A Radiomics-Based Machine Learning Model for Prediction of Tumor Mutational Burden in Lower-Grade Gliomas

Luu Ho Thanh Lam; Ngan Thy Chu; Thi-Oanh Tran; Duyen Thi Do; Nguyen Quoc Khanh Le

doi:10.3390/cancers14143492

A Radiomics-Based Machine Learning Model for Prediction of Tumor Mutational Burden in Lower-Grade Gliomas

Cancers (Basel). 2022 Jul 18;14(14):3492. doi: 10.3390/cancers14143492.

Authors

Luu Ho Thanh Lam^{1

2}, Ngan Thy Chu³, Thi-Oanh Tran^{4

5}, Duyen Thi Do⁶, Nguyen Quoc Khanh Le^{7

8

9

10}

Affiliations

¹ International Master/Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan.
² Children's Hospital 2, Ho Chi Minh City 70000, Vietnam.
³ City Children's Hospital, Ho Chi Minh City 70000, Vietnam.
⁴ International Ph.D. Program for Cell Therapy and Regeneration Medicine, College of Medicine, Taipei Medical University, Taipei 110, Taiwan.
⁵ Hematology and Blood Transfusion Center, Bach Mai Hospital, Hanoi 115-19, Vietnam.
⁶ Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei 106, Taiwan.
⁷ Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 106, Taiwan.
⁸ Research Center for Artificial Intelligence in Medicine, Taipei Medical University, Taipei 106, Taiwan.
⁹ Translational Imaging Research Center, Taipei Medical University Hospital, Taipei 110, Taiwan.
¹⁰ Neuroscience Research Center, Taipei Medical University, Taipei 110, Taiwan.

Abstract

Glioma is a Center Nervous System (CNS) neoplasm that arises from the glial cells. In a new scheme category of the World Health Organization 2016, lower-grade gliomas (LGGs) are grade II and III gliomas. Following the discovery of suppression of negative immune regulation, immunotherapy is a promising effective treatment method for lower-grade glioma patients. However, the therapy is not effective for all types of LGGs, and tumor mutational burden (TMB) has been shown to be a potential biomarker for the susceptibility and prognosis of immunotherapy in lower-grade glioma patients. Hence, predicting TMB benefits brain cancer patients. In this study, we investigated the correlation between MRI (magnetic resonance imaging)-based radiomic features and TMB in LGG by applying machine learning methods. Six machine learning classifiers were examined on the features extracted from the genetic algorithm. Subsequently, a light gradient boosting machine (LightGBM) succeeded in selecting 11 radiomics signatures for TMB classification. Our LightGBM model resulted in high accuracy of 0.7936, and reached a balance between sensitivity and specificity, achieving 0.76 and 0.8107, respectively. To our knowledge, our study represents the best model for classification of TMB in LGG patients at present.

Keywords: genetic algorithm; lower-grade glioma; radiomics signature; tumor mutational burden.

Grants and funding

This research was funded by the Taiwan Higher Education Sprout Project by the Ministry of Education, grant number (DP2-111-21121-01-A-12). The APC was funded by DP2-111-21121-01-A-12.