MRI grading of lumbar disc herniation based on AFFM-YOLOv8 system.
Authors
Affiliations (10)
Affiliations (10)
- The First College of Clinical Medical Science, China Three Gorges University, Yichang, China.
- Yichang Central People's Hospital, Yichang, Hubei, China.
- Third-grade Pharmacological Laboratory on Traditional Chinese Medicine, State Administration of Traditional Chinese Medicine, China Three Gorges University, Yichang, China.
- Hubei Provincial Clinical Research Center for Osteoporotic Fracture, Yichang, China.
- School of Biomedical Engineering, Sun Yat-sen University, Shenzhen, China.
- The First College of Clinical Medical Science, China Three Gorges University, Yichang, China. [email protected].
- Yichang Central People's Hospital, Yichang, Hubei, China. [email protected].
- Third-grade Pharmacological Laboratory on Traditional Chinese Medicine, State Administration of Traditional Chinese Medicine, China Three Gorges University, Yichang, China. [email protected].
- Hubei Provincial Clinical Research Center for Osteoporotic Fracture, Yichang, China. [email protected].
- Yichang Maternal and Child Health Care Hospital, Clinical Medical College of Women and Children, China Three Gorges University, Yichang, China. [email protected].
Abstract
Magnetic resonance imaging (MRI) serves as the clinical gold standard for diagnosing lumbar disc herniation (LDH). This multicenter study was to develop and clinically validate a deep learning (DL) model utilizing axial T2-weighted lumbar MRI sequences to automate LDH detection, following the Michigan State University (MSU) morphological classification criteria. A total of 8428 patients (100000 axial lumbar MRIs) with spinal surgeons annotating the datasets per MSU criteria, which classifies LDH into 11 subtypes based on morphology and neural compression severity, were analyzed. A DL architecture integrating adaptive multi-scale feature fusion titled as AFFM-YOLOv8 was developed. Model performance was validated against radiologists' annotations using accuracy, precision, recall, F1-score, and Cohen's κ (95% confidence intervals). The proposed model demonstrated superior diagnostic performance with a 91.01% F1-score (3.05% improvement over baseline) and 3% recall enhancement across all evaluation metrics. For surgical indication prediction, strong inter-rater agreement was achieved with senior surgeons (κ = 0.91, 95% CI 90.6-91.4) and residents (κ = 0.89, 95% CI 88.5-89.4), reaching consensus levels comparable to expert-to-expert agreement (senior surgeons: κ = 0.89; residents: κ = 0.87). This study establishes a DL framework for automated LDH diagnosis using large-scale axial MRI datasets. The model achieves clinician-level accuracy in MUS-compliant classification, addressing key limitations of prior binary classification systems. By providing granular spatial and morphological insights, this tool holds promise for standardizing LDH assessment and reducing diagnostic delays in resource-constrained settings.