Search

Abstract Foreign body aspiration continues to be a serious problem in childhood and adolescent period with significant rate of morbidity and rarely mortality. Half of the foreign body aspiration cases have no history of aspiration. The main foreign bodies inhaled are food fragments and different kinds of metallic objects. A 12-year-old girl was referred to the pediatric pulmonology department for chronic cough and hemoptysis. She had persistent infiltration and cavitary lesion mimicking cavitary tuberculosis. There was no contact history with tuberculosis in her family and acid resistant bacillus was not found in the sputum examination. Flexible bronchoscopy was performed for persistent infiltration and hemoptysis and inflamed thread was found in right lower lobe bronchus. This is the first case of thread inhalation mimicking cavitary tuberculosis in an adolescent patient.

Lung cancer is the leading cancer type that causes mortality in both men and women. Computer-aided detection (CAD) and diagnosis systems can play a very important role for helping physicians with cancer treatments. This study proposes a hierarchical deep-fusion learning scheme in a CAD framework for the detection of nodules from computed tomography (CT) scans. In the proposed hierarchical approach, a decision is made at each level individually employing the decisions from the previous level. Further, individual decisions are computed for several perspectives of a volume of interest. This study explores three different approaches to obtain decisions in a hierarchical fashion. The first model utilizes raw images. The second model uses a single type of feature image having salient content. The last model employs multi-type feature images. All models learn the parameters by means of supervised learning. The proposed CAD frameworks are tested using lung CT scans from the LIDC/IDRI database. The experimental results showed that the proposed multi-perspective hierarchical fusion approach significantly improves the performance of the classification. The proposed hierarchical deep-fusion learning model achieved a sensitivity of 95% with only 0.4 fp/scan., Competing Interests: The authors declare no conflict of interest.