Skip to main content

ORIGINAL RESEARCH article

Front. Med.
Sec. Nuclear Medicine
Volume 11 - 2024 | doi: 10.3389/fmed.2024.1453421
This article is part of the Research Topic Towards Precision Oncology: Assessing the Role of Radiomics and Artificial Intelligence View all 7 articles

Peri-and intra-nodular radiomic features based on 18 F-FDG PET/CT to distinguish lung adenocarcinomas from pulmonary granulomas

Provisionally accepted
Congna Tian Congna Tian 1Yujing Hu Yujing Hu 1Shuheng Li Shuheng Li 2Xinchao Zhang Xinchao Zhang 1Qiang Wei Qiang Wei 1Kang Li Kang Li 1Xiaolin Chen Xiaolin Chen 3Lu Zheng Lu Zheng 1Xin Yang Xin Yang 1Yanan Qin Yanan Qin 1Yanzhu Bian Yanzhu Bian 1*
  • 1 Department of Nuclear Medicine, Hebei General Hospital, Shijiazhuang, Hebei Province, China
  • 2 Department of Nuclear Medicine, Affiliated Hospital of Hebei University, Baoding, China
  • 3 Department of Nuclear Medicine, Fourth Hospital of Hebei Medical University, Shijiazhuang, Hebei Province, China

The final, formatted version of the article will be published soon.

    Objective To compare the effectiveness of radiomic features based on 18 F-FDG PET/CT images within (intranodular) and around (perinodular) lung nodules/masses in distinguishing between lung adenocarcinoma and pulmonary granulomas.Methods For this retrospective study, 18 F-FDG PET/CT images were collected for 228 patients. Patients diagnosed with lung adenocarcinoma (n = 156) or granulomas (n = 72) were randomly assigned to a training (n = 159) and validation (n = 69) groups. The volume of interest (VOI) of intranodular, perinodular (1-5 voxels, termed Lesion_margin1 to Lesion_margin5Lesion_margin1-5) and total area (intra-plus perinodular region, termed Lesion_total1-to Lesion_total5) on PET/CT images were delineated using PETtumor and Marge tool of segmentation editor. A total of 1037 radiomic features were extracted separately from PET and CT images, and the optimal features were selected to develop radiomic models. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC).Good and acceptable performance was respectively observed in both the training (AUC=0.868, p<0.001) and validation (AUC=0.715, p=0.004) sets for the intranodular radiomic model. Among the perinodular models, the Lesion_margin2 model demonstrated the highest AUC in both sets (0.883 and 0.616, p<0.001 and p=0.122). Similarly, in terms of total models, Lesion_total2 model was found to outperform others in the training (AUC=0.879, p<0.001) and validation (AUC=0.742, p=0.001) sets, slightly surpassing the intranodular model.When intra-and perinodular radiomic features extracted from the immediate vicinity of the nodule/mass up to 2 voxels distance on 18 F-FDG PET/CT imaging are combined, improved differential

    Keywords: Radiomics, pulmonary granuloma, Lung Adenocarcinoma, 18 F-FDG, PET/CT

    Received: 23 Jun 2024; Accepted: 23 Jul 2024.

    Copyright: © 2024 Tian, Hu, Li, Zhang, Wei, Li, Chen, Zheng, Yang, Qin and Bian. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Yanzhu Bian, Department of Nuclear Medicine, Hebei General Hospital, Shijiazhuang, 050051, Hebei Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.