Automatic Small Bowel Tumor Diagnosis by Using Multi-Scale Wavelet-Based Analysis in Wireless Capsule Endoscopy Images

BACKGROUND: Wireless capsule endoscopy has been introduced as an innovative, non-invasive diagnostic technique for evaluation of the gastrointestinal tract, reaching places where conventional endoscopy is unable to. However, the output of this technique is an 8 hours video, whose analysis by the expert physician is very time consuming. Thus, a computer assisted diagnosis tool to help the physicians to evaluate CE exams faster and more accurately is an important technical challenge and an excellent economical opportunity. METHOD: The set of features proposed in this paper to code textural information is based on statistical modeling of second order textural measures extracted from co-occurrence matrices. To cope with both joint and marginal non-Gaussianity of second order textural measures, higher order moments are used. These statistical moments are taken from the two-dimensional color-scale feature space, where two different scales are considered. Second and higher order moments of textural measures are computed from the co-occurrence matrices computed from images synthesized by the inverse wavelet transform of the wavelet transform containing only the selected scales for the three color channels. The dimensionality of the data is reduced by using Principal Component Analysis. RESULTS: The proposed textural features are then used as the input of a classifier based on artificial neural networks. Classification performances of 93.1% specificity and 93.9% sensitivity are achieved on real data. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis systems to assist physicians in their clinical practice.

Regulatory Cells, Cytokine Pattern and Clinical Risk Factors for Asthma in Infants and Young Children with Recurrent Wheeze

Several risk factors for asthma have been identified in infants and young children with recurrent wheeze. However, published literature has reported contradictory findings regarding the underlying immunological mechanisms. OBJECTIVES: This study was designed to assess and compare the immunological status during the first 2 years in steroid-naive young children with >or= three episodes of physician-confirmed wheeze (n=50), with and without clinical risk factors for developing subsequent asthma (i.e. parental asthma or a personal history of eczema and/or two of the following: wheezing without colds, a personal history of allergic rhinitis and peripheral blood eosinophilia >4%), with age-matched healthy controls (n=30). METHODS: Peripheral blood CD4(+)CD25(+) and CD4(+)CD25(high) T cells and their cytotoxic T-lymphocyte-associated antigen-4 (CTLA-4), GITR and Foxp3 expression were analysed by flow cytometry. Cytokine (IFN-gamma, TGF-beta and IL-10), CTLA-4 and Foxp3 mRNA expression were evaluated (real-time PCR) after peripheral blood mononuclear cell stimulation with phorbol 12-myristate 13-acetate (PMA) (24 h) and house dust mite (HDM) extracts (7th day). RESULTS: Flow cytometry results showed a significant reduction in the absolute number of CD4(+)CD25(high) and the absolute and percentage numbers of CD4(+)CD25(+)CTLA-4(+) in wheezy children compared with healthy controls. Wheezy children at a high risk of developing asthma had a significantly lower absolute number of CD4(+)CD25(+) (P=0.01) and CD4(+)CD25(high) (P=0.04), compared with those at a low risk. After PMA stimulation, CTLA-4 (P=0.03) and Foxp3 (P=0.02) expression was diminished in wheezy children compared with the healthy children. After HDM stimulation, CTLA-4 (P=0.03) and IFN-gamma (P=0.04) expression was diminished in wheezy children compared with healthy children. High-risk children had lower expression of IFN-gamma (P=0.03) compared with low-risk and healthy children and lower expression of CTLA-4 (P=0.01) compared with healthy children. CONCLUSIONS: Although our findings suggest that some immunological parameters are impaired in children with recurrent wheeze, particularly with a high risk for asthma, further studies are needed in order to assess their potential as surrogate predictor factors for asthma in early life.