Initial vital signs were significant for hypoxemia to 80% and a chest x-ray and CT scan with bilateral consolidations and ground glass opacities. Initial laboratory tests showed elevated inflammatory markers, other tests including SARS-CoV-2 PCR were negative. Bronchoscopy, bronchoalveolar lavage, and transbronchial biopsies yielded no definitive diagnosis. Following bronchoalveolar lavage, she developed rapid clinical deterioration necessitating mechanical ventilation, paralytics, and inhaled nitric oxide. Given elevated inflammatory markers and after infection was excluded, intravenous steroids were initiated with partial improvement. After extubation, a protracted inability to wean off oxygen support, and spirometry showing ongoing, severe restrictive lung disease, lung biopsy via video-assisted thorascopic surgery was performed lending to the ultimate diagnosis NSIP. Hypersensitivity pneumonitis panel, ILD panel and genetic testing were unrevealing, as such her case was classified as idiopathic NSIP. DISCUSSION: NSIP in adolescents is very rare. A meta-analysis (2) reports the average age of patients with NSIP to be 54.8 years. In the pediatric population, NSIP can be associated with systemic disease processes such as collagen vascular disease, including systemic lupus erythematosus, juvenile rheumatoid arthritis, and dermatomyositis associated with antibodies to melanoma differentiation-associated gene 5 (anti-MDA5), as well as a complication of blood stem cell transplants and surfactant dysfunction mutations, although most cases are idiopathic (3). Given that the etiology of NSIP is broad and in most cases idiopathic, response to corticosteroids is also variable. Our patient had a partial response to corticosteroids early on in her treatment, manifested by augmented gas exchange and improved symptomatology. The relatively slow response to treatment in the first several weeks is likely consistent with her biopsy findings which showed fibroblast proliferation and fibrosis. CONCLUSIONS: ILD and particularly NSIP are rare conditions in adolescents but should be suspected in patients with hypoxemia and abnormal imaging in the absence of infectious or autoimmune etiologies. An extensive workup is recommended to determine association with systemic conditions, treatment and prognosis. Reference #1: (1) Griese M, Haug M, Brasch F, et al. Incidence and classification of pediatric diffuse parenchymal lung diseases in Germany. Orphanet J Rare Dis. 2009;4:26. Published 2009 Dec 12. doi:10.1186/1750-1172-4-26 Reference #2: (2) Ebner L, Christodoulidis S, Stathopoulou T, et al. Meta-analysis of the radiological and clinical features of Usual Interstitial Pneumonia (UIP) and Nonspecific Interstitial Pneumonia (NSIP). PLoS One. 2020;15(1):e0226084. Published 2020 Jan 13. doi:10.1371/journal.pone.0226084 Reference #3: (3) Vece TJ, Fan LL. Interstitial Lung Disease in Children Older Than 2 Years. Pediatr Allergy Immunol Pulmonol. 2010;23(1):33-41. doi:10.1089/ped.2010.0008 DISCLOSURES: No relevant relationships by Giuliana Cerro, source=Web Response No relevant relationships by Gary Goulin, source=Web Response No relevant relationships by Jack Green, source=Web Response No relevant relationships by Michael Lewis, source=Web Response No relevant relationships by Tim Shen, source=Web Respon e