Lumbar Disc Herniation Detection and Classification in Sagittal, High-Resolution T2-Weighted MRI using Modified Attention U-NET

• Published in: Devices for Integrated Circuit pp. 325 - 330
• Main Authors: Chouhan, Aruna, Chauhan, Krishna, Mitharwal, Rajendra, Varma, Tarun
• Format: Conference Proceeding
• Language: English
• Published: IEEE 05.04.2025
• Subjects: Accuracy; Attention U-Net; Integrated circuit modeling; Lumbar disc herniation; Magnetic resonance imaging; MRI; Overfitting; Performance evaluation; Representation learning; Robustness; Stability analysis; Training; Visualization
• ISSN: 2996-3044
• DOI: 10.1109/DevIC63749.2025.11012422

Lumbar Disc Herniation (LDH) is a prevalent spinal disorder causing severe pain and neurological complications, requiring timely and precise diagnosis. Magnetic Resonance Imaging (MRI) provides detailed visualization of spinal abnormalities, yet manual analysis takes a lot of time and is subject to inter-observer variability. Existing deep learning approaches, such as U-Net, struggle with overfitting and unstable training, limiting their generalization. This study addresses these gaps by proposing a Modified Attention U-Net, integrating batch normalization (BN) after each convolutional layer to stabilize training and dropout (0.3) in the bottleneck layer to mitigate overfitting. Evaluated on T2-weighted sagittal MRI scans of 282 patients (1410 slices), the model achieves 87% classification accuracy, outperforming the baseline U-Net (80%). The validation accuracy curve demonstrates enhanced stability and robustness, unlike the fluctuating performance of the baseline U-Net. These advancements improve feature learning and model generalization, making the proposed method a promising automated tool for LDH detection.