Enhancing Fingerprint Liveness Detection Accuracy Using Deep Learning: A Comprehensive Study and Novel Approach.

Liveness detection for fingerprint impressions plays a role in the meaningful prevention of any unauthorized activity or phishing attempt. The accessibility of unique individual identification has increased the popularity of biometrics. Deep learning with computer vision has proven remarkable results in image classification, detection, and many others. The proposed methodology relies on an attention model and ResNet convolutions. Spatial attention (SA) and channel attention (CA) models were used sequentially to enhance feature learning. A three-fold sequential attention model is used along with five convolution learning layers. The method's performances have been tested across different pooling strategies, such as Max, Average, and Stochastic, over the LivDet-2021 dataset. Comparisons against different state-of-the-art variants of Convolutional Neural Networks, such as DenseNet121, VGG19, InceptionV3, and conventional ResNet50, have been carried out. In particular, tests have been aimed at assessing ResNet34 and ResNet50 models on feature extraction by further enhancing the sequential attention model. A Multilayer Perceptron (MLP) classifier used alongside a fully connected layer returns the ultimate prediction of the entire stack. Finally, the proposed method is also evaluated on feature extraction with and without attention models for ResNet and considering different pooling strategies.

Deep Learning-Based Automatic Detection of Ships: An Experimental Study Using Satellite Images.

The remote sensing surveillance of maritime areas represents an essential task for both security and environmental reasons. Recently, learning strategies belonging to the field of machine learning (ML) have become a niche of interest for the community of remote sensing. Specifically, a major challenge is the automatic classification of ships from satellite imagery, which is needed for traffic surveillance systems, the protection of illegal fisheries, control systems of oil discharge, and the monitoring of sea pollution. Deep learning (DL) is a branch of ML that has emerged in the last few years as a result of advancements in digital technology and data availability. DL has shown capacity and efficacy in tackling difficult learning tasks that were previously intractable. Specifically, DL methods, such as convolutional neural networks (CNNs), have been reported to be efficient in image detection and recognition applications. In this paper, we focused on the development of an automatic ship detection (ASD) approach by using DL methods for assessing the Airbus ship dataset (composed of about 40 K satellite images). The paper explores and analyzes the distinct variations of the YOLO algorithm for the detection of ships from satellite images. A comparison of different versions of YOLO algorithms for ship detection, such as YOLOv3, YOLOv4, and YOLOv5, is presented, after training them on a personal computer with a large dataset of satellite images of the Airbus Ship Challenge and Shipsnet. The differences between the algorithms could be observed on the personal computer. We have confirmed that these algorithms can be used for effective ship detection from satellite images. The conclusion drawn from the conducted research is that the YOLOv5 object detection algorithm outperforms the other versions of the YOLO algorithm, i.e., YOLOv4 and YOLOv3 in terms accuracy of 99% for YOLOv5 compared to 98% and 97% respectively for YOLOv4 and YOLOv3.

Detection and analysis of COVID-19 in medical images using deep learning techniques.

The main purpose of this work is to investigate and compare several deep learning enhanced techniques applied to X-ray and CT-scan medical images for the detection of COVID-19. In this paper, we used four powerful pre-trained CNN models, VGG16, DenseNet121, ResNet50,and ResNet152, for the COVID-19 CT-scan binary classification task. The proposed Fast.AI ResNet framework was designed to find out the best architecture, pre-processing, and training parameters for the models largely automatically. The accuracy and F1-score were both above 96% in the diagnosis of COVID-19 using CT-scan images. In addition, we applied transfer learning techniques to overcome the insufficient data and to improve the training time. The binary and multi-class classification of X-ray images tasks were performed by utilizing enhanced VGG16 deep transfer learning architecture. High accuracy of 99% was achieved by enhanced VGG16 in the detection of X-ray images from COVID-19 and pneumonia. The accuracy and validity of the algorithms were assessed on X-ray and CT-scan well-known public datasets. The proposed methods have better results for COVID-19 diagnosis than other related in literature. In our opinion, our work can help virologists and radiologists to make a better and faster diagnosis in the struggle against the outbreak of COVID-19.

