Scoliosis Detection using Deep Neural Network

TL;DR

This paper reviews deep learning methods for automatic scoliosis detection from X-ray images, aiming to improve accuracy and automate Cobb angle measurement, addressing limitations of manual diagnosis.

Contribution

It analyzes existing deep learning models for scoliosis detection and implements the most effective one for automated spinal curvature assessment.

Findings

Deep learning models significantly improve scoliosis detection accuracy.

Automated Cobb angle prediction reduces diagnosis time.

Deep learning approaches outperform traditional methods.

Abstract

Scoliosis is a sideways curvature of the spine that most often is diagnosed among young teenagers. It dramatically affects the quality of life, which can cause complications from heart and lung injuries in severe cases. The current gold standard to detect and estimate scoliosis is to manually examine the spinal anterior-posterior X-ray images. This process is time-consuming, observer-dependent, and has high inter-rater variability. Consequently, there has been increasing interest in automatic scoliosis estimation from spinal X-ray images, and the development of deep learning has shown amazing achievements in automatic spinal curvature estimation. The main target of this thesis is to review the fundamental concepts of deep learning, analyze how deep learning is applied to detect spinal curvature, explore the practical deep learning-based models that have been employed. It aims to improve the accuracy of scoliosis detection and implement the most successful one for automated Cobb angle prediction. Keywords: Scoliosis Detection, Spinal Curvature Estimation, Deep Learning. i