Performance of deep learning algorithms to distinguish high-grade glioma from low-grade glioma: A systematic review and meta-analysis

Wanyi Sun; Cheng Song; Chao Tang; Chenghao Pan; Peng Xue; Jinhu Fan; Youlin Qiao

doi:10.1016/j.isci.2023.106815

Performance of deep learning algorithms to distinguish high-grade glioma from low-grade glioma: A systematic review and meta-analysis

iScience. 2023 May 5;26(6):106815. doi: 10.1016/j.isci.2023.106815. eCollection 2023 Jun 16.

Authors

Wanyi Sun¹, Cheng Song², Chao Tang³, Chenghao Pan¹, Peng Xue², Jinhu Fan¹, Youlin Qiao²

Affiliations

¹ Department of Cancer Epidemiology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
² School of Population Medicine and Public Health, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
³ Shenzhen Maternity & Child Healthcare Hospital, Shenzhen, China.

Abstract

This study aims to evaluate deep learning (DL) performance in differentiating low- and high-grade glioma. Search online database for studies continuously published from 1st January 2015 until 16th August 2022. The random-effects model was used for synthesis, based on pooled sensitivity (SE), specificity (SP), and area under the curve (AUC). Heterogeneity was estimated using the Higgins inconsistency index (I²). 33 were ultimately included in the meta-analysis. The overall pooled SE and SP were 94% and 93%, with an AUC of 0.98. There was great heterogeneity in this field. Our evidence-based study shows DL achieves high accuracy in glioma grading. Subgroup analysis reveals several limitations in this field: 1) Diagnostic trials require standard method for data merging for AI; 2) small sample size; 3) poor-quality image preprocessing; 4) not standard algorithm development; 5) not standard data report; 6) different definition of HGG and LGG; and 7) poor extrapolation.

Keywords: Machine learning; Oncology.