-
PloS One 2024Organ segmentation has become a preliminary task for computer-aided intervention, diagnosis, radiation therapy, and critical robotic surgery. Automatic organ...
Organ segmentation has become a preliminary task for computer-aided intervention, diagnosis, radiation therapy, and critical robotic surgery. Automatic organ segmentation from medical images is a challenging task due to the inconsistent shape and size of different organs. Besides this, low contrast at the edges of organs due to similar types of tissue confuses the network's ability to segment the contour of organs properly. In this paper, we propose a novel convolution neural network based uncertainty-driven boundary-refined segmentation network (UDBRNet) that segments the organs from CT images. The CT images are segmented first and produce multiple segmentation masks from multi-line segmentation decoder. Uncertain regions are identified from multiple masks and the boundaries of the organs are refined based on uncertainty data. Our method achieves remarkable performance, boasting dice accuracies of 0.80, 0.95, 0.92, and 0.94 for Esophagus, Heart, Trachea, and Aorta respectively on the SegThor dataset, and 0.71, 0.89, 0.85, 0.97, and 0.97 for Esophagus, Spinal Cord, Heart, Left-Lung, and Right-Lung respectively on the LCTSC dataset. These results demonstrate the superiority of our uncertainty-driven boundary refinement technique over state-of-the-art segmentation networks such as UNet, Attention UNet, FC-denseNet, BASNet, UNet++, R2UNet, TransUNet, and DS-TransUNet. UDBRNet presents a promising network for more precise organ segmentation, particularly in challenging, uncertain conditions. The source code of our proposed method will be available at https://github.com/riadhassan/UDBRNet.
Topics: Humans; Neural Networks, Computer; Tomography, X-Ray Computed; Uncertainty; Organs at Risk; Image Processing, Computer-Assisted; Algorithms; Lung
PubMed: 38885241
DOI: 10.1371/journal.pone.0304771 -
PloS One 2024There has been a lot of discussion about the role of schools in the transmission of severe acute respiratory coronavirus 2 (SARS-CoV-2) during the coronavirus 2019...
Implementation and effectiveness of non-pharmaceutical interventions, including mask mandates and ventilation, on SARS-CoV-2 transmission (alpha variant) in primary schools in the Netherlands.
There has been a lot of discussion about the role of schools in the transmission of severe acute respiratory coronavirus 2 (SARS-CoV-2) during the coronavirus 2019 (COVID-19) pandemic, where many countries responded with school closures in 2020. Reopening of primary schools in the Netherlands in February 2021 was sustained by various non-pharmaceutical interventions (NPIs) following national recommendations. Our study attempted to assess the degree of regional implementation and effectiveness of these NPIs in South Limburg, Netherlands. We approached 150 primary schools with a structured questionnaire containing items on the implementation of NPIs, including items on ventilation. Based on our registry of cases, we determined the number of COVID-19 cases linked to each school, classifying cases by their source of transmission. We calculated a crude secondary attack rate by dividing the number of cases of within-school transmission by the total number of children and staff members. Two-sample proportion tests were performed to compare these rates between schools stratified by the presence of a ventilation system and mask mandates for staff members. A total of 69 schools responded. Most implemented NPIs were aimed at students, except for masking mandates, which preferentially targeted teachers over students (63% versus 22%). We observed lower crude secondary attack rates in schools with a ventilation system compared to schools without a ventilation system (1.2% versus 2.8%, p<0.01). Mandatory masking for staff members had no effect on the overall crude secondary attack rate (2.0% versus 2.1%, p = 0.03) but decreased the crude secondary attack rate among staff members (2.3% versus 1.7%, p<0.01). Schools varied in their implementation of NPIs, most of which targeted students. Rates of within-school transmission were higher compared to other studies, possibly due to a lack of proper ventilation. Our research may help improve guidance for primary schools in future outbreaks.
Topics: Humans; COVID-19; Netherlands; Schools; Masks; Ventilation; Child; SARS-CoV-2; Surveys and Questionnaires; Students; Pandemics; Male; Female
PubMed: 38885240
DOI: 10.1371/journal.pone.0305195 -
JMIR Formative Research Jun 2024The start of the COVID-19 pandemic resulted in the implementation of nonpharmaceutical interventions by US institutions of higher education at an unprecedented level....
BACKGROUND
The start of the COVID-19 pandemic resulted in the implementation of nonpharmaceutical interventions by US institutions of higher education at an unprecedented level. During the backdrop of an emerging pandemic, younger adults (eg, college students) had an overall lower risk for severe outcomes for SARS-CoV-2, making this population a potential source of transmission for age groups with high susceptibility and negative health outcomes. We examine how college students' level of concern for COVID-19 was influenced by different sources of information, their living status, income level, and other demographic identifiers and its association with prevention behavior change.
