Reproducibility of CT texture features of pancreatic neuroendocrine neoplasms

• Published in: European journal of radiology 2020-12, Vol.133, p.109371-109371, Article 109371
• Main Authors: Gruzdev, I.S., Zamyatina, K.A., Tikhonova, V.S., Kondratyev, E.V., Glotov, A.V., Karmazanovsky, G.G., Revishvili, A. Sh
• Format: Article
• Language: English
• Subjects: Humans; Neoplasms; Neuroendocrine neoplasm; Pancreas; Pancreatic Neoplasms - diagnostic imaging; Radiomics; Reproducibility of Results; Retrospective Studies; Texture analysis; Tomography, X-Ray Computed
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2020.109371

•67 % of the PNENs textural features remain reproducible.•Reproducibility is more dependent on scanning conditions than on segmentation.•It is possible to choose reliable features for PNENs structure assessment. To evaluate the reproducibility of textural features of pancreatic neuroendocrine neoplasms (PNENs), obtained under various CT-scanning conditions. We included 12 patients with PNENs and 2 contrast enhanced CT (CECT): 1) from our center according to standard CT-protocol; 2) from another institution. Two radiologists independently segmented the entire neoplasm volume using a 3D region of interest by LIFEx application on the arterial phase and then copied it to the other phases. 52 texture features were calculated for each phase. As a criterion for the segmentation consistency, a value of neoplasm volume was compared using the Bland-Altman method. The Kendall concordance coefficient was calculated to assess the texture features reproducibility in three scenarios: 1) different radiologists, same CECT; 2) same radiologist, different CECT; 3) different radiologists, different CECT. For the scenario 1 the neoplasm volumes (except one large PNEN) were found within two standard deviations; this indicates high consistency of the segmentation. For the first scenario, Kendall's coefficient exceeded a threshold of 0.7 for all 52 features for all CT phases. For the second and third scenario, the concordance coefficient exceeded a threshold of 0.7 in 38, 28, 42, 45 and in 36, 25, 36, 44 features for the native, arterial, venous and delayed phases, respectively. The highest reproducibility was found in the first scenario compared to the second and third: 100 % vs. 74 % and 67 %. Reproducible texture features can be reliably used to assess the PNENs structure.