Differentiation of Low-Grade Astrocytoma From Anaplastic Astrocytoma Using Radiomics-Based Machine Learning Techniques

Boran Chen; Chaoyue Chen; Jian Wang; Yuen Teng; Xuelei Ma; Jianguo Xu

doi:10.3389/fonc.2021.521313

Differentiation of Low-Grade Astrocytoma From Anaplastic Astrocytoma Using Radiomics-Based Machine Learning Techniques

Front Oncol. 2021 Jun 1:11:521313. doi: 10.3389/fonc.2021.521313. eCollection 2021.

Authors

Boran Chen¹, Chaoyue Chen^{1

2}, Jian Wang³, Yuen Teng¹, Xuelei Ma^{2

4}, Jianguo Xu¹

Affiliations

¹ Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, China.
² State Key Laboratory of Biotherapy and Cancer Center, West China Hospital, Sichuan University, and Collaborative Innovation Center for Biotherapy, Chengdu, China.
³ School of Computer Science, Nanjing University of Science and Technology, Nanjing, China.
⁴ Department of Biotherapy, Cancer Center, West China Hospital, Sichuan University, Chengdu, China.

Abstract

Purpose: To investigate the diagnostic ability of radiomics-based machine learning in differentiating atypical low-grade astrocytoma (LGA) from anaplastic astrocytoma (AA).

Methods: The current study involved 175 patients diagnosed with LGA (n = 95) or AA (n = 80) and treated in the Neurosurgery Department of West China Hospital from April 2010 to December 2019. Radiomics features were extracted from pre-treatment contrast-enhanced T1 weighted imaging (T1C). Nine diagnostic models were established with three selection methods [Distance Correlation, least absolute shrinkage, and selection operator (LASSO), and Gradient Boosting Decision Tree (GBDT)] and three classification algorithms [Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and random forest (RF)]. The sensitivity, specificity, accuracy, and areas under receiver operating characteristic curve (AUC) of each model were calculated. Diagnostic ability of each model was evaluated based on these indexes.

Results: Nine radiomics-based machine learning models with promising diagnostic performances were established. For LDA-based models, the optimal one was the combination of LASSO + LDA with AUC of 0.825. For SVM-based modes, Distance Correlation + SVM represented the most promising diagnostic performance with AUC of 0.808. And for RF-based models, Distance Correlation + RF were observed to be the optimal model with AUC of 0.821.

Conclusion: Radiomic-based machine-learning has the potential to be utilized in differentiating atypical LGA from AA with reliable diagnostic performance.

Keywords: astrocytoma; glioma; machine learning; radiomics; texture analysis.