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

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

doi:10.1016/j.acra.2023.06.033

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

Acad Radiol. 2024 Feb;31(2):639-647. doi: 10.1016/j.acra.2023.06.033. Epub 2023 Jul 26.

Authors

Shuang Li¹, Xiaorui Su², Juan Peng³, Ni Chen⁴, Yanhui Liu⁵, Simin Zhang², Hanbing Shao², Qiaoyue Tan⁶, Xibiao Yang⁷, Yaou Liu⁸, Qiyong Gong⁹, Qiang Yue¹⁰

Affiliations

¹ Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China (S.L., X.S., S.Z., H.S., Q.T., Q.G.); Research Unit of Psychoradiology, Chinese Academy of Medical Sciences, Chengdu, Sichuan, China (S.L.); Functional and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital of Sichuan University, Chengdu, Sichuan, China (S.L.).
² Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China (S.L., X.S., S.Z., H.S., Q.T., Q.G.).
³ Department of Radiology, The First Affiliated Hospital, Chongqing Medical University, Chongqing, China (J.P.).
⁴ Department of Pathology, West China Hospital of Sichuan University, Chengdu, Sichuan, China (N.C.).
⁵ Department of Neurosurgery, West China Hospital of Sichuan University, Chengdu, Sichuan, China (Y.L.).
⁶ Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China (S.L., X.S., S.Z., H.S., Q.T., Q.G.); Division of Radiation Physics, State Key Laboratory of Biotherapy and Cancer Center, West China Hospital of Sichuan University, Chengdu, Sichuan, China (Q.T.).
⁷ Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China (X.Y., Q.Y.).
⁸ Department of Radiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China (Y.L.).
⁹ Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China (S.L., X.S., S.Z., H.S., Q.T., Q.G.); Department of Radiology, West China Xiamen Hospital of Sichuan University, Xiamen, Fujian, China (Q.G.).
¹⁰ Department of Radiology, West China Hospital of Sichuan University, Chengdu, Sichuan, China (X.Y., Q.Y.). Electronic address: [email protected].

PMID: 37507329
DOI: 10.1016/j.acra.2023.06.033

Abstract

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: VOI_{tumor and peritumor}, VOI_whole, and VOI_interface. 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 VOI_interface 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.

Keywords: Astrocytoma; Glioma; Machine learning; Magnetic resonance imagine; Radiomic.

Publication types

Multicenter Study
Research Support, Non-U.S. Gov't

MeSH terms

Astrocytoma* / diagnostic imaging
Astrocytoma* / pathology
Glioma* / diagnostic imaging
Glioma* / pathology
Humans
Magnetic Resonance Imaging / methods
Nomograms
ROC Curve
Radiomics
Retrospective Studies