Features of T1 pancreatic cancer and validation of the eighth edition AJCC staging system definition using a Korean-Japanese joint cohort and the SEER database.

BACKGROUND/PURPOSE: Little is known about the features of T1 pancreatic ductal adenocarcinoma (PDAC) and its definition in the eighth edition of the American Joint Committee on Cancer (AJCC) staging system needs validation. The aims were to analyze the clinicopathologic features of T1 PDAC and investigate the validity of its definition. METHOD: Data from 1506 patients with confirmed T1 PDAC between 2000 and 2019 were collected and analyzed. The results were validated using 3092 T1 PDAC patients from the Surveillance, Epidemiology, and End Results (SEER) database. RESULTS: The median survival duration of patients was 50 months, and the 5-year survival rate was 45.1%. R0 resection was unachievable in 10.0% of patients, the nodal metastasis rate was 40.0%, and recurrence occurred in 55.2%. The current T1 subcategorization was not feasible for PDAC, tumors with extrapancreatic extension (72.8%) had worse outcomes than those without extrapancreatic extension (median survival 107 vs. 39 months, p < .001). Extrapancreatic extension was an independent prognostic factor whereas the current T1 subcategorization was not. The results of this study were reproducible with data from the SEER database. CONCLUSION: Despite its small size, T1 PDAC displayed aggressive behavior warranting active local and systemic treatment. The subcategorization by the eighth edition of the AJCC staging system was not adequate for PDAC, and better subcategorization methods need to be explored. In addition, the role of extrapancreatic extension in the staging system should be reconsidered.

Preoperative Extrapancreatic Extension Prediction in Patients with Pancreatic Cancer Using Multiparameter MRI and Machine Learning-Based Radiomics Model.

RATIONALE AND OBJECTIVES: Pancreatic cancer is a common malignant tumor with a dismal prognosis. Preoperative differentiation of extrapancreatic extension (EPE) based on radiomics will facilitate treatment decision-making. MATERIALS AND METHODS: This research retrospectively recruited 156 patients from two medical centers. 122 patients from the center A were randomly divided into the training set and the internal test set in a 4:1 ratio. Additionally, 34 patients from the center B served as the external test set. Radiomics features were extracted from multiparametric MRI (MP-MRI), containing axial T2 weighted imaging (T2WI), diffusion weighted imaging (DWI), and dynamic contrast enhancement (DCE) sequences. The three-step method was used for feature extraction: SelecteKBest, least absolute shrinkage and selection operator (LASSO) algorithm, and recursive feature elimination based on random forest (RFE-RF). The model was constructed using six classifiers based on machine learning, and the classifier with the best performance was chosen. Finally, clinical factors associated with EPE were incorporated into the combined model. RESULTS: The classifier with the best performance was XGBoost, which obtained area under curve (AUC) values of 0.853 and 0.848 in the internal and external test sets, respectively. Through SelectKBest, the most relevant clinical factor for EPE was determined to be platelet, which was then added to the combined model, yielding AUC values of 0.880 and 0.848 in the internal and external test sets, respectively. CONCLUSION: Radiomics models had the potential to noninvasively and accurately predict EPE before surgery. Additionally, it would add value to personalized precision treatment.

Equipping the American Joint Committee on Cancer staging for resectable pancreatic ductal adenocarcinoma with tumor grade: a recursive partitioning analysis.

Previous studies of pancreatic ductal adenocarcinoma (PDAC) have demonstrated that the addition of tumor grade to the 7th American Joint Committee on Cancer (AJCC) staging can provide improved prognostication and that the recently proposed 8th edition AJCC staging exhibited superior reproducibility to the 7th edition in resectable PDAC. Thus, we aimed to combine tumor grade and 8th AJCC stage to develop a refined staging scheme for resectable PDAC. We analyzed 7719 patients with resectable PDAC from the 2004-2012 Surveillance, Epidemiology, and End Results database. We performed recursive partitioning analysis (RPA) to objectively incorporate tumor grade with 8th AJCC stage into a novel staging system. The performance of the proposed RPA staging was assessed against the 8th AJCC staging in terms of discriminatory ability and prognostic homogeneity. For each 8th AJCC stage, survival was significantly worse for high-grade versus low-grade tumors. RPA divided resectable PDAC into five stages: RPA-IA (low-grade T1N0), RPA-IB (high-grade T1N0 or low-grade T2N0), RPA-IIA (high-grade T2N0 or low-grade T3N0/T1-T3N1), RPA-IIB (high-grade T3N0/T1-T3N1 or low-grade T1-T3N2), and RPA-III (high-grade T1-T3N2; median survival: 42, 26, 19, 15, and 12 months, respectively; P < 0.001). The RPA staging outperformed the 8th AJCC classifications in terms of discrimination (concordance index, 0.585 versus 0.565; P < 0.001) and prognostic homogeneity. Tumor grade can provide additional prognostic information to the 8th AJCC staging. The proposed RPA staging is a superior risk-stratified tool to the 8th AJCC staging and is not substantially more complex.