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 Arterial Switch Operation in Europe for Transposition of the Great Arteries: a Multi-Institutional Study from the European Congenital Heart Surgeons Association

OBJECTIVES: This study analyzes the results of the arterial switch operation for transposition of the great arteries in member institutions of the European Congenital Heart Surgeons Association. METHODS: The records of 613 patients who underwent primary arterial switch operations in each of 19 participating institutions in the period from January 1998 through December 2000 were reviewed retrospectively. RESULTS: A ventricular septal defect was present in 186 (30%) patients. Coronary anatomy was type A in 69% of the patients, and aortic arch pathology was present in 20% of patients with ventricular septal defect. Rashkind septostomy was performed in 75% of the patients, and 69% received prostaglandin. There were 37 hospital deaths (operative mortality, 6%), 13 (3%) for patients with an intact ventricular septum and 24 (13%) for those with a ventricular septal defect (P < .001). In 36% delayed sternal closure was performed, 8% required peritoneal dialysis, and 2% required mechanical circulatory support. Median ventilation time was 58 hours, and intensive care and hospital stay were 6 and 14 days, respectively. Although of various preoperative risk factors the presence of a ventricular septal defect, arch pathology, and coronary anomalies were univariate predictors of operative mortality, only the presence of a ventricular septal defect approached statistical significance (P = .06) on multivariable analysis. Of various operative parameters, aortic crossclamp time and delayed sternal closure were also univariate predictors; however, only the latter was an independent statistically significant predictor of death. CONCLUSIONS: Results of the procedure in European centers are compatible with those in the literature. The presence of a ventricular septal defect is the clinically most important preoperative risk factor for operative death, approaching statistical significance on multivariable analysis.