Perinatal Bacterial Infection: Screenning of Vertical Transmitted Infections

Perinatal bacterial infection may be caused by any microorganism colonizing the vaginal tract. Neonatologists and paediatricians are especially concerned about group B Stretpococcus (GBS). However, Enterobactereacea, mainly E.coli and Proteus, are also responsible for infection. GBS screening may be accomplished in over 90% of pregnant women. In our maternity in 2007-2008, 85% of the mothers had been screened. Screening and prophylaxis were responsible for a decreasing incidence of neonatal infection - from 0.6/1000 to 0.15/1000 live births in Portugal, from 2002 to 2007. However there are some difficulties related to screening. In the second Portuguese study 16/57 NB with early-onset infection (28%) were born to “negative” mothers. Several factors illustrate how difficult is to draw national screening policies: a wide range of carrier’s state rate throughout a country - in Portugal from 12% to 30%. The success of any screening policy may also be affected by additional technical and organizational problems. In countries where home delivery is a tradition or a trend intrapartum GBS prophylaxis requires a very well organized assistance.. Moreover factors usually accepted as protective are not so effective. In the Portuguese study 24/57 infected newborns (42%) were delivery by caesarean section. Another subject deals with the workload in the postnatal ward generated by deficient compliance to the guidelines a problem not confirm by a study of our group. Decreasing the importance of GBS, highlight the importance of E. coli in perinatal infection. From the 16 340 registrations of the National Registry 1676 were newborns with mother-related infection. Applying the same reasoning to E.coli as to GBS and Listeria monocytogenes – that is considering all of them are of maternal origin - 6.7% of these infections were due to E. coli, 4.6% to SGB and 0.5% to Listeria monocytogenes. In conclusion screening and prophylaxis may be not the best way to prevent all GBS neonatal infections but by now it is the only available procedure. The other bacteria continue to demand a high suspicion level and immediate intervention.

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.