Machine-Learning and Radiomics-Based Preoperative Prediction of Ki-67 Expression in Glioma Using MRI Data

Jiaying Ni; Hongjian Zhang; Qing Yang; Xiao Fan; Junqing Xu; Jianing Sun; Junxia Zhang; Yifang Hu; Zheming Xiao; Yuhong Zhao; Hongli Zhu; Xian Shi; Wei Feng; Junjie Wang; Cheng Wan; Xin Zhang; Yun Liu; Yongping You; Yun Yu

doi:10.1016/j.acra.2024.02.009

Machine-Learning and Radiomics-Based Preoperative Prediction of Ki-67 Expression in Glioma Using MRI Data

Acad Radiol. 2024 Mar 7:S1076-6332(24)00079-5. doi: 10.1016/j.acra.2024.02.009. Online ahead of print.

Authors

Jiaying Ni¹, Hongjian Zhang¹, Qing Yang², Xiao Fan², Junqing Xu³, Jianing Sun⁴, Junxia Zhang², Yifang Hu², Zheming Xiao¹, Yuhong Zhao¹, Hongli Zhu¹, Xian Shi¹, Wei Feng¹, Junjie Wang⁵, Cheng Wan⁵, Xin Zhang⁵, Yun Liu⁵, Yongping You², Yun Yu⁶

Affiliations

¹ School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu 211166, China.
² Department of Neurosurgery, The First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu 210029, China.
³ The second Clinical Medical School, Nanjing Medical University, Nanjing 211166, China.
⁴ School of Public Health, Nanjing Medical University, Nanjing 211166, China.
⁵ School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu 211166, China; Institute of Medical Informatics and Management, Nanjing Medical University, Jiangsu 210029, China.
⁶ School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu 211166, China; Institute of Medical Informatics and Management, Nanjing Medical University, Jiangsu 210029, China. Electronic address: yuyun@njmu.edu.cn.

PMID: 38458887
DOI: 10.1016/j.acra.2024.02.009

Abstract

Background: Gliomas are the most common primary brain tumours and constitute approximately half of all malignant glioblastomas. Unfortunately, patients diagnosed with malignant glioblastomas typically survive for less than a year. In light of this circumstance, genotyping is an effective means of categorising gliomas. The Ki67 proliferation index, a widely used marker of cellular proliferation in clinical contexts, has demonstrated potential for predicting tumour classification and prognosis. In particular, magnetic resonance imaging (MRI) plays a vital role in the diagnosis of brain tumours. Using MRI to extract glioma-related features and construct a machine learning model offers a viable avenue to classify and predict the level of Ki67 expression.

Methods: This study retrospectively collected MRI data and postoperative immunohistochemical results from 613 glioma patients from the First Affliated Hospital of Nanjing Medical University. Subsequently, we performed registration and skull stripping on the four MRI modalities: T1-weighted (T1), T2-weighted (T2), T1-weighted with contrast enhancement (T1CE), and Fluid Attenuated Inversion Recovery (FLAIR). Each modality's segmentation yielded three distinct tumour regions. Following segmentation, a comprehensive set of features encompassing texture, first-order, and shape attributes were extracted from these delineated regions. Feature selection was conducted using the least absolute shrinkage and selection operator (LASSO) algorithm with subsequent sorting to identify the most important features. These selected features were further analysed using correlation analysis to finalise the selection for machine learning model development. Eight models: logistic regression (LR), naive bayes, decision tree, gradient boosting tree, and support vector classification (SVM), random forest (RF), XGBoost, and LightGBM were used to objectively classify Ki67 expression.

Results: In total, 613 patients were enroled in the study, and 24,455 radiomic features were extracted from each patient's MRI. These features were eventually reduced to 36 after LASSO screening, RF importance ranking, and correlation analysis. Among all the tested machine learning models, LR and linear SVM exhibited superior performance. LR achieved the highest area under the curve score of 0.912 ± 0.036, while linear SVM obtained the top accuracy with a score of 0.884 ± 0.031.

Conclusion: This study introduced a novel approach for classifying Ki67 expression levels using MRI, which has been proven to be highly effective. With the LR model at its core, our method demonstrated its potential in signalling a promising avenue for future research. This innovative approach of predicting Ki67 expression based on MRI features not only enhances our understanding of cell activity but also represents a significant leap forward in brain glioma research. This underscores the potential of integrating machine learning with medical imaging to aid in the diagnosis and prognosis of complex diseases.

Keywords: Ki-67; MRI; Machine learning; Radiomics.