AUTHOR=Wang Bin , Hamal Preeti , Meng Xue , Sun Ke , Yang Yang , Sun Yangyang , Sun Xiwen 

TITLE=Evaluation of the Radiomics Method for the Prediction of Atypical Adenomatous Hyperplasia in Patients With Subcentimeter Pulmonary Ground-Glass Nodules

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.698053

DOI=10.3389/fonc.2021.698053

ISSN=2234-943X

ABSTRACT=Objectives
We aimed to develop a prediction model to distinguish atypical adenomatous hyperplasia (AAH) from early lung adenocarcinomas in patients with subcentimeter pulmonary ground-glass nodules (GGNs), which may help avoiding aggressive surgical resection for patients with AAH.
Methods
Surgically confirmed cases of AAH and lung adenocarcinomas manifesting as GGNs of less than one centimeter were retrospectively collected. A prediction model based on radiomics and clinical features identified from a training set of cases was built to differentiate AAH from lung adenocarcinomas and tested on a validation set.
Results
Four hundred and eighty-five eligible cases were included and randomly assigned to the training (n = 339) or the validation set (n = 146). The developed radiomics prediction model showed good discrimination performance to distinguish AAH from adenocarcinomas in both the training and the validation sets, with, respectively, 84.1% and 82.2 of accuracy, and AUCs of 0.899 (95%CI: 0.867–0.931) and 0.881 (95%CI: 0.827–0.936).
Conclusion
The prediction model based on radiomics and clinical features can help differentiating AAH from adenocarcinomas manifesting as subcentimeter GGNs, and may prevent aggressive resection for AAH patients, while reserving this treatment for adenocarcinomas.