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

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.

Prediction for Mitosis-Karyorrhexis Index Status of Pediatric Neuroblastoma via Machine Learning Based 18F-FDG PET/CT Radiomics

“…Among the 13 selected radiomics features in the present study, it demonstrated that features extracted from wavelet transformed images play an important role in prediction models. The wavelet transform can decompose the image into low-frequency elements and/or high-frequency components at different scales, and the texture features obtained from the wavelet decomposition of the original data can signify different frequency ranges within the tumor volume [ 31 ]. Some studies have demonstrated that wavelet-based features are important in radiomics studies and can show promising capabilities in terms of tumor classification and prognosis [ 32 , 33 ].…”

Radiomics in Oncological PET Imaging: A Systematic Review—Part 2, Infradiaphragmatic Cancers, Blood Malignancies, Melanoma and Musculoskeletal Cancers

“…Pancreatic cancer was featured in 13 studies based on 18F-FDG [ 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 ]. An average of 110.7 patients was included (range: 48–198, 8 studies with more than 100 patients) with 1 (7.7%) prospective study and 4 (30.8%) using a validation cohort.…”

“…A total of 8 studies (61.5%) focused on prognosis, while the remaining 5 dealt with diagnostic issues and histological characterization. Promising results were found in terms of grade of tumoral differentiation prediction [ 62 ] with a model based on a twelve-feature-combined radiomics signature that could stratify pancreatic ductal adenocarcinoma patients into grade G1 and grade G2/3 groups, with an AUC of 0.994 in the training set and 0.921 in the validation set.…”

Current controversies and advances in the management of pancreatic adenocarcinoma

“…Studies have shown data supporting the utility of PET scan in staging of pancreatic cancer[ 61 - 63 ], whereas other studies have shown conflicting results[ 64 , 65 ]. Use of 18F-flurodeoxyglucose (FDG) PET combined with CT (PET/CT) and MRI (PET/MRI) has generated interest in diagnosis, staging (lymph node involvement and metastasis)[ 66 ], assessment of pathological grade[ 67 ], assessment of treatment response, planning of radiation treatment, etc. [ 68 - 70 ].…”