CT-derived radiomic features to discriminate histologic characteristics of pancreatic neuroendocrine tumors

Abstract

To assess the ability of radiomic features (RF) extracted from contrast-enhanced CT images (ceCT) and non-contrast-enhanced (non-ceCT) in discriminating histopathologic characteristics of pancreatic neuroendocrine tumors (panNET). panNET contours were delineated on pre-surgical ceCT and non-ceCT. First- second- and higher-order RF (adjusted to eliminate redundancy) were extracted and correlated with histological panNET grade (G1 vs G2/G3), metastasis, lymph node invasion, microscopic vascular infiltration. Mann–Whitney with Bonferroni corrected p values assessed differences. Discriminative power of significant RF was calculated for each of the end-points. The performance of conventional-imaged-based-parameters was also compared to RF. Thirty-nine patients were included (mean age 55-years-old; 24 male). Mean diameters of the lesions were 24\u2009×\u200927 mm. Sixty-nine RF were considered. Sphericity could discriminate high grade tumors (AUC\u2009=\u20090.79, p\u2009=\u20090.002). Tumor volume (AUC\u2009=\u20090.79, p\u2009=\u20090.003) and several non-ceCT and ceCT RF were able to identify microscopic vascular infiltration: voxel-alignment, neighborhood intensity-difference and intensity-size-zone families (AUC\u2009≥\u20090.75, p\u2009<\u20090.001); voxel-alignment, intensity-size-zone and co-occurrence families (AUC\u2009≥\u20090.78, p\u2009≤\u20090.002), respectively). Non-ceCT neighborhood-intensity-difference (AUC\u2009=\u20090.75, p\u2009=\u20090.009) and ceCT intensity-size-zone (AUC\u2009=\u20090.73, p\u2009=\u20090.014) identified lymph nodal invasion; several non-ceCT and ceCT voxel-alignment family features were discriminative for metastasis (p\u2009<\u20090.01, AUC\u2009=\u20090.80–0.85). Conventional CT ‘necrosis’ could discriminate for microscopic vascular invasion (AUC\u2009=\u20090.76, p\u2009=\u20090.004) and ‘arterial vascular invasion’ for microscopic metastasis (AUC\u2009=\u20090.86, p\u2009=\u20090.001). No conventional-imaged-based-parameter was significantly associated with grade and lymph node invasion. Radiomic features can discriminate histopathology of panNET, suggesting a role of radiomics as a non-invasive tool for tumor characterization. Trial registration number: NCT03967951, 30/05/2019