ABSTRACT
BACKGROUND: Methods to improve stratification of small (≤15 mm) lung nodules are needed. We aimed to develop a radiomics model to assist lung cancer diagnosis. METHODS: Patients were retrospectively identified using health records from January 2007 to December 2018. The external test set was obtained from the national LIBRA study and a prospective Lung Cancer Screening programme. Radiomics features were extracted from multi-region CT segmentations using TexLab2.0. LASSO regression generated the 5-feature small nodule radiomics-predictive-vector (SN-RPV). K-means clustering was used to split patients into risk groups according to SN-RPV. Model performance was compared to 6 thoracic radiologists. SN-RPV and radiologist risk groups were combined to generate "Safety-Net" and "Early Diagnosis" decision-support tools. RESULTS: In total, 810 patients with 990 nodules were included. The AUC for malignancy prediction was 0.85 (95% CI: 0.82-0.87), 0.78 (95% CI: 0.70-0.85) and 0.78 (95% CI: 0.59-0.92) for the training, test and external test datasets, respectively. The test set accuracy was 73% (95% CI: 65-81%) and resulted in 66.67% improvements in potentially missed [8/12] or delayed [6/9] cancers, compared to the radiologist with performance closest to the mean of six readers. CONCLUSIONS: SN-RPV may provide net-benefit in terms of earlier cancer diagnosis.
Subject(s)
Early Detection of Cancer , Lung Neoplasms , Humans , Lung Neoplasms/diagnostic imaging , Prospective Studies , Retrospective Studies , Radiologists , LungABSTRACT
Glucagonoma is a neuroendocrine tumour of very low incidence, estimated at 1 case per 20 million people per year. It typically manifests with a clinical syndrome that includes a characteristic dermatosis called necrolytic migratory erythema (NME). We present the case of a 60-year-old male with NME as the initial presentation of a pancreatic tumour and its imaging findings. We emphasize the importance of recognizing the clinical features of NME and the role of different imaging methods for early diagnosis and correct management of these pancreatic tumours.
El glucagonoma es un tumor neuroendocrino de muy baja incidencia, se estima 1 caso cada 20 millones de personas por año. Típicamente, se manifiesta con un síndrome clínico que incluye una dermatosis característica denominada eritema necrolítico migratorio (ENM). Presentamos el caso de un varón de 60 años con ENM como presentación inicial de un tumor pancreático y los hallazgos por imágenes del mismo. Resaltamos la importancia de reconocer las características clínicas del ENM y el rol de los diferentes métodos por imágenes para un diagnóstico precoz y correcto manejo de estos tumores pancreáticos.
Subject(s)
Neuroendocrine Tumors , Pancreatic Neoplasms , Erythema , Humans , Radiography , Retrospective StudiesABSTRACT
Chronic eosinophilic pneumonia (CEP) is a rare disease of unknown cause characterized by alveolar and interstitial eosinophilic infiltration. The tomographic pattern is characterized by consolidations and peripherally distributed ground glass opacities in both upper lobes. Other findings are opacities in bands parallel to the pleura, thickening of the interlobular septa, migratory opacities, and mediastinal lymph nodes. We presented a case of a woman with CEP and described the most relevant clinical and radiological characteristics.
La neumonía eosinofílica crónica (NEC) es una enfermedad rara de causa desconocida caracterizada por infiltración eosinofílica alveolar e intersticial. El patrón tomográfico se caracteriza por consolidaciones y opacidades en vidrio esmerilado de distribución periférica en ambos lóbulos superiores. Otros hallazgos son las opacidades en bandas paralelas a la pleura, engrosamiento de septos interlobulillares, opacidades migratrices y adenomegalias mediastinales. Se presenta el caso de una mujer con NEC y se describen las características clínicas y radiológicas más relevantes.
Subject(s)
Pulmonary Eosinophilia , Female , Humans , Lung , Lymph Nodes/pathology , Pulmonary Eosinophilia/diagnostic imaging , Pulmonary Eosinophilia/pathology , Radiography , Tomography, X-Ray Computed/methodsABSTRACT
El cuadro clínico de la enfermedad conocida como COVID-19, causada por el nuevo coronavirus SARS-CoV-2 puede variar desde síntomas respiratorios leves hasta una insuficiencia respiratoria severa. Sus efectos en el organismo, especialmente la afección pulmonar, pueden ser visualizados a través de los estudios por imágenes. Si bien el diagnóstico de certeza se confirma mediante la reacción en cadena de la polimerasa con transcriptasa reversa (RT-PCR), los estudios por imágenes, especialmente la radiografía y la tomografía computarizada (TC) de tórax, desempeñan un papel fundamental en el manejo clínico de estos pacientes. Conocer su utilidad, casos de uso y hallazgos esperables brinda herramientas para el equipo de salud, temas que serán abordados en esta actualización y guía práctica. (AU)
The clinical pattern of the disease known as COVID-19, caused by the new coronavirus SARS-Cov-2 can range from mild respiratory symptoms to severe respiratory failure. Its effects on the body, especially the lung condition, can be visualized through imaging studies. While the diagnosis of certainty is confirmed by reverse transcriptase-polymerase chain reaction (RT-PCR), imaging studies, especially chest xray and computed tomography (CT), play a critical role in the clinical management of these patients. Knowing their usefulness, use cases, and expected findings provides tools for the health care team, topics that will be addressed in this update, and practical guide. (AU)
