Machine Learning-Based Radiological Features and Diagnostic Predictive Model of Xanthogranulomatous Cholecystitis

Qiao-Mei Zhou; Chuan-Xian Liu; Jia-Ping Zhou; Jie-Ni Yu; You Wang; Xiao-Jie Wang; Jian-Xia Xu; Ri-Sheng Yu

doi:10.3389/fonc.2022.792077

Machine Learning-Based Radiological Features and Diagnostic Predictive Model of Xanthogranulomatous Cholecystitis

Front Oncol. 2022 Feb 24:12:792077. doi: 10.3389/fonc.2022.792077. eCollection 2022.

Authors

Qiao-Mei Zhou¹, Chuan-Xian Liu², Jia-Ping Zhou¹, Jie-Ni Yu¹, You Wang³, Xiao-Jie Wang¹, Jian-Xia Xu⁴, Ri-Sheng Yu¹

Affiliations

¹ Department of Radiology, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
² Department of Radiology, Jiaxing Hospital of Traditional Chinese Medicine, Jiaxing, China.
³ Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
⁴ Department of Radiology, The Second Affiliated Hospital, Zhejiang Chinese Medical University, Hangzhou, China.

Abstract

Background: Xanthogranulomatous cholecystitis (XGC) is a rare benign chronic inflammatory disease of the gallbladder that is sometimes indistinguishable from gallbladder cancer (GBC), thereby affecting the decision of the choice of treatment. Thus, this study aimed to analyse the radiological characteristics of XGC and GBC to establish a diagnostic prediction model for differential diagnosis and clinical decision-making.

Methods: We investigated radiological characteristics confirmed by the RandomForest and Logistic regression to establish computed tomography (CT), magnetic resonance imaging (MRI), CT/MRI models and diagnostic prediction model, and performed receiver operating characteristic curve (ROC) analysis to prove the effectiveness of the diagnostic prediction model.

Results: Based on the optimal features confirmed by the RandomForest method, the mean area under the curve (AUC) of the ROC of the CT and MRI models was 0.817 (mean accuracy = 0.837) and 0.839 (mean accuracy = 0.842), respectively, whereas the CT/MRI model had a considerable predictive performance with the mean AUC of 0.897 (mean accuracy = 0.906). The diagnostic prediction model established for the convenience of clinical application was similar to the CT/MRI model with the mean AUC and accuracy of 0.888 and 0.898, respectively, indicating a preferable diagnostic efficiency in distinguishing XGC from GBC.

Conclusions: The diagnostic prediction model showed good diagnostic accuracy for the preoperative discrimination of XGC and GBC, which might aid in clinical decision-making.

Keywords: RandomForest; Xanthogranulomatous cholecystitis (XGC); diagnostic prediction model; gallbladder cancer; radiological features.