OBJECTIVE
We sought to examine the level of concern, defined as the extent to which the participant would take corrective action to mitigate contracting or spreading the virus (to family or friends) by using personal protective equipment such as a face mask, practicing social distancing, and following other public health recommendations, among college students during the COVID-19 pandemic.
METHODS
A cross-sectional, web-based survey was conducted in 2021 among 185 college students aged 18-41 years, with most living in New York City and the United States (n=134, 72.4%). Out of 185 college students, 94 provided their zip codes, with 51 of those college students indicating they lived in New York City areas. The participants completed the survey via a QR code. Study participants who did not complete the full survey or were not college students in any US college or university were excluded. Analyses were conducted using R (version 4.2.2; R Foundation for Statistical Computing).
RESULTS
Of 185 respondents participated in the study, 25 (13.5.%) used emails from their schools, 51 (27.6%) used mainstream media, and 109 (58.9%) used social media and other sources to obtain information about COVID-19. Of the 109 participants who learned about the pandemic from social media, 91 (83.5%) were concerned; however, only 63% (32/51) and 60% (15/25) of the participants who sourced information from mainstream media and their schools' email, respectively, were concerned. Further, the participants who received information from social media and other sources were about 3 times more likely to be concerned about COVID-19 than participants who received information from the university via email (P=.036; OR=3.07, 95% CI: 1.06-8.83)..
CONCLUSIONS
College students who received information from social media and other sources were more likely to be concerned about COVID-19 than students who received information from their school via emails.
PubMed: 38885019
DOI: 10.2196/51292 -
PNAS Nexus Jun 2024Amid the COVID-19 pandemic, education systems globally implemented protective measures, notably mandatory mask wearing. As the pandemic's dynamics changed, many...
Amid the COVID-19 pandemic, education systems globally implemented protective measures, notably mandatory mask wearing. As the pandemic's dynamics changed, many municipalities lifted these mandates, warranting a critical examination of these policy changes' implications. This study examines the effects of lifting mask mandates on COVID-19 transmission within Massachusetts school districts. We first replicated previous research that utilized a difference-in-difference (DID) model for COVID-19 incidence. We then repeated the DID analysis by replacing the outcome measurement with the reproductive number ( ), reflecting the transmissibility. Due to the data availability, the we estimated only measures the within school transmission. We found a similar result in the replication using incidence with an average treatment effect on treated (ATT) of 39.1 (95% CI: 20.4 to 57.4) COVID-19 cases per 1,000 students associated with lifting masking mandates. However, when replacing the outcome measurement to , our findings suggest that no significant association between lifting mask mandates and reduced (ATT: 0.04, 95% CI: -0.09 to 0.18), except for the first 2 weeks postintervention. Moreover, we estimated below 1 at 4 weeks before lifting mask mandates across all school types, suggesting nonsustainable transmission before the implementation. Our reanalysis suggested no evidence of lifting mask mandates in schools impacted the COVID-19 transmission in the long term. Our study highlights the importance of examining the transmissibility outcome when evaluating interventions against transmission.
PubMed: 38881839
DOI: 10.1093/pnasnexus/pgae212 -
Journal of Theoretical Biology Jun 2024The cruise ship sector is a major part of the tourism industry, and an estimated over 30 million passengers are transformed worldwide each year. Cruise ships bring...
The cruise ship sector is a major part of the tourism industry, and an estimated over 30 million passengers are transformed worldwide each year. Cruise ships bring diverse populations into proximity for many days, facilitating the transmission of respiratory illnesses. The objective of this study is to develop a modeling framework to inform the development of viable disease risk management policies and measures to control disease outbreaks on cruises. Our model, parameterized and calibrated using the data of the COVID-19 outbreak on the Diamond Princess cruise ship in 2020, is used to assess the impact of the mitigation measures such as mask wearing, vaccination, on-board and pre-traveling testing measures. Our results indicate mask wearing in public places as the cheapest and most affordable measure can drop the number of cumulative confirmed cases by almost 50%. This measure along with the vaccination by declining the number of the cumulative confirmed cases by more than 94% is the most effective measure to control outbreaks on cruises. According to our findings, outbreaks are more predominant in the passenger population than the crew members, however, the protection measures are more beneficial if they are applied by both crew members and passengers. Regarding the testing measure, pre-traveling testing is more functional than the on-board testing to control outbreaks on cruises.
