“Signal, image and video processing” special issue: Semantic representations for social behavior analysis in video surveillance systems

No abstract available

Molecular surveillance for carbapenemase genes in carbapenem-resistant Pseudomonas aeruginosa in Australian patients with cystic fibrosis.

Summary: The aim of this study was to assess the prevalence of acquired carbapenemase genes amongst carbapenem non-susceptible Pseudomonas aeruginosa isolates in Australian patients with cystic fibrosis (CF). Cross-sectional molecular surveillance for acquired carbapenemase genes was performed on CF P. aeruginosa isolates from two isolate banks comprising: (i) 662 carbapenem resistant P. aeruginosa isolates from 227 patients attending 10 geographically diverse Australian CF centres (2007-2009), and (ii) 519 P. aeruginosa isolates from a cohort of 173 adult patients attending one Queensland CF clinic in 2011. All 1189 P. aeruginosa isolates were tested by polymerase chain reaction (PCR) protocols targeting ten common carbapenemase genes, as well the Class 1 integron intI1 gene and the aadB aminoglycoside resistance gene. No carbapenemase genes were identified among all isolates tested. The intI1 and aadB genes were frequently detected and were significantly associated with the AUST-02 strain (OR 24.6, 95% CI 9.3-65.6; p < 0.0001) predominantly from Queensland patients. Despite the high prevalence of carbapenem resistance in P. aeruginosa in Australian patients with CF, no acquired carbapenemase genes were detected in the study, suggesting chromosomal mutations remain the key resistance mechanism in CF isolates. Systematic surveillance for carbapenemase-producing P. aeruginosa in CF by molecular surveillance is ongoing.

Evidence reasoning for event inference in smart transport video surveillance

In this paper we present a new event recognition framework, based on the Dempster-Shafer theory of evidence, which combines the evidence from multiple atomic events detected by low-level computer vision analytics. The proposed framework employs evidential network modelling of composite events. This approach can effectively handle the uncertainty of the detected events, whilst inferring high-level events that have semantic meaning with high degrees of belief. Our scheme has been comprehensively evaluated against various scenarios that simulate passenger behaviour on public transport platforms such as buses and trains. The average accuracy rate of our method is 81% in comparison to 76% by a standard rule-based method.

A Game-Theoretic Approach for Threats Detection and Intervention in Surveillance

Threat prevention with limited security resources is a challenging problem. An optimal strategy is to eectively predict attackers' targets (or goals) based on current available information, and use such predictions to prevent (or disrupt) their planned attacks. In this paper, we propose a game-theoretic framework to address this challenge which encompasses the following three elements. First, we design a method to analyze an attacker's types in order to determine the most plausible type of an attacker. Second, we propose an approach to predict possible targets of an attack and the course of actions that the attackers may take even when the attackers' types are ambiguous. Third, a game-theoretic based strategy is developed to determine the best protection actions for defenders (security resources).

Game-­theoretic Resource Allocation with Real-­time Probabilistic Surveillance Information

Game-theoretic security resource allocation problems have generated significant interest in the area of designing and developing security systems. These approaches traditionally utilize the Stackelberg game model for security resource scheduling in order to improve the protection of critical assets. The basic assumption in Stackelberg games is that a defender will act first, then an attacker will choose their best response after observing the defender’s strategy commitment (e.g., protecting a specific asset). Thus, it requires an attacker’s full or partial observation of a defender’s strategy. This assumption is unrealistic in real-time threat recognition and prevention. In this paper, we propose a new solution concept (i.e., a method to predict how a game will be played) for deriving the defender’s optimal strategy based on the principle of acceptable costs of minimax regret. Moreover, we demonstrate the advantages of this solution concept by analyzing its properties.

