Evaluation of tumor pseudocapsule using computed tomography-based radiomics in pancreatic neuroendocrine tumors to predict prognosis and guide surgical strategy: a cohort study
Yan Wang, Wenchao Gu, Dan Huang, Wuhu Zhang, Yingli Chen, Junfeng Xu, Zheng Li, Chenjie Zhou, Jie Chen, Xiaowu Xu, Wei Tang, Xianjun Yu, Shunrong Ji
Abstract
BACKGROUND: To date, indications for a surgical approach to small pancreatic neuroendocrine tumors (PanNETs) remain controversial. This cohort study aimed to identify the pseudocapsule status preoperatively to estimate the rationality of enucleation and survival prognosis of PanNETs, particularly in small tumors. MATERIALS AND METHODS: Clinicopathological data were collected from patients with PanNETs who underwent the first pancreatectomy at Fudan University Shanghai Cancer Center (n = 578) between February 2012 and September 2023. Kaplan-Meier curves were constructed to visualize prognostic differences. Five distinct tissue samples were obtained for single-cell RNA sequencing (scRNA-seq) to evaluate variations in the tumor microenvironment. Radiological features were extracted from preoperative arterial-phase contrast-enhanced computed tomography. The performance of the pseudocapsule radiomics model was assessed using the area under the curve (AUC) metric. RESULTS: A total of 475 cases [mean (SD) age, 53.01 (12.20) years; female vs. male, 1.24:1] were eligible for this study. The mean pathological diameter of tumor was 2.99 cm [median: 2.50 cm; interquartile range (IQR): 1.50-4.00 cm]. These cases were stratified into complete (223, 46.95%) and incomplete (252, 53.05%) pseudocapsule groups. A statistically significant difference in aggressive indicators was observed between the two groups ( P < 0.001). Through scRNA-seq analysis, we identified that the incomplete group presented a markedly immunosuppressive microenvironment. Regarding the impact on recurrence-free survival, the 3- and 5-year rates were 94.8% and 92.5%, respectively, for the complete pseudocapsule group, compared to 76.7% and 70.4% for the incomplete pseudocapsule group. The radiomics-predictive model has a significant discrimination for the state of the pseudocapsule, particularly in small tumors (AUC, 0.744; 95% confidence interval, 0.652-0.837). CONCLUSION: By combining computed tomography-based radiomics and machine learning for preoperative identification of pseudocapsule status, the intact group is more likely to benefit from enucleation.