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.

Five-Year Review of an International Clinical Research-Training Program

The exponential increase in clinical research has profoundly changed medical sciences. Evidence that has accumulated in the past three decades from clinical trials has led to the proposal that clinical care should not be based solely on clinical expertise and patient values, and should integrate robust data from systematic research. As a consequence, clinical research has become more complex and methods have become more rigorous, and evidence is usually not easily translated into clinical practice. Therefore, the instruction of clinical research methods for scientists and clinicians must adapt to this new reality. To address this challenge, a global distance-learning clinical research-training program was developed, based on collaborative learning, the pedagogical goal of which was to develop critical thinking skills in clinical research. We describe and analyze the challenges and possible solutions of this course after 5 years of experience (2008-2012) with this program. Through evaluation by students and faculty, we identified and reviewed the following challenges of our program: 1) student engagement and motivation, 2) impact of heterogeneous audience on learning, 3) learning in large groups, 4) enhancing group learning, 5) enhancing social presence, 6) dropouts, 7) quality control, and 8) course management. We discuss these issues and potential alternatives with regard to our research and background.