PubMed: 38880330
DOI: 10.1016/j.jtbi.2024.111875 -
Scientific Reports Jun 2024Recent advancements in machine learning and deep learning have revolutionized various computer vision applications, including object detection, tracking, and...
Recent advancements in machine learning and deep learning have revolutionized various computer vision applications, including object detection, tracking, and classification. This research investigates the application of deep learning for cattle lameness detection in dairy farming. Our study employs image processing techniques and deep learning methods for cattle detection, tracking, and lameness classification. We utilize two powerful object detection algorithms: Mask-RCNN from Detectron2 and the popular YOLOv8. Their performance is compared to identify the most effective approach for this application. Bounding boxes are drawn around detected cattle to assign unique local IDs, enabling individual tracking and isolation throughout the video sequence. Additionally, mask regions generated by the chosen detection algorithm provide valuable data for feature extraction, which is crucial for subsequent lameness classification. The extracted cattle mask region values serve as the basis for feature extraction, capturing relevant information indicative of lameness. These features, combined with the local IDs assigned during tracking, are used to compute a lameness score for each cattle. We explore the efficacy of various established machine learning algorithms, such as Support Vector Machines (SVM), AdaBoost and so on, in analyzing the extracted lameness features. Evaluation of the proposed system was conducted across three key domains: detection, tracking, and lameness classification. Notably, the detection module employing Detectron2 achieved an impressive accuracy of 98.98%. Similarly, the tracking module attained a high accuracy of 99.50%. In lameness classification, AdaBoost emerged as the most effective algorithm, yielding the highest overall average accuracy (77.9%). Other established machine learning algorithms, including Decision Trees (DT), Support Vector Machines (SVM), and Random Forests, also demonstrated promising performance (DT: 75.32%, SVM: 75.20%, Random Forest: 74.9%). The presented approach demonstrates the successful implementation for cattle lameness detection. The proposed system has the potential to revolutionize dairy farm management by enabling early lameness detection and facilitating effective monitoring of cattle health. Our findings contribute valuable insights into the application of advanced computer vision methods for livestock health management.
Topics: Animals; Cattle; Lameness, Animal; Cattle Diseases; Algorithms; Support Vector Machine; Image Processing, Computer-Assisted; Deep Learning; Machine Learning; Video Recording
PubMed: 38877097
DOI: 10.1038/s41598-024-64664-7 -
Journal of Cardiothoracic and Vascular... Apr 2024
PubMed: 38876814
DOI: 10.1053/j.jvca.2024.04.017 -
International Journal of Surgery Case... Jun 2024Percutaneous endoscopic lumbar discectomy (PELD) is increasingly being utilized to treat patients with lumbar disc herniation. PELD is unique in that it uses a single...
Contrast enhancing epidural fluid accumulation after percutaneous endoscopic lumbar discectomy: A case report of recurrent disc herniation within pseudocyst secondary to irrigation fluid.
INTRODUCTION
Percutaneous endoscopic lumbar discectomy (PELD) is increasingly being utilized to treat patients with lumbar disc herniation. PELD is unique in that it uses a single working port endoscope with constant irrigation of the surgical field to visualize pathology. The current report is of a case of postoperative epidural irrigation fluid accumulation presenting as peripherally enhancing epidural lesions, masking an underlying re-herniation.
PRESENTATION OF CASE
A patient with a Lumbar 5-Sacral 1 level disc herniation presenting with radiculopathy was treated using PELD. Following the operation, the patient experienced recurrent pain, prompting a repeat MRI of the lumbar spine. Multiple ring-enhancing lesions within the epidural space were observed, creating diagnostic dilemmas. The differential diagnoses included epidural abscess, pseudomeningocele from unintended durotomy, epidural hematoma, or trapped epidural fluid collection presenting as a pseudocyst with or without recurrent disc herniation. A repeat endoscopic discectomy was performed to confirm the diagnosis of pseudocyst, revealing a recurrent disc herniation.
DISCUSSION
Pseudocysts are not an uncommon complication of PELD, typically believed to be due to an inflammatory response to disc fragments. However, in this case, the epidural fluid collection was likely the result of trapped irrigation fluid from continuous irrigation during the procedure, which masked an underlying re-herniation on imaging.
CONCLUSION
With the increasing utilization of PELD, it is important to acknowledge unique complications such as fluid accumulation from irrigation within the epidural space. Fluid accumulation can lead to contrast-enhancing pseudocyst formation, which can theoretically lead to mass effect or increased intracranial and intraspinal pressure and may mask additional underlying pathology.
