This paper describes an experimental computer-aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has proven useful for medical decision support in previous works from our team. In the proposed framework, the breasts are first partitioned adaptively into regions. Then, either textural features, or features derived from the detection of masses and microcalcifications, are extracted from each region. Finally, feature vectors extracted from each region are combined using an MIL algorithm (Citation k-NN or mi-Graph), in order to recognize "normal" mammography examinations or to categorize examinations as "normal", "benign" or "cancer". An accuracy of 91.1% (respectively 62.1%) was achieved for normality recognition (respectively three-class categorization) in a subset of 720 mammograms from the DDSM dataset. The paper also discusses future improvements, that will make the most of the MIL paradigm, in order to improve "benign" versus "cancer" discrimination in particular.
Embase, Scielo and LILACS using the key words "multiple sclerosis" and "esclerosis múltiple" plus "Latin America" and all country names. Full articles or abstracts from meetings reporting original research on cost or economic analyses, budget impact or resource utilization were obtained. No restrictions were placed on publication date or language. All work was done in duplicate by two independent reviewers with adjudication by consensus discussion. Results: We identified 1482 papers, of which 27 were considered for analysis. There were 7 economic analyses (5 costeffectiveness, 2 cost-utility), 5 budget impact analyses, 10 cost analyses (6 drug expenditures and 4 cost of illness), 4 on resource utilization and 1 on productivity loss. Studies were obtained from 5 countries (18 Brazil, 3 Argentina, 3 Colombia, 2 Mexico, 1 Chile). Mostly (22/27, 81%) were published as abstracts; 5 were published as full text articles (19%). Dates for these publications ranged from 2002 to 2013, with an exponential increase over time. The number of MS patients is increasing rapidly (71% increase in Brazil between 2006 and 2009). However, hospitalization rates (overall and per patient) have been decreasing, as newer more effective drugs have been increasingly used. Disease modulating therapies are predominantly used. Costs of care are quite high and have risen dramatically, e. g. > 200% in Brazil between 2007-2012, with beta-interferons mostly used (78%). Some high cost drugs such as fingolimod and natalizumab have been found cost-effective over older drugs such as beta-interferons or glatiramer acetate in Mexico, Brazil and Colombia, with modest impact on budgets. ConClusions: Very little evidence related to cost of MS has been produced in Latin America. More research is needed to better support decisions regarding care of MS patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.