Aspergillus is a large genus of saprophytic fungi which are present everywhere in the environment. However, in persons with underlying weakened immune response this innocent bystander can cause fatal illness if timely diagnosis and management is not done. Chest infection is the most common infection caused by Aspergillus in human beings. Radiological investigations particularly Computed Tomography (CT) provides the easiest, rapid and decision making information where tissue diagnosis and culture may be difficult and time-consuming. This article explores the crucial role of CT and offers a bird's eye view of all the radiological patterns encountered in pulmonary aspergillosis viewed in the context of the immune derangement associated with it.
The clinical manifestations of foreign body (FB) aspiration can range from an asymptomatic presentation to a life-threatening emergency. Patients may present with acute onset cough, chest pain, breathlessness or sub-acutely with unexplained hemoptysis, non-resolving pneumonia and at times, as an incidental finding on imaging. Patients with iatrogenic FB such as an aspirated broken tooth during difficult intubation or a broken instrument are more common scenarios in the intensive care unit (ICU).Patients with post-obstructive pneumonia with or without sepsis, or variable degree of hemoptysis often require ICU level of care and bronchoscopic interventions. Rigid bronchoscopy has traditionally been the modality of choice; however, with the innovation in instrumentation and wider availability of flexible bronchoscopes, most of the FB removal is now successfully performed using flexible bronchoscopy.Proceduralists choose instruments in accordance with their training and expertise. We describe the use of most common instruments including forceps, balloon catheters, and baskets. Role of cryoprobe and LASER in FB removal is reviewed as well. In general, larger working channel bronchoscopes are preferred; however, smaller working channel bronchoscopes may be used in situations when the patients are intubated with a smaller diameter endotracheal or tracheostomy tubes. Large size FB are removed en bloc with the grasping tool, bronchoscope, and endotracheal or tracheostomy tube, requiring preparation to safely re-establish the airway. After FB removal, bronchoscopy is re-performed to identify any residual FB, assess any injury to the airway, suction post-obstructive secretions or pus, control any active bleeding and remove granulation tissue that may be obstructing the airway. Additional interventions like balloon dilatation may be required to dislodge an impacted FB or to maintain patency of bronchial lumen. If bronchoscopic methods fail, surgery may be required for retrieval of FB in symptomatic patients or to resect suppurative or necrotizing lung process. Multidisciplinary approach involving intensivists, surgeons, and anesthesiologists is the key to optimal patient outcomes.
To mitigate the outbreak of highly contagious COVID-19, we need a sensitive, robust automated diagnostic tool. This paper proposes a three-level approach to separate the cases of COVID-19, pneumonia from normal patients using chest CT scans. At the first level, we fine tune a multi-scale ResNet50 model for feature extraction from all the slices of CT scan for each patient. By using multi-scale residual network, we can learn different sizes of infection, thereby making the detection possible at early stages too. These extracted features are used to train a patient-level classifier, at the second level. Four different classifiers are trained at this stage. Finally, predictions of patient level classifiers are combined by training an ensemble classifier. We test the proposed method on three sets of data released by ICASSP, COVID-19 Signal Processing Grand Challenge (SPGC). The proposed method has been successful in classifying the three classes with a validation accuracy of 94.9% and testing accuracy of 88.89%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.