Purpose:The development of computer-aided diagnostic ͑CAD͒ methods for lung nodule detection, classification, and quantitative assessment can be facilitated through a well-characterized repository of computed tomography ͑CT͒ scans. The Lung Image Database Consortium ͑LIDC͒ and Image Database Resource Initiative ͑IDRI͒ completed such a database, establishing a publicly available reference for the medical imaging research community. Initiated by the National Cancer Institute ͑NCI͒, further advanced by the Foundation for the National Institutes of Health ͑FNIH͒, and accompanied by the Food and Drug Administration ͑FDA͒ through active participation, this public-private partnership demonstrates the success of a consortium founded on a consensus-based process. Methods: Seven academic centers and eight medical imaging companies collaborated to identify, address, and resolve challenging organizational, technical, and clinical issues to provide a solid foundation for a robust database. The LIDC/IDRI Database contains 1018 cases, each of which includes images from a clinical thoracic CT scan and an associated XML file that records the results of a two-phase image annotation process performed by four experienced thoracic radiologists. In the initial blinded-read phase, each radiologist independently reviewed each CT scan and marked lesions belonging to one of three categories ͑"noduleՆ 3 mm," "noduleϽ 3 mm," and "non-noduleՆ 3 mm"͒. In the subsequent unblinded-read phase, each radiologist independently reviewed their own marks along with the anonymized marks of the three other radiologists to render a final opinion. The goal of this process was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus. Results:The Database contains 7371 lesions marked "nodule" by at least one radiologist. 2669 of these lesions were marked "noduleՆ 3 mm" by at least one radiologist, of which 928 ͑34.7%͒ received such marks from all four radiologists. These 2669 lesions include nodule outlines and subjective nodule characteristic ratings. Conclusions:The LIDC/IDRI Database is expected to provide an essential medical imaging research resource to spur CAD development, validation, and dissemination in clinical practice.

In the past decade, lung transplantation has become established as an accepted therapy for end-stage pulmonary disease. Complications of lung transplantation that may occur in the immediate or longer postoperative term include mechanical problems due to a size mismatch between the donor lung and the recipient thoracic cage; malposition of monitoring tubes and lines; injuries from ischemia and reperfusion; acute pleural events; hyperacute, acute, and chronic rejection; pulmonary infections; bronchial anastomotic complications; pulmonary thromboembolism; upper-lobe fibrosis; primary disease recurrence; posttransplantation lymphoproliferative disorder; and native lung complications such as hyperinflation, malignancy, and infection. Radiologic imaging--particularly chest radiography, computed tomography (CT), and high-resolution CT--is critical for the early detection, evaluation, and diagnosis of complications after lung transplantation. To enable the selection of an effective and relevant course of therapy and, ultimately, to decrease morbidity and mortality among lung transplant recipients, radiologists at all levels of experience must be able to recognize and understand the imaging manifestations of posttransplantation complications.

Two hundred seventy-five computed tomographic (CT) angiograms of the thoracic aorta were obtained over a period of approximately 4 years in patients with suspected or known aortic dissection. In all cases, unenhanced images were initially obtained, followed by contrast material-enhanced images. A variety of pitfalls were encountered that mimicked aortic dissection. These pitfalls were attributable to technical factors (eg, improper timing of contrast material administration relative to image acquisition); streak artifacts generated by high-attenuation material, high-contrast interfaces, or cardiac motion; periaortic structures (eg, aortic arch branches, mediastinal veins, pericardial recess, thymus, atelectasis, pleural thickening or effusion adjacent to the aorta); aortic wall motion and normal aortic sinuses; aortic variations such as congenital ductus diverticulum and acquired aortic aneurysm with thrombus; and penetrating atherosclerotic ulcer. Although several of these pitfalls are easy to recognize and therefore unlikely to present a diagnostic problem, others are potentially confusing. Familiarity with these common pitfalls, coupled with a knowledge of normal intrathoracic anatomy, will facilitate recognition of true aortic dissection and help avoid misdiagnosis at thoracic aortic CT angiography.

No abstract

No abstract

Antipsychotic-induced weight gain has emerged as a serious complication in the treatment of patients with atypical antipsychotic drugs. The cannabinoid receptor 1 (CNR1) is expressed centrally in the hypothalamic region and associated with appetite and satiety, as well as peripherally. An antagonist of CNR1 (rimonabant) has been effective in causing weight loss in obese patients indicating that CNR1 might be important in antipsychotic-induced weight gain. Twenty tag SNPs were analyzed in 183 patients who underwent treatment (with either clozapine, olanzapine, haloperidol, or risperidone) for chronic schizophrenia were evaluated for antipsychotic-induced weight gain for up to 14 weeks. The polymorphism rs806378 was nominally associated with weight gain in patients of European ancestry treated with clozapine or olanzapine. 'T' allele carriers (CT + TT) gained more weight (5.96%), than the CC carriers (2.76%, p ¼ 0.008, FDR q-value ¼ 0.12). This translated into approximately 2.2 kg more weight gain in patients carrying the T allele than the patients homozygous for the CC genotype (CC vs CT + TT, 2.21±4.51 vs 4.33±3.89 kg; p ¼ 0.022). This was reflected in the allelic analysis (C vs T allele, 3.84 vs 5.83%, p ¼ 0.035). We conducted electrophoretic mobility shift assays which showed that the presence of the T allele created a binding site for arylhydrocarbon receptor translocator (ARNT), a member of the basic helix-loop-helix/Per-Arnt-Sim protein family. In this study, we provide evidence that the CNR1 gene may be associated with antipsychotic-induced weight gain in chronic schizophrenia patients. However, these observations were made in a relatively small patient population; therefore these results need to be replicated in larger sample sets.

Most patients with advanced liver disease have one or more types of abnormality in lung function, a reduced DLCO being the single most common functional defect. Mechanisms accounting for the abnormality in gas transfer may include intrapulmonary vascular dilatations, diffuse interstitial lung disease, pulmonary vaso-occlusive disease, and/or ventilation-perfusion imbalance.

Lung CAD systems require the ability to classify a variety of pulmonary structures as part of the diagnostic process. The purpose of this work was to develop a methodology for fully automated voxel-by-voxel classification of airways, fissures, nodules, and vessels from chest CT images using a single feature set and classification method. Twenty-nine thin section CT scans were obtained from the Lung Image Database Consortium (LIDC). Multiple radiologists labeled voxels corresponding to the following structures: airways (trachea to 6th generation), major and minor lobar fissures, nodules, and vessels (hilum to peripheral), and normal lung parenchyma. The labeled data was used in conjunction with a supervised machine learning approach (AdaBoost) to train a set of ensemble classifiers. Each ensemble classifier was trained to detect voxels part of a specific structure (either airway, fissure, nodule, vessel, or parenchyma). The feature set consisted of voxel attenuation and a small number of features based on the eigenvalues of the Hessian matrix (used to differentiate structures by shape). When each ensemble classifier was composed of 20 weak classifiers, the AUC values for the airway, fissure, nodule, vessel, and parenchyma classifiers were 0.984 ± 0.011, 0.949 ± 0.009, 0.945 ± 0.018, 0.953 ± 0.016, and 0.931± 0.015 respectively. The strong results suggest that this could be an effective input to higher-level anatomical based segmentation models with the potential to improve CAD performance.