Lili Wang1, Tiancheng Li2, Junjie Hong1, Mingyue Zhang3, Mingli Ouyang4, Xiangwu Zheng1, Kun Tang1. 1. Department of PET/CT, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China. 2. PET Center, the First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. 3. Department of Radiology, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China. 4. Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Abstract
BACKGROUND: This study aimed to develop a preoperative positron emission tomography (PET)-based radiomics model for predicting occult lymph node metastasis (OLM) in clinical N0 (cN0) solid lung adenocarcinoma. METHODS: The preoperative fluorine-18-fludeoxyglucose (18F-FDG) PET images of 370 patients with cN0 lung adenocarcinoma confirmed by histopathological examination were retrospectively reviewed. Patients were divided into training and validation sets. Radiomics features and relevant data were extracted from PET images. A nomogram was developed in a training set via univariate and multivariate logistic analyses, and its performance was assessed by concordance-index (C-index), calibration curves, and decision curve analysis (DCA) in the training and validation sets. RESULTS: The multivariate logistic regression analysis showed that only carcinoembryonic antigen (CEA), metabolic tumor volume (MTV), and the radiomics signature had statistically significant differences between patients with and without OLM (P<0.05). A nomogram was developed based on the logistic analyses, and its C-index was 0.769 in the training set and 0.768 in the validation set. The calibration curve demonstrated good consistency between the nomogram-predicted probability of OLM and the actual rate. The DCA also confirmed the clinical utility of the nomogram. CONCLUSIONS: A PET/computed tomography (CT)-based radiomics model including CEA, MTV, and the radiomics signature was developed and demonstrated adequate predictive accuracy and clinical net benefit in the present study, and was conveniently used to facilitate the individualized preoperative prediction of OLM. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
BACKGROUND: This study aimed to develop a preoperative positron emission tomography (PET)-based radiomics model for predicting occult lymph node metastasis (OLM) in clinical N0 (cN0) solid lung adenocarcinoma. METHODS: The preoperative fluorine-18-fludeoxyglucose (18F-FDG) PET images of 370 patients with cN0 lung adenocarcinoma confirmed by histopathological examination were retrospectively reviewed. Patients were divided into training and validation sets. Radiomics features and relevant data were extracted from PET images. A nomogram was developed in a training set via univariate and multivariate logistic analyses, and its performance was assessed by concordance-index (C-index), calibration curves, and decision curve analysis (DCA) in the training and validation sets. RESULTS: The multivariate logistic regression analysis showed that only carcinoembryonic antigen (CEA), metabolic tumor volume (MTV), and the radiomics signature had statistically significant differences between patients with and without OLM (P<0.05). A nomogram was developed based on the logistic analyses, and its C-index was 0.769 in the training set and 0.768 in the validation set. The calibration curve demonstrated good consistency between the nomogram-predicted probability of OLM and the actual rate. The DCA also confirmed the clinical utility of the nomogram. CONCLUSIONS: A PET/computed tomography (CT)-based radiomics model including CEA, MTV, and the radiomics signature was developed and demonstrated adequate predictive accuracy and clinical net benefit in the present study, and was conveniently used to facilitate the individualized preoperative prediction of OLM. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Authors: Sara Carvalho; Ralph T H Leijenaar; Esther G C Troost; Janna E van Timmeren; Cary Oberije; Wouter van Elmpt; Lioe-Fee de Geus-Oei; Johan Bussink; Philippe Lambin Journal: PLoS One Date: 2018-03-01 Impact factor: 3.240
Authors: Huang Miao; Li Shaolei; Li Nan; Lai Yumei; Zhang Shanyuan; Lu Fangliang; Yang Yue Journal: Thorac Cancer Date: 2019-05-24 Impact factor: 3.500