Prevalence and Inpatient Hospital Outcomes of Malignancy-Related Ascites in the United States.

OBJECTIVE: Malignancy-related ascites (MRA) is the terminal stage of many advanced cancers, and the treatment is mainly palliative. This study looked for epidemiology and inpatient hospital outcomes of patients with MRA in the United States using a national database. METHODS: The current study was a cross-sectional analysis of 2015 National Inpatient Sample data and consisted of patients ≥18 years with MRA. Descriptive statistics were used for understanding demographics, clinical characteristics, and MRA hospitalization costs. Multivariate regression models were used to identify predictors of length of hospital stay and in-hospital mortality. RESULTS: There were 123 410 MRA hospitalizations in 2015. The median length of stay was 4.7 days (interquartile range [IQR]: 2.5-8.6 days), median cost of hospitalization was US$43 543 (IQR: US$23 485-US$82 248), and in-hospital mortality rate was 8.8% (n = 10 855). Multivariate analyses showed that male sex, black race, and admission to medium and large hospitals were associated with increased hospital length of stay. Factors associated with higher in-hospital mortality rates included male sex; Asian or Pacific Islander race; beneficiaries of private insurance, Medicaid, and self-pay; patients residing in large central and small metro counties; nonelective admission type; and rural and urban nonteaching hospitals. CONCLUSIONS: Our study showed that many demographic, socioeconomic, health care, and geographic factors were associated with hospital length of stay and in-hospital mortality and may suggest disparities in quality of care. These factors could be targeted for preventing unplanned hospitalization, decreasing hospital length of stay, and lowering in-hospital mortality for this population.

Inpatient Palliative Care Use Among Critically III Brain Metastasis Patients in the United States.

OBJECTIVE: The objective of this study was to understand the trends and characteristics of palliative care delivery among critically ill brain metastasis patients using a nationally representative database. MATERIALS AND METHODS: This study was a retrospective analysis of Nationwide Inpatient Sample data collected during 2005 to 2014. This study included critically ill patients, 18 years and above, diagnosed with brain metastasis, identified using International Classification of Diseases-Ninth Revision-Clinical Modification diagnosis and procedure codes. Multivariable logistic regression models were used for predicting factors associated with inpatient palliative care use. RESULTS: Among 18,309 critically ill patients with brain metastasis, 3298 (18.0%) received inpatient palliative care. The rate of inpatient palliative care use among these patients increased from 3.2% to 28.5%, during 2005 to 2014 (P<0.001). Regression analysis showed that hospital teaching status (odds ratio [ORs], 1.45; 95% confidence interval [CI], 1.14-1.84), primaries located in head and neck (OR, 1.42; 95% CI, 1.21-2.05) or lung (OR, 1.32; 95% CI, 1.22-1.44), and primary diagnosis of pneumonia (OR, 1.42; 95% CI, 1.22-1.97) or septicemia (OR, 1.59; 95% CI, 1.30-1.97), were associated with higher palliative care use. Hispanic ethnicity (OR, 0.86; 95% CI, 0.67-0.96), and hospital location in Northeast (OR, 0.73; 95% CI, 0.54-0.96), Midwest (OR, 0.63; 95% CI, 0.45-0.87), or South (OR, 0.64; 95% CI, 0.48-0.86) were associated with lower palliative care use. CONCLUSIONS: Inpatient palliative care use increased significantly among critically ill patients with brain metastases, though overall rate was low. There were geographical and racial disparities among these patients. Health care providers and policy makers should focus on decreasing these disparities. In addition, hospitals should focus on adopting more palliative care services.

A risk model for prediction of 30-day readmission rates after surgical treatment for colon cancer.

