Because of the growing volume of digital registrations obtained from bronchoscopic examinations it proved necessary to summarize (“brief”) their results, namely to mark the parts that are relevant and/or irrelevant for medical diagnosis. The parts in which the ramification areas of bronchial tree are visualized belong to the first group. The paper presents an automatic method for detection of the areas where next level orifices of bronchial tree are visible. The applied algorithms allow the shape evaluation for both orifices and the area located between them (carina). In both cases backpropagation type neural networks are used as classifiers.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.