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.

Variation in Haemodynamic Monitoring for Major Surgery in European Nations: Secondary Analysis of the EuSOS Dataset

BACKGROUND: The use of cardiac output monitoring may improve patient outcomes after major surgery. However, little is known about the use of this technology across nations. METHODS: This is a secondary analysis of a previously published observational study. Patients aged 16 years and over undergoing major non-cardiac surgery in a 7-day period in April 2011 were included into this analysis. The objective is to describe prevalence and type of cardiac output monitoring used in major surgery in Europe. RESULTS: Included in the analysis were 12,170 patients from the surgical services of 426 hospitals in 28 European nations. One thousand four hundred and sixteen patients (11.6 %) were exposed to cardiac output monitoring, and 2343 patients (19.3 %) received a central venous catheter. Patients with higher American Society of Anesthesiologists (ASA) scores were more frequently exposed to cardiac output monitoring (ASA I and II, 643 patients [8.6 %]; ASA III-V, 768 patients [16.2 %]; p < 0.01) and central venous catheter (ASA I and II, 874 patients [11.8 %]; ASA III-V, 1463 patients [30.9 %]; p < 0.01). In elective surgery, 990 patients (10.8 %) were exposed to cardiac output monitoring, in urgent surgery 252 patients (11.7 %) and in emergency surgery 173 patients (19.8 %). A central venous catheter was used in 1514 patients (16.6 %) undergoing elective, in 480 patients (22.2 %) undergoing urgent and in 349 patients (39.9 %) undergoing emergency surgery. Nine hundred sixty patients (7.9 %) were monitored using arterial waveform analysis, 238 patients (2.0 %) using oesophageal Doppler ultrasound, 55 patients (0.5 %) using a pulmonary artery catheter and 44 patients (2.0 %) using other technologies. Across nations, cardiac output monitoring use varied from 0.0 % (0/249 patients) to 27.5 % (19/69 patients), whilst central venous catheter use varied from 5.6 % (7/125 patients) to 43.2 % (16/37 patients). CONCLUSIONS: One in ten patients undergoing major surgery is exposed to cardiac output monitoring whilst one in five receives a central venous catheter. The use of both technologies varies widely across Europe.