Learn More
OBJECTIVES To develop a general structure for semantic image analysis that is suitable for content-based image retrieval in medical applications and an architecture for its efficient implementation. METHODS Stepwise content analysis of medical images results in six layers of information modeling incorporating medical expert knowledge (raw data layer,(More)
Content-based image retrieval requires a formal description of visual information. In medical applications, all relevant biological objects have to be represented by this description. Although color as the primary feature has proven successful in publicly available retrieval systems of general purpose, this description is not applicable to most medical(More)
Picture archiving and communication systems (PACS) aim to efficiently provide the radiologists with all images in a suitable quality for diagnosis. Modern standards for digital imaging and communication in medicine (DICOM) comprise alphanumerical descriptions of study, patient, and technical parameters. Currently, this is the only information used to select(More)
The objective of this work is to develop a general structure for semantic image analysis that is suitable for content-based image retrieval in medical applications and an architecture for its efficient implementation. Stepwise content analysis of medical images results in six layers of information modeling (raw data layer, registered data layer, feature(More)
Most of the estimated 125,000 injection drug users (IDUs) in Canada use illicit opioids and are outside treatment (i.e., methadone maintenance treatment). Empirical data suggest that illicit opioid users outside treatment are characterized by various health and social problem characteristics, including polydrug use, physical and mental morbidity, social(More)
Recent research has suggested that there is no general similarity measure, which can be applied on arbitrary databases without any parameterization. Hence, the optimal combination of similarity measures and parameters must be identified for each new image repository. This optimization loop is time consuming and depends on the experience of the designer as(More)
OBJECTIVES To summarize key characteristics and consequences of illicit opioid use from the literature and to present corresponding data from a multisite sample of illicit opioid users in 5 Canadian cities (OPICAN study). METHOD We undertook an overview of recent literature from North America, Australia, and Europe. We obtained data from the multicity(More)
INTRODUCTION Studies have shown important gender differences among drug (including crack) users related to: drug use patterns; health risks and consequences; criminal involvement; and service needs/use. Crack use is prevalent in Brazil; however, few comparative data by sex exist. We examined and compared by sex key drug use, health, socio-economic(More)
BACKGROUND Crack use is prevalent among street drug users in Brazilian cities, yet despite recent help system reforms and investments, treatment utilization is low. Other studies have identified a variety of - often inconsistent - factors associated with treatment status among crack or other drug users. This study compared socio-economic, drug use, health(More)
Debates about which policy initiatives can prevent or reduce the damage that illicit drugs cause to the public good are rarely informed by scientific evidence. Fortunately, evidence-based interventions are increasingly being identified that are capable of making drugs less available, reducing violence in drug markets, lessening misuse of legal(More)