Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Feb 25;11(1):19.
doi: 10.1186/s13550-021-00760-3.

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

Haiqun Xing  1   2 , Zhixin Hao  1   2 , Wenjia Zhu  1   2 , Dehui Sun  3 , Jie Ding  1   2 , Hui Zhang  4 , Yu Liu  1   2 , Li Huo  5   6
Affiliations

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

Haiqun Xing et al. EJNMMI Res. .

Abstract

Purpose: To 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).

Methods: A 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).

Results: The 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.

Conclusion: The model developed is capable of predicting pathological differentiation grade of PDAC based on preoperative 18F-FDG PET/CT radiomics features.

Keywords: 18F-FDG PET/CT; Machine learning; Pancreatic cancer; Radiomics; XGBoost.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
Analysis flowchart. a Study workflow. b Radiomics process
Fig. 2
Fig. 2
Examples of ROI segmentation in pancreatic ductal adenocarcinoma (PDAC) using 18F-FDG PET/CT images. One physician segmented tumor in blue along the edge of tumor (above), and the other physician segmented tumor in green to include voxels presenting SUV values greater than 50% of SUVmax (below). a The axial CT (above) and fusion (below) images of grade 3 (2010 World Health Organization classification system) PDAC in a 69-year-old man. The images showed a mass measuring about 3.7 × 3.4 × 2.8 cm with SUVmax of 3.7 in pancreatic head. b The axial images of grade 2 PDAC in a 57-year-old man. The image showed a mass with necrotic lesion in tail of pancreas, and SUVmax was 4.1. c The axial images of grade 1 PDAC in a 56-year-old man. The images showed a mass measuring about 2.7 × 2.7 × 2.8 cm with SUVmax of 3.0 in pancreatic body
Fig. 3
Fig. 3
Radiomics score of each patient. a Training set. b Validation set
Fig. 4
Fig. 4
ROC curve. a Training set. b Validation set
Fig. 5
Fig. 5
ROC curve of the difference modality radiomics-based model
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Bilici A. Prognostic factors related with survival in patients with pancreatic adenocarcinoma. World J Gastroenterol. 2014;20:10802–10812. doi: 10.3748/wjg.v20.i31.10802. - DOI - PMC - PubMed
    1. Hidalgo M, Alvarez R, Gallego J, Guillen-Ponce C, Laquente B, Macarulla T, et al. Consensus guidelines for diagnosis, treatment and follow-up of patients with pancreatic cancer in Spain. Clin Transl Oncol. 2017;19:667–681. doi: 10.1007/s12094-016-1594-x. - DOI - PMC - PubMed
    1. Rossi ML, Rehman AA, Gondi CS. Therapeutic options for the management of pancreatic cancer. World J Gastroenterol. 2014;20:11142–11159. doi: 10.3748/wjg.v20.i32.11142. - DOI - PMC - PubMed
    1. Ko AH. Pancreatic cancer and the possibility of long-term survival: a glimmer of hope? JAMA Oncol. 2016;2:380–381. doi: 10.1001/jamaoncol.2015.4869. - DOI - PubMed
    1. Le N, Sund M, Vinci A, Pancreas G. Prognostic and predictive markers in pancreatic adenocarcinoma. Dig Liver Dis. 2016;48:223–230. doi: 10.1016/j.dld.2015.11.001. - DOI - PubMed

LinkOut - more resources