Pioneering Precision in Lumbar Spine MRI Segmentation with Advanced Deep Learning and Data Enhancement
Preprint
- 30 September 2024
- preprint
- Published by Springer Nature in Research Square
Abstract
This study presents an advanced approach to lumbar spine segmentation using deep learning techniques, focusing on addressing key challenges such as class imbalance and data preprocessing. Magnetic resonance imaging (MRI) scans of patients with low back pain are meticulously preprocessed to accurately represent three critical classes: vertebrae, spinal canal, and intervertebral discs (IVDs). By rectifying class inconsistencies in the data preprocessing stage, the fidelity of the training data is ensured. The modified U-Net model incorporates innovative architectural enhancements, including an upsample block with leaky Rectified Linear Units (ReLU) and Glorot uniform initializer, to mitigate common issues such as the dying ReLU problem and improve stability during training. Introducing a custom combined loss function effectively tackles class imbalance, significantly improving segmentation accuracy. Evaluation using a comprehensive suite of metrics showcases the superior performance of this approach, outperforming existing methods and advancing the current techniques in lumbar spine segmentation. These findings hold significant advancements for enhanced lumbar spine MRI and segmentation diagnostic accuracy.Keywords
All Related Versions
This publication has 40 references indexed in Scilit:
- Lunar ground segmentation using a modified U-net neural networkMachine Vision and Applications, 2024
- A Comprehensive Review of Various Approach for Medical Image Segmentation and Disease PredictionWireless Personal Communications, 2023
- RAU-Net: U-Net network based on residual multi-scale fusion and attention skip layer for overall spine segmentationMachine Vision and Applications, 2022
- Radiologists with and without deep learning–based computer-aided diagnosis: comparison of performance and interobserver agreement for characterizing and diagnosing pulmonary nodules/massesEuropean Radiology, 2022
- A convenient and stable vertebrae instance segmentation method for transforaminal endoscopic surgery planningInternational Journal of Computer Assisted Radiology and Surgery, 2021
- Improving Weight Initialization of ReLU and Output Layers2019
- Comparative Study of Convolution Neural Network’s Relu and Leaky-Relu Activation Functions2019
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Review Article: MRI of the postoperative lumbar spineNeuroradiology, 2002