Deep learning-based classification of lumbar T2-weighted MRIs to subjects with and without low back pain symptoms

Background: Low back pain (LBP) is a prevalent condition, with most individuals experiencing it at some point. Magnetic resonance imaging (MRI) is the primary imaging modality for LBP diagnostics, enabling visualization of bones, intervertebral discs, and neural structures. While MRI can reveal degenerative changes associated with LBP, these findings are also observed in asymptomatic individuals, limiting its diagnostic specificity. Purpose: This study investigates the feasibility of deep learning for automated classification of lumbar spine MRIs into symptomatic and asymptomatic cases. The proposed method could assist in LBP diagnostics by either detecting LBP presence or ruling out negative cases, streamlining the diagnostic workflow. Study Design: A deep learning-based classification approach using a pre-trained ResNet50 convolutional neural network (CNN) was developed to distinguish between symptomatic and asymptomatic cases. Methods: Sagittal T2-weighted MRIs from the Northern Finland Birth Cohort 1966 dataset were used to train, validate, and test the ResNet50-based model for LBP classification. The impact of varying the number of sagittal slices per subject was also evaluated. Results: The best classification performance was achieved using a modified pre-trained ResNet50 network. The model attained a Balanced Accuracy of \((0.713 \pm 0.014)\), an Average Precision of \((0.494 \pm 0.013)\), and an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of \((0.724 \pm 0.004)\). Binary classification was more effective in predicting asymptomatic cases, while incorporating Pfirrmann grading improved symptomatic case predictions. Conclusions: Deep learning-based classification of lumbar spine MRIs can distinguish symptomatic and asymptomatic cases, with potential applications in LBP diagnostics.