PURPOSE: The purpose of this study was to develop a risk model for the prediction of 30-day unplanned readmission rate after surgery for colon cancer. METHOD: This study was a cross-sectional analysis of data from Nationwide Readmissions Database, collected during 2010-2014. Patients ≥ 18 years of age who underwent surgery for colon cancer were included in the study. The primary outcome of the study was 30-day unplanned readmission rate. RESULTS: There were 141,231 index hospitalizations for surgical treatment of colon cancers and 16,551 had unplanned readmissions. Age, sex, primary payer, Elixhauser comorbidity index, node positive or metastatic disease, length of stay, hospital bedsize, teaching status, hospital ownership, presence of stoma, surgery types, surgery procedures, infectious complications, surgical complications, mechanical wounds, pulmonary complications, and gastrointestinal complications were selected for the risk analysis during backward regression model. Based on the estimated coefficients of selected variables, risk scores were developed and stratified as low risk (≤ 1.08), moderate risk (> 1.08 to ≤ 1.5), and high risk (> 1.5) for unplanned readmission. Validation analysis (n = 42,269) showed that 7.1% of low-risk individuals, 11.1% of moderate-risk individuals, and 17.1% of high-risk individuals experienced unplanned readmissions (P < 0.001). Pairwise comparisons also showed statistically significant differences between low-risk and moderate-risk participants (P < 0.001), between moderate-risk and high-risk participants (P < 0.001), and between low-risk and high-risk participants (P < 0.001). The area under the ROC curve was 0.622. CONCLUSIONS: Our risk model could be helpful for risk-stratifying patients for readmission after surgical treatment for colon cancer. This model needs further validation by incorporating all possible clinical variables.

Recent Health Care Expenditure Trends Among Adult Cancer Survivors in United States, 2009-2016.

OBJECTIVE: The objective of this study was to understand recent trends in direct health care expenditures among cancer survivors using novel cost-estimation methods and a nationally representative database. MATERIALS AND METHODS: This study was a retrospective analysis of 193,003 adults, ≥18 years of age, using the Medical Expenditure Panel Survey during the years 2009-2016. Manning and Mullahy two-part model was used to calculate adjusted mean and incremental medical expenditures after adjusting for covariates. RESULTS: The mean direct annual health care expenditure among cancer survivors ($13,025.0 [$12,572.0 to $13,478.0]) was nearly 3 times greater than noncancer participants ($4689.3 [$4589.2 to $4789.3]) and were mainly spent on inpatient services, office-based visits, and prescription medications. Cancer survivors had an additional health care expenditure of $4407.6 ($3877.6, $4937.6) per person per year, compared with noncancer participants after adjusting for covariates (P<0.001). The total mean annual direct health care expenditure for cancer survivors increased from $12,960.0 (95% confidence interval: $12,291.0-$13,628.0) in 2009-2010 to $13,807.0 ($12,828.0 to $14,787.0) in 2015-2016. CONCLUSIONS: Given the higher health care expenditures among cancer survivors and the increasing prevalence of cancers, cost-saving measures should be planned through multidisciplinary initiatives, collaborative research, and importantly, health care planning and policy changes. Our findings could be helpful in streamlining health care resources and interventions, developing national health care coverage policies, and possibly considering radically new insurance strategies for cancer survivors.

Viral suppression among persons living with HIV in Trinidad & Tobago: Implications for targeted prevention programmes.

In Trinidad and Tobago, despite persons living with HIV (PLHIV) having access to subsidised treatment and care, only 47% PLHIV attain viral suppression. The study assessed the role of individual-level factors on viral suppression among PLHIV in Trinidad and Tobago. Data from 9,629 PLHIV who attended an HIV clinic between 2016 and 2018 were analysed. Cases were aged ≥18 who met the CDC HIV case definition. Viral suppression defined as a viral load of <200 copies/ml at last assessment. The chi-square test of association determined statistically significant relationships between individual factors and viral suppression. Logistic regression was used to estimate odds ratios (OR) for viral suppression. PLHIV who were males (OR = 0.76, 95% CI 0.67-0.87), men who have sex with men (MSM) (OR = 0.82, 95% CI 0.67-0.99), single/unmarried (OR = 0.69, 95% CI 0.55-0.87), aged 18-24 years (OR = 0.66, 95% CI 0.49-0.89), aged 25-49 years (OR = 0.81, 95% CI 0.70-0.94) were less likely to achieve viral suppression. These study findings demonstrate that retention/adherence programmes must urgently identify and target vulnerable PLHIV populations in Trinidad and Tobago to improve viral suppression. Further research examining community and societal factors, such as stigma and discrimination, is warranted.

