AUTHOR=Fan Ziwen , Sun Zhiyan , Fang Shengyu , Li Yiming , Liu Xing , Liang Yucha , Liu Yukun , Zhou Chunyao , Zhu Qiang , Zhang Hong , Li Tianshi , Li Shaowu , Jiang Tao , Wang Yinyan , Wang Lei 

TITLE=Preoperative Radiomics Analysis of 1p/19q Status in WHO Grade II Gliomas

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.616740

DOI=10.3389/fonc.2021.616740

ISSN=2234-943X

ABSTRACT=Purpose: The present study aimed to preoperatively predict the status of 1p/19q based on radiomics analysis in patients with low grade gliomas.
Methods: This study retrospectively enrolled 157 patients with World Health Organization grade II gliomas. We acquired radiomic features from magnetic resonance images, including T1 weighted, contrast T1 weighted, and T2 weighted images. Support vector machines and elastic net with radial basis function kernel were used in nested 10-fold cross-validation loops to predict the 1p/19q status. Receiver operating characteristic analysis and precision-recall analysis were used to evaluate the model performance. Student’s t-tests were then used to compare the posterior probabilities of 1p/19q co-deletion prediction in the group with different 1p/19q status.	
Results: Six valuable radiomic features, along with age, were selected with the nested 10-fold cross-validation loops. Five features showed significant difference in patients with different 1p/19q status. The area under curve and accuracy of the predictive model were 0.8079 (95% confidence interval, 0.733–0.8755) and 0.758 (0.6879–0.8217), respectively, and the F1-score of the precision-recall curve achieved 0.6667 (0.5201–0.7705). The posterior probabilities in the 1p/19q co-deletion group were significantly different from the non-deletion group.
Conclusion: Radiomics analysis combined with machine learning can preoperatively predict 1p/19q status in WHO grade II gliomas and can compute potential predictors in a customized neurosurgery plan and glioma management.