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.

Avaliação da Morbilidade e Mortalidade no Serviço de Ginecologia da Maternidade Dr. Alfredo da Costa. Jan/Set 1991

Foram avaliados todos os internamentos no Serviço de Ginecologia da MAC de 2 de Janeiro a 19 de Setembro de 1991. O critério de selecção baseou-se no registo de morbilidade intra-operatória e no prolongamento de tempo de internamento. Foram estudados os dados relativos à idade, factores de risco associados, risco anestésico, tipo de intervenção cirúrgica, tempo operatório, tipo de complicações e média de tempo de internamento. Verificou-se uma morbilidade global de 5,6%, tendo-se constatado uma maior incidência de complicações no grupo das histerectomias abdominais (16,8%). Nos casos com morbilidade 72% apresentavam um ou mais factores de risco associados. Ocorreram 5 lesões de órgão (0,73%), 33 complicações pós-operatórias (4,8%) e 7 reintervenções (1%). A média de internamento neste grupo de doentes foi de 11 dias.