Machine Learning Using Multiparametric Magnetic Resonance Imaging Radiomic Feature Analysis to Predict Ki-67 in World Health Organization Grade I Meningiomas

Abstract

BACKGROUND Although World Health Organization (WHO) grade I meningiomas are considered “benign” tumors, an elevated Ki-67 is one crucial factor that has been shown to influence tumor behavior and clinical outcomes. The ability to preoperatively discern Ki-67 would confer the ability to guide surgical strategy. OBJECTIVE In this study, we develop a machine learning (ML) algorithm using radiomic feature analysis to predict Ki-67 in WHO grade I meningiomas. METHODS A retrospective analysis was performed for a cohort of 306 patients who underwent surgical resection of WHO grade I meningiomas. Preoperative magnetic resonance imaging was used to perform radiomic feature extraction followed by ML modeling using least absolute shrinkage and selection operator wrapped with support vector machine through nested cross-validation on a discovery cohort (n = 230), to stratify tumors based on Ki-67 <5% and ≥5%. The final model was independently tested on a replication cohort (n = 76). RESULTS An area under the receiver operating curve (AUC) of 0.84 (95% CI: 0.78-0.90) with a sensitivity of 84.1% and specificity of 73.3% was achieved in the discovery cohort. When this model was applied to the replication cohort, a similar high performance was achieved, with an AUC of 0.83 (95% CI: 0.73-0.94), sensitivity and specificity of 82.6% and 85.5%, respectively. The model demonstrated similar efficacy when applied to skull base and nonskull base tumors. CONCLUSION Our proposed radiomic feature analysis can be used to stratify WHO grade I meningiomas based on Ki-67 with excellent accuracy and can be applied to skull base and nonskull base tumors with similar performance achieved.

Efficient Prediction of Ki-67 Proliferation Index in Meningiomas on MRI: From Traditional Radiological Findings to a Machine Learning Approach

“…Generally, models involving multiparametric feature sets are superior to models involving single-sequence feature sets [ 26 , 27 , 28 ]. Similarly, in previous research, radiomic-based machine learning algorithms were built to predict the Ki-67 status in meningiomas by enrolling the features extracted from multiple MR sequences, including T1/T2-weighted, T1-weighted contrast-enhanced (T1CE), and FLAIR [ 20 ]. Their radiomic model outperformed our model with an AUC of 0.84.…”

“…This result undoubtedly suggests that multiparametric feature sets could provide more information and assist in classification, which corroborated previous findings that some radiological features were more apparent on multiparametric MRI sequences. However, overfitting should be considered and investigated if the model can generalize the learning of the training data [ 20 ]. One major concern should be noted that there were too many features involved in their modeling compared to ours (60 vs. 14).…”

“…Advances in the extraction of high-throughput computational features encourage oncologists to convert the gray-level intensity of clinical digital images into mineable data [ 17 ], which can be subsequently analyzed by machine learning algorithms [ 18 , 19 ]. Recently, evidence suggested machine learning was feasible to stratify the Ki-67 status in WHO grade I meningiomas based on a radiomic analysis from multiparametric MRI [ 20 ]. However, the following concerns remain to be addressed: first, the generalization of this method has not been tested on multicenter data; second, it remains unknown if the results are applicable to high-grade meningiomas; third, clinical and radiologic features were not yet incorporated into the model.…”

Prediction for Mitosis-Karyorrhexis Index Status of Pediatric Neuroblastoma via Machine Learning Based 18F-FDG PET/CT Radiomics

“…Radiomics analysis using multiparametric imaging can be utilized to produce high-throughput computation feature extraction, including tumor feature extraction, size, shape, feature intensity, which can subsequently be investigated to build radiomics models that can predict tumor pathology and prognosis. One of the most obvious values of radiomics study was to optimize patient-specific therapy paradigms [ 9 ]. The application of 18 F-FDG PET/CT in neuroblastoma has been reported previously and has been confirmed its value in staging and prognosis prediction [ 10 , 11 , 12 ].…”

Applications of Radiomics and Radiogenomics in High-Grade Gliomas in the Era of Precision Medicine

“…However, clinical images are mainly evaluated with a qualitative approach, and additional untapped potential remains, which may lead to a comprehensive picture of the tumor characteristics [ 8 ]. As radiologic scans reflect the underlying pathophysiology of the tumors, quantitative assessment of these images and development of imaging biomarkers with “radiomics” can aid in understanding the tumor biology [ 9 , 10 , 11 ] and treatment response [ 8 , 12 , 13 , 14 ]. Radiomics refers to extraction of high-throughput quantitative and mineable features characterizing the underlying pathophysiology of the tumor from medical images [ 12 ].…”