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.

Lack of Spontaneous Venous Pulsation: Possible Risk Indicator in Normal Tension Glaucoma?

PURPOSE: Recently, the absence of spontaneous venous pulsation (SVP) has been suggested as a vascular risk factor for primary open-angle glaucoma (POAG). As the mechanism behind this phenomenon is still unknown, the authors have studied this vascular component using colour Doppler imaging (CDI). METHODS: A total of 236 patients were divided into three diagnostic groups: healthy controls (81), POAG (86) and normal tension glaucoma (NTG; 69). All subjects were submitted to CDI studies of the retrobulbar circulation, intraocular pressure measurements and assessment of SVP existence. Mann-Whitney, chi-square contingency tables and Spearman correlations were used to explore differences and correlations between variables in the diagnostic groups. RESULTS: Eighty-two percent of healthy controls had SVP (66/81), while a smaller numbers were registered in both glaucoma groups: POAG - 50% (43/86); NTG - 51% (35/69). In NTG patients, but not in POAG patients, the prevalence of the SVP phenomenon decreases with increased glaucoma damage (p = 0.04; p = 0.55, respectively). Overall glaucoma patients from both groups had lower central retinal vein (CRV) velocities than the healthy controls (p < 0.05). NTG patients with SVP had less severe visual field defects (mean defect -6.92 versus -11.1, p < 0.05), higher [correction added after online publication 21 September 2012; the word 'higher' has been inserted to replace the word 'lower'] peak systolic and mean flow velocities in the central retinal artery (p < 0.01; p < 0.05, respectively) as well as higher [correction added after online publication 21 September 2012; the word higher has been inserted to replace the word lower] maximal velocities and RI of the CRV (p < 0.02; p < 0.05, respectively). CONCLUSIONS: Glaucoma patients have a decrease in CRV velocities. SVP is less prevalent in glaucoma patients than in healthy individuals. This phenomenon apparently reflects different hemodynamic patterns in the central retinal vessels. This variable may be of particular importance in NTG patients, where it may be associated with more advanced functional damage.