Preoperative assessment of lymph nodal metastases with [ 68 Ga]Ga-DOTATOC PET radiomics for improved surgical planning in well-differentiated pancreatic neuroendocrine tumours.

Purpose: Accurate identification of lymph node (LN) metastases is pivotal for surgical planning of pancreatic neuroendocrine tumours (PanNETs); however, current imaging techniques have sub-optimal diagnostic sensitivity. Aim of this study is to investigate whether [ ⁶⁸ Ga]Ga-DOTATOC PET radiomics might improve the identification of LN metastases in patients with non-functioning PanNET (NF-PanNET) referred to surgical intervention.
Methods: Seventy-two patients who performed preoperative [ ⁶⁸ Ga]Ga-DOTATOC PET between December 2017 and March 2022 for NF-PanNET. [ ⁶⁸ Ga]Ga-DOTATOC PET qualitative assessment of LN metastases was measured using diagnostic balanced accuracy (bACC), sensitivity (SN), specificity (SP), positive and negative predictive values (PPV, NPV). SUVmax, SUVmean, Somatostatin receptor density (SRD), total lesion SRD (TLSRD) and IBSI-compliant radiomic features (RFs) were obtained from the primary tumours. To predict LN involvement, these parameters were engineered, selected and used to train different machine learning models. Models were validated using tenfold repeated cross-validation and control models were developed. Models' bACC, SN, SP, PPV and NPV were collected and compared (Kruskal-Wallis, Mann-Whitney).
Results: LN metastases were detected in 29/72 patients at histology. [ ⁶⁸ Ga]Ga-DOTATOC PET qualitative examination of LN involvement provided bACC = 60%, SN = 24%, SP = 95%, PPV = 78% and NPV = 65%. The best-performing radiomic model provided a bACC = 70%, SN = 77%, SP = 61%, PPV = 60% and NPV = 83% (outperforming the control model, p < 0.05*).
Conclusion: In this study, [ ⁶⁸ Ga]Ga-DOTATOC PET radiomics allowed to increase diagnostic sensitivity in detecting LN metastases from 24 to 77% in NF-PanNET patients candidate to surgery. Especially in case of micrometastatic involvement, this approach might assist clinicians in a better patients' stratification.
(© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)