Value of 18-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) in the differential diagnosis of sarcoidosis and lung cancer with lymph node metastasis: a retrospective study

Abstract

Background: Fluorine 18-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) has been proven to be valuable in guiding the diagnosis and management of sarcoidosis.However, its differential value for sarcoidosis is unclear. The objective of this study was to explore the value of 18F-FDG PET/CT in differentiation sarcoidosis from lung cancer with lymph node metastasis.Methods: A total of 361 consecutively diagnosed sarcoidosis patients and 1,944 consecutively diagnosed lung cancer patients at Shanghai Pulmonary Hospital were retrospectively reviewed. Among them, 85 patients diagnosed with sarcoidosis and 94 lung cancer patients with lymph node metastasis were enrolled.Demographic data and 18F-FDG PET/CT parameters were analyzed by the chi-square test or independent sample Student's t-test. Receiver operating characteristic (ROC) curves were generated to identify cut-off values. Multivariate logistic regression was performed to identify independent predictors of sarcoidosis on 18F-FDG PET/CT, and those with P<0.1 were included in a regression model using the forward log rank (LR) method to generate a ROC curve. Results:The ratio of extrapulmonary lymph node involvement in sarcoidosis patients was significantly higher than that in lung cancer patients (64.7% vs. 29.8%, P<0.001). After adjusting for gender and age, extrapulmonary lymph node involvement [odds ratio (OR): 3.160; 95% confidence interval (CI): 1.105-9.035], maximum standardized uptake value (SUVmax) of mediastinum/hilar lymph nodes >13.86

Prediction of metastases in confusing mediastinal lymph nodes based on flourine-18 fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) imaging using machine learning

“…To avoid overfitting, the model was given an additional drop layer, but the model still underperformed. This can be attributed to the need for deep learning models to have a large number of high-quality images, and medical images, especially PET/CT images, being more difficult to obtain, more expensive to annotate, and more time consuming than other imaging disciplines ( 37 , 38 ). Despite attempts to increase the sample size and improve deep learning model classification accuracy through migration learning ( 39 ) and data augmentation ( 40 ), the results remain unsatisfactory.…”

Sarcoidosis revealed by long-term fever at the Vierzon Hospital: About a case and literature review

“…The absence of exposure to silica and beryllium or drug intake made it possible not to retain the toxic or drug causes. In case of doubt between sarcoidosis and a malignant tumor, positron emission tomography is a useful examination but its routine use is not yet unanimous [19]. Therapeutically, abstention is recommended in cases of asymptomatic stage 1 or 2 lung involvement [3,20].…”

Sarcoidosis detected after COVID‑19 with T‑SPOT.TB positive: A case report

“…18 F-FDG PET-CT is widely used for the diagnosis, staging and therapeutic assessment of malignancies and inflammatory diseases. It can reveal the anatomical localization of residual FDG uptake throughout the whole body, providing guidance for further diagnostic tests (28,29). Previous studies have demonstrated the good diagnostic performance of 18 F-FDG PET-CT for several inflammatory and infectious diseases, including fever of unknown origin and inflammation of unknown origin (30,31).…”