The Pre-exposure Prophylaxis (PrEP) Continuum of Care and Correlates to Initiation Among HIV-Negative Men Recruited at Miami Gay Pride 2018.

While the national HIV infection rate is decreasing, the highest rates of infections continue among men who have sex with men (MSM), particularly minority MSM. It is important to understand attitudes, knowledge, and behaviors surrounding HIV prevention methods, such as pre-exposure prophylaxis (PrEP). In the present study, we created a snapshot of the PrEP continuum of care and identified participant demographic and sources of PrEP awareness factors that were associated with PrEP initiation. Data were collected using anonymous paper-based surveys employing a venue intercept procedure. A total of 188 HIV-negative men completed the survey at Miami Gay Pride 2018. Participants answered questions regarding demographics, PrEP use, and sources of PrEP awareness. The sample was majority Hispanic (55.4%), gay (83.0%), and single (57.7%). The constructed PrEP continuum revealed that a low proportion of those identified as PrEP naïve (n = 143) for HIV infection had PrEP interest (49/143). Moreover, among those who initiated PrEP (n = 45), a high proportion were retained in a PrEP program (37/45), with approximately half achieving medication adherence (25/45). Age group, PrEP knowledge, and source of PrEP awareness were all significantly associated with PrEP initiation. In areas with high HIV infection rates, studies like these offer crucial insight on how public health practitioners should proceed in the goal of decreasing HIV transmission rates. More research is needed to increase PrEP uptake and adherence.

Implementation and outcomes of a patient tracing programme for HIV in Trinidad and Tobago.

A patient tracing programme was implemented at an HIV clinic in Trinidad and Tobago to address the problem of defaulters from HIV care and non-adherence to antiretroviral treatment (ART). The study objective was to evaluate the implementation and outcomes of this programme conducted between April and September 2017. Using patient tracing contact methods, trained social workers attempted to contact 1058 patients lost to follow up (LTFU) between July 2016 and March 2017. Of the 1058 LTFU, 192 were ineligible: 27 (2.5%) were transferred to another clinic, 64 (6%) deceased, 35 (3.3%) hospitalised, 50 (4.7%) migrated and 16 (1.5%) incarcerated. Of the 866 eligible patients for patient tracing, 277 (32%) remained permanently LTFU and 589 (68%) were successfully contacted, re-engaged in care and received adherence counselling. Of the 589 who returned to care, 507 (86%) restarted ART. The three most common barriers reported among the 589 who were reengaged were 'forgetting their appointments' (20%), 'being too busy/work' (16%), and 'not wanting to be seen attending the HIV clinic' (12%). The study findings demonstrated the tracing programme as feasible for re-engaging those who are LTFU and highlighted barriers that can be addressed to further improve retention in HIV care among people living with HIV.

Prevalence of Cardiovascular Risk Factors Among Cancer Patients in the United States.

Background: Cancer and cardiovascular diseases (CVDs) are leading causes of morbidity and mortality. We analyzed national data to examine the prevalence of CVD risk factors among adult cancer survivors in the United States. Methods: Participants included adults ≥18 years of age from the National Health and Nutrition Examination Survey 2001-2002 to 2013-2014. CVD risk factors included hypertension, diabetes, dyslipidemia, obesity, smoking, and physical activity. Prevalence of 1, 2, or ≥3 CVD risk factors was compared between cancer and noncancer participants. All CVD risk factors were adjusted for age and smoking and additionally for sex. Differences in CVD risk factors among cancer and noncancer participants were identified using logistic regression analysis. Results: Among 35,379 eligible participants, 2906 (8.4%) had a history of cancer. The proportion of participants having a single CVD risk factor was lower among cancer survivors compared with noncancer participants (25.8% vs. 33.9%, P < 0.001). The proportions of participants having two CVD risk factors (33.5% vs. 24.6%, P < 0.001) and ≥3 CVD risk factors (27.4% vs. 16.4%, P < 0.001) were higher among cancer survivors. However, these associations lost significance upon adjusting for age. The odds of total hypertension (odds ratio [OR] 1.25, 95% confidence interval [CI]: 1.11-1.40) and total diabetes (OR 1.33, 95% CI: 1.08-1.65) were significantly higher among cancer survivors. Conclusions: Our study showed that adult cancer survivors in the United States had higher levels of CVD risk factors primarily due to age-related factors, in addition to cancer complications. There is a significant need for improved CVD risk assessment and prevention services for cancer survivors.

