Predicting intervertebral disc degeneration using Pyradiomics features and XGBoost classification
Authors
Affiliations (1)
Affiliations (1)
- Medical College of Wisconsin
Abstract
BackgroundDisc degeneration is the primary cause of low back pain, although the disc itself is not usually the source of the pain. Instead, it can lead to various clinically significant conditions that cause pain. However, there are no objective measures of the disc degeneration. PurposeLack of objective measures of disc degeneration may sometimes cause uncertainties in treatment decisions. Currently disc degeneration is graded by visual assessment of MRI, which often leads to uncertainty and disagreements. Therefore, the objective of this study was to develop a simple, efficient, accurate, and objective diagnostic tool for assessing disc degeneration. Study typeProspective (data acquired on site) and retrospective (data from online repository). PopulationLumbar spine MRI data from 277 participants are used. 208 of those were from an online repository and 69 were from our site. Field strength/Sequence3.0T; T2 weighted 2D and 3D fast spin echo pulse sequences. AssessmentA fully automated method is implemented where selected radiomics features are calculated from T2 weighted MRI and used for classification of the disc degeneration grade. Binary disc masks are generated using nnU-Net and radiomics features are extracted using Pyradiomics. Optimal preprocessing approaches are explored to obtain reliable feature calculations from repeated scans. Several advanced decision tree classification methods were also tested. Statistical testsF1 accuracy score, Area Under the Curve, confidence interval. ResultsXGBoost was in good agreement with the rater and the important features used in classification were in accord with expected changes in discs. Data conclusionAutomated evaluation of disc degeneration streamlines the physicians workflow and reduces uncertainties. Using radiomics features enables explainability and provides simple and robust training for machine learning approaches. Level of evidence2 Technical Efficacy3