IDDF2023-ABS-0128 Ct-based nomogram development and validation to predict SSTR2, VEGFR2, and mgmt expression for pancreatic neuroendocrine neoplasms

Background

To establish and validate a model to predict somatostatin receptor 2 (SSTR2), vascular endothelial growth factor receptor 2 (VEGFR2), and O⁶-methylguanine-DNA methyltransferase (MGMT) expression in pancreatic neuroendocrine neoplasms (pNENs) based on computed tomography (CT) images.

Methods

Data from 85 patients with 88 pathologically confirmed pNENs, who underwent contrast-enhanced CT before radical resection, were retrospectively collected. Immunohistochemical analysis was performed for SSTR2 (n=86), VEGFR2 (n=53), and MGMT (n=84) expressions. The CT features were evaluated by two radiologists. The patients were randomly divided into training and test datasets for each immunohistochemical group. Nomograms were developed based on CT features associated with these immunohistochemical expressions in the training sets, which were subsequently validated and evaluated.

Results

Sex, tumour boundary, and location showed a statistically significant difference between the SSTR2 positive and negative groups; sex, maximum tumour diameter, boundary, the enhanced ratio in the venous phase, and CT ratio in arterial and venous phases were statistically different between the VEGFR2 positive and negative groups; maximum tumour diameter, boundary, shape, CT ratio in unenhanced, arterial, and venous phases, and enhanced ratio in the arterial phase were statistically different between the MGMT positive and negative groups (P<0.05). The nomograms showed good discrimination ability, with AUCs of 0.88 and 0.94 for the training and test sets in the SSTR2 group, 0.96 and 0.84 in the VEGFR2 group, and 0.81 and 0.82 in the MGMT group, respectively. Each nomogram exhibited good calibration and clinical usefulness.

Conclusions

CT-based nomograms effectively predict SSTR2, VEGFR2, and MGMT expression in pNENs and may assist clinicians in pretreatment decisions.