Zika Virus Awareness and Prevention Practices Among University Students in Miami: 2016.

In January 2016, the first case of mosquito-borne Zika infection in the mainland United States was confirmed in Miami, Florida. The first locally acquired case was reported 6 months later. Local public health and school officials began warning students of the outbreak on their return to the classroom in August 2016. In November-December 2016, we conducted a survey of students attending a large public university in Miami to determine how well informed they were about Zika. A multistage sampling design was used to contact teaching assistants and ask them for help in recruiting their students. Eligible students had to be 18 years of age or older and enrolled in at least one three-credit course during fall semester. A 25-item questionnaire based on the World Health Organization Zika Knowledge, Attitudes, and Practice Resource Pack was developed, pretested, and approved by the university's institutional review board before it was made available to eligible students through Blackboard Learn or a survey link. About half (50.4%) of the 139 respondents had heard about Zika prior to 2016. Only one student was unaware of Zika before our survey. Most (47.1%) first learned about Zika through television, 18.8% from family or friends, and 15.2% from the Internet, social media, or university e-mail. Two thirds (66.2%) believed Zika could be prevented, 15.1% thought it might be prevented, and 85.7% had taken some precautions. A high level of awareness of the risk of Zika infection was apparent. Most students reported taking steps to avoid exposure to the Zika virus.

Medicaid Expansion and Infant Mortality in the United States.

OBJECTIVES: To explore the effect of Medicaid expansion on US infant mortality rate. METHODS: We examined data from 2010 to 2016 and 2014 to 2016 to compare infant mortality rates in states and Washington, DC, that accepted the Affordable Care Act Medicaid expansion (Medicaid expansion states) and states that did not (non-Medicaid expansion states), stratifying data by race/ethnicity. RESULTS: Mean infant mortality rate in non-Medicaid expansion states rose (6.4 to 6.5) from 2014 to 2016 but declined in Medicaid expansion states (5.9 to 5.6). Mean difference in infant mortality rate in Medicaid expansion versus non-Medicaid expansion states increased from 0.573 (P = .08) in 2014 to 0.838 in 2016 (P = .006) because of smaller declines in non-Medicaid expansion (11.0%) than in Medicaid expansion (15.2%) states. The 14.5% infant mortality rate decline from 11.7 to 10.0 in African American infants in Medicaid expansion states was more than twice that in non-Medicaid expansion states (6.6%: 12.2 to 11.4; P = .012). CONCLUSIONS: Infant mortality rate decline was greater in Medicaid expansion states, with greater declines among African American infants. Future research should explore what aspects of Medicaid expansion may improve infant survival.

Recruiting and Engaging Older Men in Evidence-Based Health Promotion Programs: Perspectives on Barriers and Strategies.

Evidence-based health promotion programs are effective at reducing health risks and healthcare costs among older adults, but few men participate in the programs. This mixed methods study aimed to gain insight into the barriers to recruiting and engaging older men in evidence-based health promotion programs offered by the Healthy Aging Regional Collaborative of South Florida (HARC). Fourteen program coordinators participated in a focus group to identify barriers and strategies to improve male participation, and 49 instructors participated in a survey to triangulate the findings. Themes among barriers to male participation included women outnumbering men in the implementation sites and programs, conflict between male gender roles and the programs, and preference for other activities. Themes among strategies included public support of programs by male community leaders, program advertisements featuring males, and adapting program content. Survey results supported themes identified in the focus group. Nearly 78% of the survey respondents agreed that the perception of exercise programs as feminine was a barrier and over 90% of the survey respondents believed program advertisements featuring men would increase male participation. Findings indicate that health promotion programs and recruiting strategies need to be tailored to the unique needs and preferences of older men to improve participation.

