Optimal machine learning methods for radiomic prediction models: Clinical application for preoperative T₂*‐weighted images of cervical spondylotic myelopathy

Abstract

Introduction: Predicting the postoperative neurological function of cervical spondylotic myelopathy (CSM) patients is generally based on conventional magnetic resonance imaging (MRI) patterns, but this approach is not completely satisfactory. This study utilized radiomics, which produced advanced objective and quantitative indicators, and machine learning to develop, validate, test, and compare models for predicting the postoperative prognosis of CSM.Materials and methods: In total, 151 CSM patients undergoing surgical treatment and preoperative MRI was retrospectively collected and divided into good/poor outcome groups based on postoperative modified Japanese Orthopedic Association (mJOA) scores. The datasets obtained from several scanners (an independent scanner) for the training (testing) cohort were used for cross-validation (CV). Radiological models based on the intramedullary hyperintensity and compression ratio were constructed with 14 binary classifiers. Radiomic models based on 237 robust radiomic features were constructed with the same 14 binary classifiers in combination with 7 feature reduction methods, resulting in 98 models. The main outcome measures were the area under the receiver operating characteristic curve (AUROC) and accuracy.Results: Forty-one (11) radiomic models were superior to random guessing during CV (testing), with significant increased AUROC and/or accuracy (P AUROC < .05 and/or P accuracy < .05). One radiological model performed better than random guessing during CV (P accuracy < .05). In the testing cohort, the linear SVM preprocessor + SVM, the best radiomic model (AUROC: 0.74 ± 0.08, accuracy: 0.73 ± 0.07), overperformed the best radiological model (P AUROC = .048). Conclusion: Radiomic features can predict postoperative spinal cord function in CSMpatients. The linear SVM preprocessor + SVM has great application potential in building radiomic models.Meng-Ze Zhang and Han-Qiang Ou-Yang contributed equally to this work.

Cross-species application of the lumbar intervertebral disc radiomics model in humans and cynomolgus monkeys

“…Lambin et al 9 rst introduced the concept of radiomics, the quantitative extraction and analysis of highthroughput radiomics features (RFs) from medical images, which could provide more and better information than what physicians could obtain using traditional methods. By leveraging these highthroughput RFs, radiomics has shown great value in applications such as diseases diagnosis 10 , prediction of clinical treatment outcomes [11][12][13] , assessment of the pathological heterogeneity of whole tumor tissues 14,15 , and gene expression prediction 16 . Therefore, radiomics technology should be adopted to extract high-throughput RFs from IVD imaging data, and based on these high-throughput RFs could determine the degree of disc degeneration more precisely.…”