PubMed: 38875830
DOI: 10.1016/j.ijscr.2024.109884 -
JMIR Biomedical Engineering Oct 2023Accurate and portable respiratory parameter measurements are critical for properly managing chronic obstructive pulmonary diseases (COPDs) such as asthma or sleep apnea,...
BACKGROUND
Accurate and portable respiratory parameter measurements are critical for properly managing chronic obstructive pulmonary diseases (COPDs) such as asthma or sleep apnea, as well as controlling ventilation for patients in intensive care units, during surgical procedures, or when using a positive airway pressure device for sleep apnea.
OBJECTIVE
The purpose of this research is to develop a new nonprescription portable measurement device that utilizes relative humidity sensors (RHS) to accurately measure key respiratory parameters at a cost that is approximately 10 times less than the industry standard.
METHODS
We present the development, implementation, and assessment of a wearable respiratory measurement device using the commercial Bosch BME280 RHS. In the initial stage, the RHS was connected to the pneumotach (PNT) gold standard device via its external connector to gather breathing metrics. Data collection was facilitated using the Arduino platform with a Bluetooth Low Energy connection, and all measurements were taken in real time without any additional data processing. The device's efficacy was tested with 7 participants (5 men and 2 women), all in good health. In the subsequent phase, we specifically focused on comparing breathing cycle and respiratory rate measurements and determining the tidal volume by calculating the region between inhalation and exhalation peaks. Each participant's data were recorded over a span of 15 minutes. After the experiment, detailed statistical analysis was conducted using ANOVA and Bland-Altman to examine the accuracy and efficiency of our wearable device compared with the traditional methods.
RESULTS
The perfused air measured with the respiratory monitor enables clinicians to evaluate the absolute value of the tidal volume during ventilation of a patient. In contrast, directly connecting our RHS device to the surgical mask facilitates continuous lung volume monitoring. The results of the 1-way ANOVA showed high P values of .68 for respiratory volume and .89 for respiratory rate, which indicate that the group averages with the PNT standard are equivalent to those with our RHS platform, within the error margins of a typical instrument. Furthermore, analysis utilizing the Bland-Altman statistical method revealed a small bias of 0.03 with limits of agreement (LoAs) of -0.25 and 0.33. The RR bias was 0.018, and the LoAs were -1.89 and 1.89.
CONCLUSIONS
Based on the encouraging results, we conclude that our proposed design can be a viable, low-cost wearable medical device for pulmonary parametric measurement to prevent and predict the progression of pulmonary diseases. We believe that this will encourage the research community to investigate the application of RHS for monitoring the pulmonary health of individuals.
PubMed: 38875670
DOI: 10.2196/47146 -
Medicine Jun 2024In the fight against the COVID-19 pandemic, the importance of health literacy in individuals' attitudes has increased. This study aimed to show whether there is a...
In the fight against the COVID-19 pandemic, the importance of health literacy in individuals' attitudes has increased. This study aimed to show whether there is a relationship between health literacy and adherence to personal protective anti-COVID-19 health behaviors in health workers and their relatives and to evaluate the barriers to adherence to personal protective anti-COVID-19 health behaviors. Designed as a cross-sectional mixed-methods study. Participants were asked to fill in an online survey form containing questions designed to determine their sociodemographic data, health literacy, adherence to protective anti-COVID-19 health behaviors, and barriers to adherence. The research results were evaluated with a confidence interval of 95% and margin of error of 0.05. Thematic content analysis was used to evaluate participants' answers to the open-ended questions. In this study, data collected from 393 participants were analyzed. In the Disease Prevention and Health Promotion Subscale, the group of participants who adhered to wearing masks "at all times" obtained a higher average score from the Turkey Health Literacy Scale than other participant groups, while the participant group that "always" complied with hand washing and social distancing obtained higher average scores from the Turkey Health Literacy Scale and its two subscales compared to other participant groups. As a result of the thematic content analysis carried out in order to determine the situations that prevent the participants from complying with personal protective anti-COVID-19 health behaviors, the main themes were determined as "forgetting/not wearing the habit of wearing a mask," "mask ergonomics" and "noncompliance with social distance." This study shows that there is a positive relationship between health literacy and adherence to protective anti-COVID-19 health behaviors among health workers and their relatives and revealed major barriers to adherence to protective anti-COVID-19 health behaviors among health workers and their relatives.
Topics: Humans; Health Literacy; COVID-19; Male; Female; Cross-Sectional Studies; Adult; Health Personnel; Health Behavior; Turkey; Middle Aged; SARS-CoV-2; Family; Masks; Surveys and Questionnaires; Young Adult
PubMed: 38875376
DOI: 10.1097/MD.0000000000038505