CT-Based Radiomics Analysis of Different Machine Learning Models for Discriminating the Risk Stratification of Pheochromocytoma and Paraganglioma: A Multicenter Study

Yongjie Zhou; Yuan Zhan; Jinhong Zhao; Linhua Zhong; Yongming Tan; Wei Zeng; Qiao Zeng; Mingxian Gong; Aihua Li; Lianggeng Gong; Lan Liu

doi:10.1016/j.acra.2024.01.008

CT-Based Radiomics Analysis of Different Machine Learning Models for Discriminating the Risk Stratification of Pheochromocytoma and Paraganglioma: A Multicenter Study

Acad Radiol. 2024 Jan 31:S1076-6332(24)00009-6. doi: 10.1016/j.acra.2024.01.008. Online ahead of print.

Authors

Yongjie Zhou¹, Yuan Zhan², Jinhong Zhao³, Linhua Zhong⁴, Yongming Tan⁵, Wei Zeng⁴, Qiao Zeng⁴, Mingxian Gong⁴, Aihua Li⁴, Lianggeng Gong³, Lan Liu⁶

Affiliations

¹ Department of Radiology, Jiangxi Cancer Hospital, Nanchang, China; The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China; Jiangxi Clinical Research Center for Cancer, Nanchang, China.
² Department of Pathology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, China.
³ Department of Radiology, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, China.
⁴ Department of Radiology, Jiangxi Cancer Hospital, Nanchang, China.
⁵ Department of Radiology, The First Affiliated Hospital, Jiangxi Medical College, Nanchang University, Nanchang, China.
⁶ Department of Radiology, Jiangxi Cancer Hospital, Nanchang, China; The Second Affiliated Hospital of Nanchang Medical College, Nanchang, China; Jiangxi Clinical Research Center for Cancer, Nanchang, China. Electronic address: 919986102@qq.com.

PMID: 38302388
DOI: 10.1016/j.acra.2024.01.008

Abstract

Rationale and objectives: Using different machine learning models CT-based radiomics to integrate clinical radiological features to discriminating the risk stratification of pheochromocytoma/paragangliomas (PPGLs).

Materials and methods: The present study included 201 patients with PPGLs from three hospitals (training set: n = 125; external validation set: n = 45; external test set: n = 31). Patients were divided into low-risk and high-risk groups using a staging system for adrenal pheochromocytoma and paraganglioma (GAPP). We extracted and selected CT radiomics features, and built radiomics models using support vector machines (SVM), k-nearest neighbors, random forests, and multilayer perceptrons. Using receiver operating characteristic curve analysis to select the optimal radiomics model, a combined model was built using the output of the optimal radiomics model and clinical radiological features, and its accuracy and clinical applicability were evaluated using calibration curves and clinical decision curve analysis (DCA).

Results: Finally, 13 radiomics features were selected to construct machine learning models. In the radiomics model, the SVM model demonstrated higher accuracy and stability, with an AUC value of 0.915 in the training set, 0.846 in external validation set, and 0.857 in external test set. Combining the outputs of SVM models with two clinical radiological features, a combined model constructed has demonstrated optimal risk stratification ability for PPGLs with an AUC of 0.926 for the training set, 0.883 for the external validation set, and 0.899 for the external test set. The calibration curve and DCA show good calibration accuracy and clinical effectiveness for the combined model.

Conclusion: Combined model that integrates radiomics and clinical radiological features can discriminate the risk stratification of PPGLs.

Keywords: Computed tomography; Machine learning; Paraganglioma; Pheochromocytoma; Risk classification.