Solitary pulmonary nodule

CT bronchus sign (BS) designates a bronchus leading directly to a peripheral pulmonary lesion. The objective of this investigation is to determine the contribution of BS-guided bronchoscopic multiple diagnostic procedures (BMDPs) to the diagnostic yield of solitary nodules or masses (SPNMs) suspected of pulmonary carcinoma (PC). A prospective study was carried out in 92 patients with a 2–5 cm diameter

Descriptive-analytic appraisal of validity of surgical approach to diagnosis and therapy in solitary pulmonary nodules (SPNSs). TASK: to establish justification of surgical removing of SPNs which etiology is unclear after complete previous clinical investigation. In the period between 1 January 1999 and 1 January 2004, included in this investigation were all patients with SPN of unclear origin who were referred to the Clinic for Thoracic Surgery-UCC Sarajevo after complete previous clinical investigation. We operated 60 patients with proved SPN. The malignancy was found in 44/60 (73,3%) patients. There were established following types of malignancy carcinoma planocellulare in 54,5%, adeno carcinoma in 36,5% carcinoma bronchioloalveolare in 4,5% and tumor carcinoides in 4, % patients. We did following types of operation atypical (wedge) resection in 20 (33,3%), lobectomy in 36 (60,0%) and pneumonectomy in 4 (6,7%) patients. There were neither intra- operative complications nor intra ...

Computed tomography (CT) examinations are commonly used to predict lung nodule malignancy in patients, which are shown to improve noninvasive early diagnosis of lung cancer. It remains challenging for computational approaches to achieve performance comparable to experienced radiologists. Here we present NoduleX, a systematic approach to predict lung nodule malignancy from CT data, based on deep learning convolutional neural networks (CNN). For training and validation, we analyze >1000 lung nodules in images from the LIDC/IDRI cohort. All nodules were identified and classified by four experienced thoracic radiologists who participated in the LIDC project. NoduleX achieves high accuracy for nodule malignancy classification, with an AUC of ~0.99. This is commensurate with the analysis of the dataset by experienced radiologists. Our approach, NoduleX, provides an effective framework for highly accurate nodule malignancy prediction with the model trained on a large patient population....

Lung cancer screening with a low-dose chest CT scan can result in more benefit than harm when performed in settings committed to developing and maintaining high-quality programs. This project aimed to identify the components of screening that should be a part of all lung cancer screening programs. To do so, committees with expertise in lung cancer screening were assembled by the Thoracic Oncology Network of the American College of Chest Physicians (CHEST) and the Thoracic Oncology Assembly of the American Thoracic Society (ATS). Lung cancer program components were derived from evidence-based reviews of lung cancer screening and supplemented by expert opinion. This statement was developed and modified based on iterative feedback of the committees. Nine essential components of a lung cancer screening program were identified. Within these components 21 Policy Statements were developed and translated into criteria that could be used to assess the qualification of a program as a screenin...

A realistic dynamic positron-emission tomography (PET) thoracic study was generated, using the 4D NURBS-based (non-uniform rational B-splines) cardiac-torso (NCAT) phantom and a sophisticated model of the PET imaging process, simulating two solitary pulmonary nodules. Three data reduction and blind source separation methods were applied to the simulated data: principal component analysis, independent component analysis and similarity mapping. All methods reduced the initial amount of image data to a smaller, comprehensive and easily managed set of parametric images, where structures were separated based on their different kinetic characteristics and the lesions were readily identified. The results indicate that the above-mentioned methods can provide an accurate tool for the support of both visual inspection and subsequent detailed kinetic analysis of the dynamic series via compartmental or non-compartmental models.