Hui and Walter's latent-class model extended to estimate diagnostic test properties from surveillance data: a latent model for latent data

Diagnostic test sensitivity and specificity are probabilistic estimates with far reaching implications for disease control, management and genetic studies. In the absence of 'gold standard' tests, traditional Bayesian latent class models may be used to assess diagnostic test accuracies through the comparison of two or more tests performed on the same groups of individuals. The aim of this study was to extend such models to estimate diagnostic test parameters and true cohort-specific prevalence, using disease surveillance data. The traditional Hui-Walter latent class methodology was extended to allow for features seen in such data, including (i) unrecorded data (i.e. data for a second test available only on a subset of the sampled population) and (ii) cohort-specific sensitivities and specificities. The model was applied with and without the modelling of conditional dependence between tests. The utility of the extended model was demonstrated through application to bovine tuberculosis surveillance data from Northern and the Republic of Ireland. Simulation coupled with re-sampling techniques, demonstrated that the extended model has good predictive power to estimate the diagnostic parameters and true herd-level prevalence from surveillance data. Our methodology can aid in the interpretation of disease surveillance data, and the results can potentially refine disease control strategies.

Gleason Upgrading with Time in a Large Prostate Cancer Active Surveillance Cohort

PURPOSE: We report the percentage of patients on active surveillance who had disease pathologically upgraded and factors that predict for upgrading on surveillance biopsies.

MATERIALS AND METHODS: Patients in our active surveillance database with at least 1 repeat prostate biopsy were included. Histological upgrading was defined as any increase in primary or secondary Gleason grade on repeat biopsy. Multivariate analysis was used to determine baseline and dynamic factors associated with Gleason upgrading. This information was used to develop a nomogram to predict for upgrading or treatment in patients electing for active surveillance.

RESULTS: Of 862 patients in our cohort 592 had 2 or more biopsies. Median followup was 6.4 years. Of the patients 20% were intermediate risk, 0.3% were high risk and all others were low risk. During active surveillance 31.3% of cases were upgraded. On multivariate analysis clinical stage T2, higher prostate specific antigen and higher percentage of cores involved with disease at the time of diagnosis predicted for upgrading. A total of 27 cases (15% of those upgraded) were Gleason 8 or higher at upgrading, and 62% of all 114 upgraded cases went on to have active treatment. The nomogram incorporated clinical stage, age, prostate specific antigen, core positivity and Gleason score. The concordance index was 0.61.

CONCLUSIONS: In this large re-biopsy cohort with medium-term followup, most cases have not been pathologically upgraded to date. A model predicting for upgrading or radical treatment was developed which could be useful in counseling patients considering active surveillance for prostate cancer.

Long-Term Follow-Up of a Large Active Surveillance Cohort of Patients With Prostate Cancer

PURPOSE: Active surveillance is increasingly accepted as a treatment option for favorable-risk prostate cancer. Long-term follow-up has been lacking. In this study, we report the long-term outcome of a large active surveillance protocol in men with favorable-risk prostate cancer.

PATIENTS AND METHODS: In a prospective single-arm cohort study carried out at a single academic health sciences center, 993 men with favorable- or intermediate-risk prostate cancer were managed with an initial expectant approach. Intervention was offered for a prostate-specific antigen (PSA) doubling time of less than 3 years, Gleason score progression, or unequivocal clinical progression. Main outcome measures were overall and disease-specific survival, rate of treatment, and PSA failure rate in the treated patients.

RESULTS: Among the 819 survivors, the median follow-up time from the first biopsy is 6.4 years (range, 0.2 to 19.8 years). One hundred forty-nine (15%) of 993 patients died, and 844 patients are alive (censored rate, 85.0%). There were 15 deaths (1.5%) from prostate cancer. The 10- and 15-year actuarial cause-specific survival rates were 98.1% and 94.3%, respectively. An additional 13 patients (1.3%) developed metastatic disease and are alive with confirmed metastases (n = 9) or have died of other causes (n = 4). At 5, 10, and 15 years, 75.7%, 63.5%, and 55.0% of patients remained untreated and on surveillance. The cumulative hazard ratio for nonprostate-to-prostate cancer mortality was 9.2:1.

