tsta

Home / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

2D Residual U-Net for Accurate Lumbar Vertebrae Segmentation in MRI-Based Low Back Pain Diagnosis using the SPIDER Dataset

Authors :

Armita Rahimi Borgi¹ Abdollah Zohrabi² Ali Kazemi³ Mostafa Abdolghaffar⁴ Ramin Kordi⁵ Parastoo Farnia⁶ Alireza Ahmadian⁷

1- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Research Center of Biomedical Technology and Robotics (RCBTR), Advanced Medical Technologies and Equipment Institute (AMTEI), Imam Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran 2- Department of Mathematics (Computer Science), Sharif University of Technology, Tehran, Iran 3- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Research Center of Biomedical Technology and Robotics (RCBTR), Advanced Medical Technologies and Equipment Institute (AMTEI), Imam Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran 4- Parseh Intelligent Surgical Systems Co., R&D Dept, Tehran, Iran 5- Department of Sports Medicine, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran 6- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Research Center for Intelligent Technologies in Medicine (RCITM), Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medical Sciences, Tehran, Iran 7- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Research Center of Biomedical Technology and Robotics (RCBTR), Advanced Medical Technologies and Equipment Institute (AMTEI), Imam Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran

Keywords :

Low Back Pain (LBP)،Magnetic Resonance Imaging (MRI)،Segmentation،Deep Learning،ResUNet

Abstract :

Low back pain (LBP) affects nearly 12% of the global population and remains a leading cause of disability. Precise visualization of lumbar vertebrae and intervertebral discs is critical for detecting pathological changes and guiding clinical interventions. Accurate segmentation of these structures is essential for reliable diagnosis and treatment planning. Compared to X-ray or CT scans, magnetic resonance imaging (MRI) provides superior soft-tissue contrast, making it the preferred modality for comprehensive spinal assessments. However, manual segmentation of vertebrae is labor-intensive and prone to inter-observer variability, while semi-automatic approaches are often time-consuming and lack robustness in accurately identifying vertebral anatomical structures, particularly when applied to low-quality or diverse clinical MRI data. In this study, we propose a 2D Residual U-Net (ResUNet) for vertebral segmentation on the SPIDER dataset. The pipeline includes reorientation, resolution standardization, and morphological mask refinement, along with a hybrid Dice–Binary Cross-Entropy loss to address class imbalance, particularly in non-vertebral structures. The proposed model achieved a Dice score of 0.945 and an IoU of 0.897, slightly surpassing a standard 2DU-Net with Dice = 0.940 and IoU=0.823. These results demonstrate that accurate 2D segmentation enables reliable 3D reconstruction, providing an efficient and clinically applicable solution for spinal analysis and LBP diagnosis.