Development and External Validation of an MRI-based Radiomics Nomogram to Distinguish Circumscribed Astrocytic Gliomas and Diffuse Gliomas: A Multicenter Study

作者全名：Li, Shuang; Su, Xiaorui; Peng, Juan; Chen, Ni; Liu, Yanhui; Zhang, Simin; Shao, Hanbing; Tan, Qiaoyue; Yang, Xibiao; Liu, Yaou; Gong, Qiyong; Yue, Qiang

作者地址：[Li, Shuang; Su, Xiaorui; Zhang, Simin; Shao, Hanbing; Tan, Qiaoyue; Gong, Qiyong] Sichuan Univ, Dept Radiol, Huaxi MR Res Ctr HMRRC, West China Hosp, Chengdu, Sichuan, Peoples R China; [Li, Shuang] Chinese Acad Med Sci, Res Unit Psychoradiol, Chengdu, Sichuan, Peoples R China; [Li, Shuang] Sichuan Univ, West China Hosp, Funct & Mol Imaging Key Lab Sichuan Prov, Chengdu, Sichuan, Peoples R China; [Peng, Juan] Chongqing Med Univ, Affiliated Hosp 1, Dept Radiol, Chongqing, Peoples R China; [Chen, Ni] Sichuan Univ, West China Hosp, Dept Pathol, Chengdu, Sichuan, Peoples R China; [Liu, Yanhui] Sichuan Univ, Dept Neurosurg, West China Hosp, Chengdu, Sichuan, Peoples R China; [Tan, Qiaoyue] Sichuan Univ, Div Radiat Phys, State Key Lab Biotherapy, Chengdu, Sichuan, Peoples R China; [Tan, Qiaoyue] Sichuan Univ, Canc Ctr, West China Hosp, Chengdu, Sichuan, Peoples R China; [Yang, Xibiao; Yue, Qiang] Sichuan Univ, Dept Radiol, West China Hosp, Chengdu, Sichuan, Peoples R China; [Liu, Yaou] Capital Med Univ, Beijing Tiantan Hosp, Dept Radiol, Beijing, Peoples R China; [Gong, Qiyong] Sichuan Univ, Dept Radiol, West China Xiamen Hosp, Xiamen, Fujian, Peoples R China

通信作者：Yue, Q (通讯作者)，Sichuan Univ, Dept Radiol, West China Hosp, Chengdu, Sichuan, Peoples R China.

来源：ACADEMIC RADIOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001197637900001

JCR分区：Q1

影响因子：3.8

年份：2024

卷号：31

期号：2

开始页：639

结束页：647

文献类型：Article

关键词：Glioma; Astrocytoma; Radiomic; Machine learning; Magnetic resonance imagine.

摘要：Rationale and Objectives: The 5th edition of the World Health Organization classification of tumors of the Central Nervous System (WHO CNS) has introduced the term "diffuse" and its counterpart "circumscribed" to the category of gliomas. This study aimed to develop and validate models for distinguishing circumscribed astrocytic gliomas (CAGs) from diffuse gliomas (DGs). Materials and Methods: We retrospectively analyzed magnetic resonance imaging (MRI) data from patients with CAGs and DGs across three institutions. After tumor segmentation, three volume of interest (VOI) types were obtained: VOItumor and peritumor, VOIwhole, and VOIinterface. Clinical and combined models (incorporating radiomics and clinical features) were also established. To address imbalances in training dataset, Synthetic Minority Oversampling Technique was employed. Results: A total of 475 patients (DGs: n = 338, CAGs: n = 137) were analyzed. The VOIinterface model demonstrated the best performance for differentiating CAGs from DGs, achieving an area under the curve (AUC) of 0.806 and area under the precision-recall curve (PRAUC) of 0.894 in the cross-validation set. Using analysis of variance (ANOVA) feature selector and Support Vector Machine (SVM) classifier, seven features were selected. The model achieved an AUC and AUPRC of 0.912 and 0.972 in the internal validation dataset, and 0.897 and 0.930 in the external validation dataset. The combined model, incorporating interface radiomics and clinical features, showed improved performance in the external validation set, with an AUC of 0.94 and PRAUC of 0.959. Conclusion: Radiomics models incorporating the peritumoral area demonstrate greater potential for distinguishing CAGs from DGs compared to intratumoral models. These findings may hold promise for evaluating tumor nature before surgery and improving clinical management of glioma patients.

基金机构：National Natural Science Foundation of China [82271961]; Sichuan Provincial Foundation of Science and Technology [2019YFS0428, 2022YFS0073]

基金资助正文：This work was supported by the National Natural Science Foundation of China (Grant No. 82271961) and the Sichuan Provincial Foundation of Science and Technology (Grant Nos. 2019YFS0428 and 2022YFS0073) .