CONCLUSION: Active surveillance for favorable-risk prostate cancer is feasible and seems safe in the 15-year time frame. In our cohort, 2.8% of patients have developed metastatic disease, and 1.5% have died of prostate cancer. This mortality rate is consistent with expected mortality in favorable-risk patients managed with initial definitive intervention.

Handling Sequential Observations in Intelligent Surveillance

Demand for intelligent surveillance in public transport systems is growing due to the increased threats of terrorist attack, vandalism and litigation. The aim of intelligent surveillance is in-time reaction to information received from various monitoring devices, especially CCTV systems. However, video analytic algorithms can only provide static assertions, whilst in reality, many related events happen in sequence and hence should be modeled sequentially. Moreover, analytic algorithms are error-prone, hence how to correct the sequential analytic results based on new evidence (external information or later sensing discovery) becomes an interesting issue. In this paper, we introduce a high-level sequential observation modeling framework which can support revision and update on new evidence. This framework adapts the situation calculus to deal with uncertainty from analytic results. The output of the framework can serve as a foundation for event composition. We demonstrate the significance and usefulness of our framework with a case study of a bus surveillance project.

Evidential event inference in transport video surveillance

This paper presents a new framework for multi-subject event inference in surveillance video, where measurements produced by low-level vision analytics usually are noisy, incomplete or incorrect. Our goal is to infer the composite events undertaken by each subject from noise observations. To achieve this, we consider the temporal characteristics of event relations and propose a method to correctly associate the detected events with individual subjects. The Dempster–Shafer (DS) theory of belief functions is used to infer events of interest from the results of our vision analytics and to measure conflicts occurring during the event association. Our system is evaluated against a number of videos that present passenger behaviours on a public transport platform namely buses at different levels of complexity. The experimental results demonstrate that by reasoning with spatio-temporal correlations, the proposed method achieves a satisfying performance when associating atomic events and recognising composite events involving multiple subjects in dynamic environments.

Adjusting HIV Prevalence Estimates for Non-participation: an Application to Demographic Surveillance

Introduction: HIV testing is a cornerstone of efforts to combat the HIV epidemic, and testing conducted as part of surveillance provides invaluable data on the spread of infection and the effectiveness of campaigns to reduce the transmission of HIV. However, participation in HIV testing can be low, and if respondents systematically select not to be tested because they know or suspect they are HIV positive (and fear disclosure), standard approaches to deal with missing data will fail to remove selection bias. We implemented Heckman-type selection models, which can be used to adjust for missing data that are not missing at random, and established the extent of selection bias in a population-based HIV survey in an HIV hyperendemic community in rural South Africa.

Methods: We used data from a population-based HIV survey carried out in 2009 in rural KwaZulu-Natal, South Africa. In this survey, 5565 women (35%) and 2567 men (27%) provided blood for an HIV test. We accounted for missing data using interviewer identity as a selection variable which predicted consent to HIV testing but was unlikely to be independently associated with HIV status. Our approach involved using this selection variable to examine the HIV status of residents who would ordinarily refuse to test, except that they were allocated a persuasive interviewer. Our copula model allows for flexibility when modelling the dependence structure between HIV survey participation and HIV status.

Results: For women, our selection model generated an HIV prevalence estimate of 33% (95% CI 27–40) for all people eligible to consent to HIV testing in the survey. This estimate is higher than the estimate of 24% generated when only information from respondents who participated in testing is used in the analysis, and the estimate of 27% when imputation analysis is used to predict missing data on HIV status. For men, we found an HIV prevalence of 25% (95% CI 15–35) using the selection model, compared to 16% among those who participated in testing, and 18% estimated with imputation. We provide new confidence intervals that correct for the fact that the relationship between testing and HIV status is unknown and requires estimation.

Conclusions: We confirm the feasibility and value of adopting selection models to account for missing data in population-based HIV surveys and surveillance systems. Elements of survey design, such as interviewer identity, present the opportunity to adopt this approach in routine applications. Where non-participation is high, true confidence intervals are much wider than those generated by standard approaches to dealing with missing data suggest.