AI and Deep Learning for Automated Segmentation and Quantitative Measurement of Spinal Structures in MRI
Praveen Shastry, Bhawana Sonawane, Kavya Mohan, Naveen Kumarasami, Raghotham Sripadraj, Anandakumar D, Keerthana R, Mounigasri M, Kaviya SP, Kishore Prasath Venkatesh, Bargava Subramanian, Kalyan Sivasailam
TL;DR
This work tackles the subjectivity and time cost of manual spinal MRI measurements by proposing an autonomous pipeline that combines nnU-Net-based segmentation of spinal discs, vertebrae, and canal with a 3D CNN-based measurement module for disc height and spinal canal diameter. Trained on a large, multi-manufacturer proprietary dataset, the system achieves high segmentation accuracy (Dice scores around $0.90$–$0.94$) and precise quantitative metrics (disc height and canal diameter with $MSE$ in the $1.3$–$1.8$ mm$^2$ range), enabling robust cross-region assessments. The approach emphasizes standardized preprocessing, region-focused annotations, and rigorous evaluation, demonstrating potential to reduce clinician workload and improve diagnostic consistency in spine care. Overall, the method provides a scalable, clinically applicable solution for automated MRI spine analysis with broad implications for degenerative spine evaluation and postoperative monitoring.
Abstract
Background: Accurate spinal structure measurement is crucial for assessing spine health and diagnosing conditions like spondylosis, disc herniation, and stenosis. Manual methods for measuring intervertebral disc height and spinal canal diameter are subjective and time-consuming. Automated solutions are needed to improve accuracy, efficiency, and reproducibility in clinical practice. Purpose: This study develops an autonomous AI system for segmenting and measuring key spinal structures in MRI scans, focusing on intervertebral disc height and spinal canal anteroposterior (AP) diameter in the cervical, lumbar, and thoracic regions. The goal is to reduce clinician workload, enhance diagnostic consistency, and improve assessments. Methods: The AI model leverages deep learning architectures, including UNet, nnU-Net, and CNNs. Trained on a large proprietary MRI dataset, it was validated against expert annotations. Performance was evaluated using Dice coefficients and segmentation accuracy. Results: The AI model achieved Dice coefficients of 0.94 for lumbar, 0.91 for cervical, and 0.90 for dorsal spine segmentation (D1-D12). It precisely measured spinal parameters like disc height and canal diameter, demonstrating robustness and clinical applicability. Conclusion: The AI system effectively automates MRI-based spinal measurements, improving accuracy and reducing clinician workload. Its consistent performance across spinal regions supports clinical decision-making, particularly in high-demand settings, enhancing spinal assessments and patient outcomes.