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.

Analysis of the Dynamics and Origin of Epileptic Activity in Patients with Tuberous Sclerosis Evaluated for Surgery of Epilepsy

Objective: The epilepsies associated with the tuberous sclerosis complex (TSC) are very often refractory to medical therapy. Surgery for epilepsy is an effective alternative when the critical link between the localization of seizure onset in the scalp and a particular cortical tuber can be established. In this study we perform analysis of ictal and interictal EEG to improve such link. Methods: The ictal and interictal recordings of four patients with TSC undergoing surgery for epilepsy were submitted to independent component analysis (ICA), followed by source analysis, using the sLORETA algorithm. The localizations obtained for the ictal EEG and for the average interictal spikes were compared. Results: The ICA of ictal EEG produced consistent results in different events, and there was good agreement with the tubers that were successfully removed in three of the four patients (one patient refused surgery). In some patients there was a large discrepancy between the localization of ictal and interictal sources. The interictal activity produced more widespread source localizations. Conclusions: The use of ICA of ictal EEG followed by the use of source analysis methods in four cases of epilepsy and TSC was able to localize the epileptic generators very near the lesions successfully removed in surgery for epilepsy. Significance: The ICA of ictal EEG events may be a useful add-on to the tools used to establish the connection between epileptic scalp activity and the cortical tubers originating it, in patients with TSC considered for surgery of epilepsy.

Acute Otitis Media a Reliable Warning Sign for Primary Immunodeficiencies?- A Critical Appraisal

Acute otitis media (AOM) is the most common infection in childhood, resulting from both anatomic and immunologic specificities of this age group. Recurrent AOM has been defined as one of the warning signs for primary immunodeficiencies (PID), In this study we evaluated the strength of recurrent AOM as clinical predictor of PID. Methods: Retrospective study (August 2010 - December 2013) which included all patients referred to PID appointment because of recurrent AOM (= 8 AOM episodes/year). Syndromic patients or those presenting with another warning sign for PID were excluded. Clinical, demographic and laboratory results were analized and statistical analysis was made using SPSS 20. Results: Seventy-five patients were included (median age 37,8 months; 62,7% male gender), corresponding to 15% of all first appointments. Other comorbidities were present in 20% of the patients and 17% had ORL surgery prior to PID referral. In most patients, the immunologic screening consisted on the evaluation of humoral function, but in selected cases other studies were performed (namely complement and lymphocyte immunophenotyping). A PID was identified in 12 children (16,0%) and the majority of these patients had other distinctive feature (personal or familiar antecedent of infection or auto-immunity, 66,7%, p<0,05). Nine children (12,0%) underwent prophylactic cotrimoxazole. The average length of follow-up was 11,2 months. Conclusion: Despite being a very frequent cause of immunologic screening, in this study recurrent AOM was not found to be a good predictor of underlying PID, unless the patients presents other significant personal or family history.