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.

Low Socioeconomic Status is an Independent Risk Factor for Survival After Abdominal Aortic Aneurysm Repair and Open Surgery for Peripheral Artery Disease

OBJECTIVE/BACKGROUND: The association between socioeconomic status (SES), presentation, and outcome after vascular surgery is largely unknown. This study aimed to determine the influence of SES on post-operative survival and severity of disease at presentation among vascular surgery patients in the Dutch setting of equal access to and provision of care. METHODS: Patients undergoing surgical treatment for peripheral artery disease (PAD), abdominal aortic aneurysm (AAA), or carotid artery stenosis between January 2003 and December 2011 were retrospectively included. The association between SES, quantified by household income, disease severity at presentation, and survival was studied using logistic and Cox regression analysis adjusted for demographics, and medical and behavioral risk factors. RESULTS: A total of 1,178 patients were included. Low income was associated with worse post-operative survival in the PAD cohort (n = 324, hazard ratio 1.05, 95% confidence interval [CI] 1.00-1.10, per 5,000 Euro decrease) and the AAA cohort (n = 440, quadratic relation, p = .01). AAA patients in the lowest income quartile were more likely to present with a ruptured aneurysm (odds ratio [OR] 2.12, 95% CI 1.08-4.17). Lowest income quartile PAD patients presented more frequently with symptoms of critical limb ischemia, although no significant association could be established (OR 2.02, 95% CI 0.96-4.26). CONCLUSIONS: The increased health hazards observed in this study are caused by patient related factors rather than differences in medical care, considering the equality of care provided by the study setting. Although the exact mechanism driving the association between SES and worse outcome remains elusive, consideration of SES as a risk factor in pre-operative decision making and focus on treatment of known SES related behavioral and psychosocial risk factors may improve the outcome of patients with vascular disease.