Preoperative prediction of pathological grade in pancreatic ductal adenocarcinoma based on 18F-FDG PET/CT radiomics

EJNMMI Research

Hui Zhang¹  Zhixin Hao²  Jie Ding²  Haiqun Xing²  Li Huo²  Wenjia Zhu²  Yu Liu²  Dehui Sun³ 

[1] Department of Biomedical Engineering, School of Medicine, Tsinghua University, 100084, Beijing, China;Department of Nuclear Medicine, Peking Union Medical College Hospital, Dongcheng District, Chinese Academy of Medical Science, Peking Union Medical College, No.1 Shuaifuyuan, 100730, Beijing, China;Beijing Key Laboratory of Molecular Targeted Diagnosis and Therapy in Nuclear Medicine, 100730, Beijing, China;Sinounion Healthcare Inc., Building 3-B, Zhongguancun Dong Sheng International Pioneer Park, 100192, Beijing, China;

关键词: F-FDG PET/CT;    Pancreatic cancer;    Radiomics;    Machine learning;    XGBoost;   

DOI  :  10.1186/s13550-021-00760-3

来源: Springer

【 摘 要 】

PurposeTo develop and validate a machine learning model based on radiomic features derived from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) images to preoperatively predict the pathological grade in patients with pancreatic ductal adenocarcinoma (PDAC).MethodsA total of 149 patients (83 men, 66 women, mean age 61 years old) with pathologically proven PDAC and a preoperative 18F-FDG PET/CT scan between May 2009 and January 2016 were included in this retrospective study. The cohort of patients was divided into two separate groups for the training (99 patients) and validation (50 patients) in chronological order. Radiomics features were extracted from PET/CT images using Pyradiomics implemented in Python, and the XGBoost algorithm was used to build a prediction model. Conventional PET parameters, including standardized uptake value, metabolic tumor volume, and total lesion glycolysis, were also measured. The quality of the proposed model was appraised by means of receiver operating characteristics (ROC) and areas under the ROC curve (AUC).ResultsThe prediction model based on a twelve-feature-combined radiomics signature could stratify PDAC patients into grade 1 and grade 2/3 groups with AUC of 0.994 in the training set and 0.921 in the validation set.ConclusionThe model developed is capable of predicting pathological differentiation grade of PDAC based on preoperative 18F-FDG PET/CT radiomics features.

【 授权许可】

CC BY