Pandiastolic antegrade flow in patient with severe right ventricle to pulmonary artery conduit stenosis: An interesting phenomenon.

In a post operative tetralogy of fallot (TOF) physiology patient, abnormal right ventricular (RV) function remains the greatest matter of concern. Due to restrictive RV diastolic dysfunction, there is detectable antegrade diastolic flow in the pulmonary artery during atrial systole. We report a case of 21 year old male patient with total correction done in infancy using right ventricle to pulmonary artery conduit. He was relatively asymptomatic with a unique pattern of antegrade diastolic flow in both early and late diastolic phases (pan diastolic). This physiology was supportive and made him relatively asymptomatic. We discuss the physiology and clinical implication of the same.

Survival analysis for white non-Hispanic female breast cancer patients.

BACKGROUND: Race and ethnicity are significant factors in predicting survival time of breast cancer patients. In this study, we applied advanced statistical methods to predict the survival of White non-Hispanic female breast cancer patients, who were diagnosed between the years 1973 and 2009 in the United States (U.S.). MATERIALS AND METHODS: Demographic data from the Surveillance Epidemiology and End RESULTS (SEER) database were used for the purpose of this study. Nine states were randomly selected from 12 U.S. cancer registries. A stratified random sampling method was used to select 2,000 female breast cancer patients from these nine states. We compared four types of advanced statistical probability models to identify the best-fit model for the White non- Hispanic female breast cancer survival data. Three model building criterion were used to measure and compare goodness of fit of the models. These include Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC). In addition, we used a novel Bayesian method and the Markov Chain Monte Carlo technique to determine the posterior density function of the parameters. After evaluating the model parameters, we selected the model having the lowest DIC value. Using this Bayesian method, we derived the predictive survival density for future survival time and its related inferences. RESULTS: The analytical sample of White non-Hispanic women included 2,000 breast cancer cases from the SEER database (1973-2009). The majority of cases were married (55.2%), the mean age of diagnosis was 63.61 years (SD = 14.24) and the mean survival time was 84 months (SD = 35.01). After comparing the four statistical models, results suggested that the exponentiated Weibull model (DIC= 19818.220) was a better fit for White non-Hispanic females' breast cancer survival data. This model predicted the survival times (in months) for White non-Hispanic women after implementation of precise estimates of the model parameters. CONCLUSIONS: By using modern model building criteria, we determined that the data best fit the exponentiated Weibull model. We incorporated precise estimates of the parameter into the predictive model and evaluated the survival inference for the White non-Hispanic female population. This method of analysis will assist researchers in making scientific and clinical conclusions when assessing survival time of breast cancer patients.

Morphometric Study of Coeliac Trunk Specific Reference to Hepatic Artery Pattern in the West-Indian Population.

The aim of this study was to analyze anatomy of the celiac trunk through its diameter, length, and variation of its branches. We studied 40 cadavers (25 males and 15 females) in the various colleges in the west India for the variation in the celiac trunk. Dissection of the celiac trunk was performed after opening of the peritoneal cavity. The length of the celiac trunk up to the common hepatic artery was observed. Diameter of the celiac trunk and distance between the celiac trunk and the superior mesenteric artery were observed. We found cases of rare vascular variation in the branching pattern and the common hepatic artery, which arises from the superior mesenteric artery and there is abnormal relation between the common hepatic artery portal vein and the bile duct. In a case we have observed that the superior mesenteric artery gives acute angulations downward on the right side. This type of study of celiac trunk and presence of variation in hepatic arteries will allow the surgeon to practice safe laparoscopic cholecystectomy, liver resections, or vascular recombination in transplantation and, thereby, avoid errors and patient morbidity.