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.

The Role of the Humoral Immune Response in the Molecular Evolution of the Envelope C2, V3 and C3 Regions in Chronically HIV-2 Infected Patients

BACKGROUND: This study was designed to investigate, for the first time, the short-term molecular evolution of the HIV-2 C2, V3 and C3 envelope regions and its association with the immune response. Clonal sequences of the env C2V3C3 region were obtained from a cohort of eighteen HIV-2 chronically infected patients followed prospectively during 2-4 years. Genetic diversity, divergence, positive selection and glycosylation in the C2V3C3 region were analysed as a function of the number of CD4+ T cells and the anti-C2V3C3 IgG and IgA antibody reactivity RESULTS: The mean intra-host nucleotide diversity was 2.1% (SD, 1.1%), increasing along the course of infection in most patients. Diversity at the amino acid level was significantly lower for the V3 region and higher for the C2 region. The average divergence rate was 0.014 substitutions/site/year, which is similar to that reported in chronic HIV-1 infection. The number and position of positively selected sites was highly variable, except for codons 267 and 270 in C2 that were under strong and persistent positive selection in most patients. N-glycosylation sites located in C2 and V3 were conserved in all patients along the course of infection. Intra-host variation of C2V3C3-specific IgG response over time was inversely associated with the variation in nucleotide and amino acid diversity of the C2V3C3 region. Variation of the C2V3C3-specific IgA response was inversely associated with variation in the number of N-glycosylation sites. CONCLUSION: The evolutionary dynamics of HIV-2 envelope during chronic aviremic infection is similar to HIV-1 implying that the virus should be actively replicating in cellular compartments. Convergent evolution of N-glycosylation in C2 and V3, and the limited diversification of V3, indicates that there are important functional constraints to the potential diversity of the HIV-2 envelope. C2V3C3-specific IgG antibodies are effective at reducing viral population size limiting the number of virus escape mutants. The C3 region seems to be a target for IgA antibodies and increasing N-linked glycosylation may prevent HIV-2 envelope recognition by these antibodies. Our results provide new insights into the biology of HIV-2 and its relation with the human host and may have important implications for vaccine design.