Lumbar Disc Herniation Automatic Detection in Magnetic Resonance Imaging Based on Deep Learning

• Published in: Frontiers in bioengineering and biotechnology Vol. 9; p. 708137
• Main Authors: Tsai, Jen-Yung, Hung, Isabella Yu-Ju, Guo, Yue Leon, Jan, Yih-Kuen, Lin, Chih-Yang, Shih, Tiffany Ting-Fang, Chen, Bang-Bin, Lung, Chi-Wen
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 19.08.2021
• Subjects: Bioengineering and Biotechnology; data augmentation; low back pain; medical image; object detection; YOLO; YOLO; medical image; object detection; data augmentation; low back pain
• ISSN: 2296-4185; 2296-4185
• DOI: 10.3389/fbioe.2021.708137

Background: Lumbar disc herniation (LDH) is among the most common causes of lower back pain and sciatica. The causes of LDH have not been fully elucidated but most likely involve a complex combination of mechanical and biological processes. Magnetic resonance imaging (MRI) is a tool most frequently used for LDH because it can show abnormal soft tissue areas around the spine. Deep learning models may be trained to recognize images with high speed and accuracy to diagnose LDH. Although the deep learning model requires huge numbers of image datasets to train and establish the best model, this study processed enhanced medical image features for training the small-scale deep learning dataset. Methods: We propose automatic detection to assist the initial LDH exam for lower back pain. The subjects were between 20 and 65 years old with at least 6 months of work experience. The deep learning method employed the YOLOv3 model to train and detect small object changes such as LDH on MRI. The dataset images were processed and combined with labeling and annotation from the radiologist’s diagnosis record. Results: Our method proves the possibility of using deep learning with a small-scale dataset with limited medical images. The highest mean average precision (mAP) was 92.4% at 550 images with data augmentation (550-aug), and the YOLOv3 LDH training was 100% with the best average precision at 550-aug among all datasets. This study used data augmentation to prevent under- or overfitting in an object detection model that was trained with the small-scale dataset. Conclusions: The data augmentation technique plays a crucial role in YOLOv3 training and detection results. This method displays a high possibility for rapid initial tests and auto-detection for a limited clinical dataset.