Dataset Information

Comparison of different automated lesion delineation methods for metabolic tumor volume of 18F-FDG PET/CT in patients with stage I lung adenocarcinoma.

ABSTRACT: The aim of the study was to investigate the suitable segmentation method in small, low uptake and heterogeneous nodules of stage I lung adenocarcinoma.133 stage I lung adenocarcinoma patients with F-FDG PET/CT scans were enrolled in this retrospective study. All lesions were divided into different groups according to nodule density, nodule size, and the maximum standard uptake value (SUVmax) level. Four different PET segmentation methods were performed, including percentage threshold of SUVmax (T42% and T42%?×?RC), gradient-based threshold (adaptive iterative algorithm, AT-AIA), and background-related threshold (adaptive thresholding at 40% SUVmax, AT40%) approaches. The MTVs were evaluated and compared with CT volume (CTV). Percentage volume error (%VE) compared to CTV was calculated and the correlations between MTVs and CTV were analyzed.AT-AIA had the highest accuracy in large, high uptake, and solid nodules (72.5%, 72.4%, and 65.6%, respectively). AT40% had the highest accuracy in small, low uptake and nonsolid nodules (56.6%, 56.1%, and 62.6%, respectively). In part-solid nodules, the accuracy of AT-AIA (60.0%) and AT40% (56.7%) were higher than that of T42% and T42%?×?RC. The MTV of AT-AIA was in excellent correlation with the CTV in solid nodules (R?=?0.831, P?

SUBMITTER: Wang XY

PROVIDER: S-EPMC5758229 | biostudies-literature | 2017 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of different automated lesion delineation methods for metabolic tumor volume of 18F-FDG PET/CT in patients with stage I lung adenocarcinoma.

Wang Xiao-Yi XY Zhao Yan-Feng YF Liu Ying Y Yang Yi-Kun YK Zhu Zheng Z Wu Ning N

Medicine 20171201 51

The aim of the study was to investigate the suitable segmentation method in small, low uptake and heterogeneous nodules of stage I lung adenocarcinoma.133 stage I lung adenocarcinoma patients with F-FDG PET/CT scans were enrolled in this retrospective study. All lesions were divided into different groups according to nodule density, nodule size, and the maximum standard uptake value (SUVmax) level. Four different PET segmentation methods were performed, including percentage threshold of SUVmax ( ...[more]

PMID: 29390527

Similar Datasets

Project description:Background The aim of this work was to investigate the ability of building prognostic models in non-small cell lung cancer (NSCLC) using radiomic features from positron emission tomography and computed tomography with 2-deoxy-2-[fluorine-18]fluoro-d-glucose (18F-FDG PET/CT) images based on a “rough” volume of interest (VOI) containing the tumor instead of its accurate delineation, which is a significant time-consuming bottleneck of radiomics analyses. Methods A cohort of 138 patients with stage II–III NSCLC treated with radiochemotherapy recruited retrospectively (n = 87) and prospectively (n = 51) was used. Two approaches were compared: firstly, the radiomic features were extracted from the delineated primary tumor volumes in both PET (using the automated fuzzy locally adaptive Bayesian, FLAB) and CT (using a semi-automated approach with 3D Slicer™) components. Both delineations were carried out within previously manually defined “rough” VOIs containing the tumor and the surrounding tissues, which were exploited for the second approach: the same features were extracted from this alternative VOI. Both sets for features were then combined with the clinical variables and processed through the same machine learning (ML) pipelines using the retrospectively recruited patients as the training set and the prospectively recruited patients as the testing set. Logistic regression (LR), random forest (RF), and support vector machine (SVM), as well as their consensus through averaging the output probabilities, were considered for feature selection and modeling for overall survival (OS) prediction as a binary classification (either median OS or 6 months OS). The resulting models were compared in terms of balanced accuracy, sensitivity, and specificity. Results Overall, better performance was achieved using the features from delineated tumor volumes. This was observed consistently across ML algorithms and for the two clinical endpoints. However, the loss of performance was not significant, especially when a consensus of the three ML algorithms was considered (0.89 vs. 0.88 and 0.78 vs. 0.77). Conclusion Our findings suggest that it is feasible to achieve similar levels of prognostic accuracy in radiomics-based modeling by relying on a faster and easier VOI definition, skipping a time-consuming tumor delineation step, thus facilitating automation of the whole radiomics workflow. The associated cost is a loss of performance in the resulting models, although this loss can be greatly mitigated when a consensus of several models is relied upon.

Dataset Information

Comparison of different automated lesion delineation methods for metabolic tumor volume of 18F-FDG PET/CT in patients with stage I lung adenocarcinoma.

Publications

Comparison of different automated lesion delineation methods for metabolic tumor volume of 18F-FDG PET/CT in patients with stage I lung adenocarcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets