Predicting symptomatic mesenteric mass in neuroendocrine tumors using radiomics

in Endocrine-Related Cancer
View More View Less
  • 1 A Blazevic, Endocrinologie, Erasmus MC, Rotterdam, Netherlands
  • 2 M Starmans, Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands
  • 3 T Brabander, Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands
  • 4 R Dwarkasingh, Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands
  • 5 R van Gils, Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands
  • 6 ( Hofland, Interne Medicine, section Endocrinology, Erasmus MC, Rotterdam, Netherlands
  • 7 G Franssen, Department of Surgery, Erasmus MC - University Medical Centre Rotterdam, ROTTERDAM, Netherlands
  • 8 R Feelders, Internal Medicine, Erasmus Medical Center, Rotterdam, Netherlands
  • 9 W Niessen, Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands
  • 10 S Klein, Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, Netherlands
  • 11 W de Herder, Internal Medicine, Erasmus MC, Rotterdam, Netherlands

Correspondence: Anela Blazevic, Email: a.blazevic.1@erasmusmc.nl
Restricted access

Metastatic mesenteric masses of small intestinal neuroendocrine tumors (SI-NETs) are known to often cause intestinal complications. The aim of this study was to identify patients at risk to develop these complications based on routinely acquired CT scans using a standardised set of clinical criteria and radiomics. Retrospectively, CT scans of SI-NET patients with a mesenteric mass were included and systematically evaluated by five clinicians. For the radiomics approach, 1081 features were extracted from segmentations of the mesenteric mass and mesentery, after which radiomics models were created using a combination of machine learning approaches. The performances were compared to a multidisciplinary tumor board (MTB). The dataset included 68 patients (32 asymptomatic, 36 symptomatic). The clinicians had AUCs between 0.62–0.85 and showed poor agreement. The best radiomics model had a mean AUC of 0.77. The MTB had a sensitivity of 0.64 and specificity of 0.68. We conclude that systematic clinical evaluation of SI-NETs to predict intestinal complications had a similar performance than an expert MTB, but poor inter-observer agreement. Radiomics showed a similar performance and is objective, and thus is a promising tool to correctly identify these patients. However, further validation is needed before transition to clinical practice.

 

Society for Endocrinology