ABSTRACT
Video-based intelligent action recognition remains challenging in the field of computer vision.The review analyzes the state-of-the-art methods of video-based intelligent action recognition,including machine learning methods with handcrafted features,deep learning methods with automatically extracted features,and multi-information fusion methods.In addition,the important medical applications and limitations of these technologies in the past decade are introduced,and the interdisciplinary views on the future application to improve human health are also shared.
ABSTRACT
Cigarette smoking is the major risk factor for smoking-related interstitial fibrosis (SRIF). Despite recent advances, the molecular mechanisms involved in the initiation and progression of this disease remain elusive. We found 6 months of chronic mainstream smoking exposure induced SRIF in C57 mice, which was associated with pronounced enhanced oxidative stress, bronchoalveolar inflammation and fibrosis but not apoptosis of alveolar septal cell. We used Affymetrix microRNA (miRNA) arrays to determine the temporal alteration in global gene expression of peripheral blood during the progression of diffuse pulmonary interstitial fibrosis in C57 mice. Microarray analysis revealed the upregulation of 3 miRNAs (miR-92b, miR-700 and miR-668) and the downregulation of 5 miRNAs (let-7e, miR-142-5p, miR-350, miR-19a and miR191*) in the peripheral blood of mice exposed to mainstream smoking for 1, 2, 3 and 6 months. We proposed that circulating miRNAs might be promising biomarkers to reflect the dynamic pathological changes of SRIF related interstitial fibrosis.
Subject(s)
Biomarkers/blood , Lung Diseases, Interstitial/pathology , MicroRNAs/blood , MicroRNAs/genetics , Pulmonary Fibrosis/pathology , Smoking/adverse effects , Animals , Apoptosis , Body Weight , Down-Regulation , In Situ Nick-End Labeling , Inflammation , Lung Diseases, Interstitial/etiology , Male , Mice , Mice, Inbred C57BL , Microarray Analysis , Oxidative Stress/drug effects , Pulmonary Fibrosis/etiology , Risk Factors , Up-RegulationABSTRACT
Smoking, leading to over 438,000 annual deaths in the US and 92 billion US dollars in lost productivity, is an important risk factor for several diseases. Global smoking statistics for 2002 have shown that 80,000 to 100,000 children worldwide start smoking every day. Human biomonitoring nowadays has provided an efficient and cost-effective means of measuring human exposures and biological effects of smoking. To review the utility of biomarkers in reflecting the hazard from cigarette smoking, we comprehensively searched the Cochrane Library, Medline and EMbase from 1966 to May 2010 with the language limit of English. We found that the currently used biomarkers, such as tobacco-specific metabolites, smoking-induced genotoxic products, may not scientifically reflect the hazard from cigarette smoking. More research is needed to find out more effective biomarkers for estimating hazards from cigarette smoking. This paper is expected to help researchers understand the current utilization of biomarkers related to cigarette smoking and to provide suggestive guides to tobacco companies in producing less-toxic cigarettes, thus to provide a safe way to smoke.