Multiparametric MRI-Based Machine Learning Models for the Characterization of Cystic Renal Masses Compared to the Bosniak Classification, Version 2019: A Multicenter Study

Huanhuan Kang; Wanfang Xie; He Wang; Huiping Guo; Jiahui Jiang; Zhe Liu; Xiaohui Ding; Lin Li; Wei Xu; Jian Zhao; Xu Bai; Mengqiu Cui; Huiyi Ye; Baojun Wang; Dawei Yang; Xin Ma; Jiangang Liu; Haiyi Wang

doi:10.1016/j.acra.2024.01.003

Multiparametric MRI-Based Machine Learning Models for the Characterization of Cystic Renal Masses Compared to the Bosniak Classification, Version 2019: A Multicenter Study

Acad Radiol. 2024 Jan 18:S1076-6332(24)00003-5. doi: 10.1016/j.acra.2024.01.003. Online ahead of print.

Authors

Huanhuan Kang¹, Wanfang Xie², He Wang³, Huiping Guo¹, Jiahui Jiang⁴, Zhe Liu³, Xiaohui Ding⁵, Lin Li⁶, Wei Xu¹, Jian Zhao¹, Xu Bai¹, Mengqiu Cui¹, Huiyi Ye¹, Baojun Wang⁷, Dawei Yang⁴, Xin Ma⁷, Jiangang Liu², Haiyi Wang⁸

Affiliations

¹ Department of Radiology, First Medical Center of Chinese PLA General Hospital, No.28 Fuxing Road, Haidian District, Beijing 100853, China (H.K., H.G., W.X., J.Z., X.B., M.C., H.Y., H.W.).
² School of Engineering Medicine, Beihang University, Beijing 100191, China (W.X., J.L.); Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of China, Beijing 100191, China (W.X., J.L.).
³ Radiology Department, Peking University First Hospital, Beijing 100034, China (H.W., Z.L.).
⁴ Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing 100050, China (J.J., D.Y.).
⁵ Department of Pathology, First Medical Center, Chinese PLA General Hospital, Beijing 100853, China (X.D.).
⁶ Hospital Management Institute, Department of Innovative Medical Research, Chinese PLA General Hospital, Outpatient Building, Beijing 100853, China (L.L.).
⁷ Department of Urology, Third Medical Center of Chinese PLA General Hospital, Beijing 100039, China (B.W., X.M.).
⁸ Department of Radiology, First Medical Center of Chinese PLA General Hospital, No.28 Fuxing Road, Haidian District, Beijing 100853, China (H.K., H.G., W.X., J.Z., X.B., M.C., H.Y., H.W.). Electronic address: wanghaiyi301@outlook.com.

PMID: 38242731
DOI: 10.1016/j.acra.2024.01.003

Abstract

Rationale and objective: Accurate differentiation between benign and malignant cystic renal masses (CRMs) is challenging in clinical practice. This study aimed to develop MRI-based machine learning models for differentiating between benign and malignant CRMs and compare the best-performing model with the Bosniak classification, version 2019 (BC, version 2019).

Methods: Between 2009 and 2021, consecutive surgery-proven CRM patients with renal MRI were enrolled in this multicenter study. Models were constructed to differentiate between benign and malignant CRMs using logistic regression (LR), random forest (RF), and support vector machine (SVM) algorithms, respectively. Meanwhile, two radiologists classified CRMs into I-IV categories according to the BC, version 2019 in consensus in the test set. A subgroup analysis was conducted to investigate the performance of the best-performing model in complicated CRMs (II-IV lesions in the test set). The performances of models and BC, version 2019 were evaluated using the area under the receiver operating characteristic curve (AUC). Performance was statistically compared between the best-performing model and the BC, version 2019.

Results: 278 and 48 patients were assigned to the training and test sets, respectively. In the test set, the AUC and accuracy of the LR model, the RF model, the SVM model, and the BC, version 2019 were 0.884 and 75.0%, 0.907 and 83.3%, 0.814 and 72.9%, and 0.893 and 81.2%, respectively. Neither the AUC nor the accuracy of the RF model that performed best were significantly different from the BC, version 2019 (P = 0.780, P = 0.065). The RF model achieved an AUC and accuracy of 0.880 and 81.0% in complicated CRMs.

Conclusions: The MRI-based RF model can accurately differentiate between benign and malignant CRMs with comparable performance to the BC, version 2019, and has good performance in complicated CRMs, which may facilitate treatment decision-making and is less affected by interobserver disagreements.

Keywords: Bosniak classification; Cystic renal masses; Machine learning; Multiparametric MRI.