The effect of CT texture-based analysis using machine learning approaches on radiologists' performance in differentiating focal-type autoimmune pancreatitis and pancreatic duct carcinoma

• Published in: Japanese journal of radiology Vol. 40; no. 11; pp. 1156 - 1165
• Main Authors: Anai, Kenta, Hayashida, Yoshiko, Ueda, Issei, Hozuki, Eri, Yoshimatsu, Yuuta, Tsukamoto, Jun, Hamamura, Toshihiko, Onari, Norihiro, Aoki, Takatoshi, Korogi, Yukunori
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.11.2022; Springer Nature B.V
• Subjects: Autoimmune Pancreatitis - diagnostic imaging; Carcinoma, Pancreatic Ductal - diagnostic imaging; Classifiers; Computed tomography; Data compression; Diagnosis, Differential; Diagnostic systems; Humans; Image compression; Image contrast; Image enhancement; Imaging; Machine Learning; Medicine; Medicine & Public Health; Nuclear Medicine; Original; Original Article; Pancreas; Pancreatic carcinoma; Pancreatic Ducts; Pancreatic Neoplasms; Pancreatic Neoplasms - diagnostic imaging; Pancreatitis; Principal components analysis; Radiologists; Radiology; Radiotherapy; Retrospective Studies; Support vector machines; Texture; Tomography, X-Ray Computed - methods; CT; Pancreatic duct carcinoma; Texture analysis; Autoimmune pancreatitis; Machine learning
• ISSN: 1867-1071; 1867-108X
• DOI: 10.1007/s11604-022-01298-7

Purpose To develop a support vector machine (SVM) classifier using CT texture-based analysis in differentiating focal-type autoimmune pancreatitis (AIP) and pancreatic duct carcinoma (PD), and to assess the radiologists’ diagnostic performance with or without SVM. Materials and methods This retrospective study included 50 patients (20 patients with focal-type AIP and 30 patients with PD) who underwent dynamic contrast-enhanced CT. Sixty-two CT texture-based features were extracted from 2D images of the arterial and portal phase CTs. We conducted data compression and feature selections using principal component analysis (PCA) and produced the SVM classifier. Four readers participated in this observer performance study and the statistical significance of differences with and without the SVM was assessed by receiver operating characteristic (ROC) analysis. Results The SVM performance indicated a high performance in differentiating focal-type AIP and PD (AUC = 0.920). The AUC for all 4 readers increased significantly from 0.827 to 0.911 when using the SVM outputs ( p  = 0.010). The AUC for inexperienced readers increased significantly from 0.781 to 0.905 when using the SVM outputs ( p  = 0.310). The AUC for experienced readers increased from 0.875 to 0.912 when using the SVM outputs, however, there was no significant difference ( p  = 0.018). Conclusion The use of SVM classifier using CT texture-based features improved the diagnostic performance for differentiating focal-type AIP and PD on CT.