Usefulness of texture analysis for grading pancreatic neuroendocrine tumors on contrast-enhanced computed tomography and apparent diffusion coefficient maps

• Published in: Japanese journal of radiology Vol. 39; no. 1; pp. 66 - 75
• Main Authors: Ohki, Kazuyoshi, Igarashi, Takao, Ashida, Hirokazu, Takenaga, Shinsuke, Shiraishi, Megumi, Nozawa, Yosuke, Ojiri, Hiroya
• Format: Journal Article
• Language: English
• Published: Tokyo Springer Japan 01.01.2021; Springer Nature B.V
• Subjects: Computed tomography; Correlation coefficient; Correlation coefficients; Diagnostic systems; Diffusion coefficient; Feature extraction; Imaging; Kurtosis; Medicine; Medicine & Public Health; Neuroendocrine tumors; Nuclear Medicine; Original Article; Pancreas; Pancreatic cancer; Radiology; Radiotherapy; Texture; Tumors; CT; Neuroendocrine neoplasm; Texture analysis; Pancreas; MR-imaging
• ISSN: 1867-1071; 1867-108X
• DOI: 10.1007/s11604-020-01038-9

Purpose To determine whether texture analysis of contrast-enhanced computed tomography (CECT) and apparent diffusion coefficient (ADC) maps could predict tumor grade (G1 vs G2–3) in patients with pancreatic neuroendocrine tumor (PNET). Materials and methods Thirty-three PNETs (22 G1 and 11 G2–3) were retrospectively reviewed. Fifty features were individually extracted from the arterial and portal venous phases of CECT and ADC maps by two radiologists. Diagnostic performance was assessed by receiver operating characteristic curves while inter-observer agreement was determined by calculating intraclass correlation coefficients (ICCs). Results G2–G3 tumors were significantly larger than G1. Seventeen features significantly differed among the two readers on univariate analysis, with ICCs > 0.6; the largest area under the curve (AUC) for features of each CECT phase and ADC map was log-sigma 1.0 joint-energy = 0.855 for the arterial phase, log-sigma 1.5 kurtosis = 0.860 for the portal venous phase, and log-sigma 1.0 correlation = 0.847 for the ADC map. The log-sigma 1.5 kurtosis of the portal venous phase showed the largest AUC in the CECT and ADC map, and its sensitivity, specificity, and accuracy were 95.5%, 72.7%, and 87.9%, respectively. Conclusion Texture analysis may aid in differentiating between G1 and G2–3 PNET.