A Deep Learning Approach for Automatic Scoliosis Cobb Angle Identification
Renato R. Maaliw, Julie Ann B. Susa, Alvin Sarraga Alon, Ace C. Lagman, Shaneth C. Ambat, Manuel B. Garcia, Keno Piad, Ma. Corazon F. Raguro
Abstract
Efficient and reliable medical image analysis is indispensable in modern healthcare settings. The conventional approaches in diagnostics and evaluations from a mere picture are complex. It often leads to subjectivity due to experts' various experiences and expertise. Using convolutional neural networks, we proposed an end-to-end pipeline for automatic Cobb angle measurement to pinpoint scoliosis severity. Our results show that the Residual U-Net architecture provides vertebrae average segmentation accuracy of 92.95% based on Dice and Jaccard similarity coefficients. Furthermore, a comparative benchmark between physician's measurement and our machine-driven approach produces an acceptable mean deviation of 1.57 degrees and a T-test p-value of 0.9028, indicating no significant difference. This study has the potential to help doctors in prompt scoliosis magnitude assessments.