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 Use of Statins in People at Risk of Developing Diabetes Mellitus: Evidence and Guidance for Clinical Practice

Reducing low-density lipoprotein cholesterol (LDL-C) levels using statins is associated with significant reductions in cardiovascular (CV) events in a wide range of patient populations. Although statins are generally considered to be safe, recent studies suggest they are associated with an increased risk of developing Type 2 diabetes (T2D). This led the US Food and Drug Administration (FDA) to change their labelling requirements for statins to include a warning about the possibility of increased blood sugar and HbA1c levels and the European Medicines Agency (EMA) to issue guidance on a small increased risk of T2D with the statin class. This review examines the evidence leading to these claims and provides practical guidance for primary care physicians on the use of statins in people with or at risk of developing T2D. Overall, evidence suggests that the benefits of statins for the reduction of CV risk far outweigh the risk of developing T2D, especially in individuals with higher CV risk. To reduce the risk of developing T2D, physicians should assess all patients for T2D risk prior to starting statin therapy, educate patients about their risks, and encourage risk-reduction through lifestyle changes. Whether some statins are more diabetogenic than others requires further study. Statin-treated patients at high risk of developing T2D should regularly be monitored for changes in blood glucose or HbA1c levels, and the risk of conversion from pre-diabetes to T2D should be reduced by intensifying lifestyle changes. Should a patient develop T2D during statin treatment, physicians should continue with statin therapy and manage T2D in accordance with relevant national guidelines.