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.

Disruption of Urate Transport in Familial Renal Glucosuria and Report on SGLT2 Expression in Normal and Pathological Kidney

Familial renal glucosuria (FRG) is a rare co -dominantly inherited benign phenotype characterized by the presence of glucose in the urine. It is caused by mutations in the SLC5A2 gene that encodes SGLT2, a Na+ -glucose co -transporter. The purpose of our current work was twofold: to characterize the molecular and phenotype findings of an FRG cohort and, in addition, to detail the SGLT2 expression in the adult human kidney. The phenotype of FRG pedigrees was evaluated using direct sequencing for the identification of sequence variations in the SLC5A2 gene. The expression of SGLT2 in the adult human kidney was studied by immunofluorescence on kidney biopsy specimens. In the absence of renal biopsies from FRG individuals, and in order to evaluate the potential disruption of SGLT2 expression in a glucosuric nephropathy, we have selected cases of nucleoside analogues induced proximal tubular toxicity. We identified six novel SLC5A2 mutations in six FRG pedigrees and described the occurrence of hyperuricosuria associated with hypouricaemia in the two probands with the most severe phenotypes. Histopathological studies proved that SGLT2 is localized to the brush -border of the proximal tubular epithelia cell and that this normal pattern was found to be disrupted in cases of nucleoside analogues induced tubulopathy. We present six novel SLC5A2 mutations, further contributing to the allelic heterogeneity in FRG, and identified hyperuricosuria and hypouricaemia as part of the FRG phenotype. SGLT2 is localized to the brush -border of the proximal tubule in the adult human normal kidney, and aberrant expression of the co -transporter may underlie the glucosuria seen with the use of nucleoside analogues.