B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation

TL;DR

B-Spine introduces a deep learning pipeline that uses B-spline curves for robust and interpretable spinal curvature estimation from low-quality X-ray images, reducing reliance on expensive annotations.

Contribution

The paper proposes a novel B-spline based deep learning method with a SegRefine network and hybrid Cobb angle estimation, improving robustness and interpretability over existing approaches.

Findings

Outperforms state-of-the-art methods on public and new challenging datasets.

Achieves robust spinal curvature estimation from low-quality images.

Provides interpretable B-spline curve representations of the spine.

Abstract

Spinal curvature estimation is important to the diagnosis and treatment of the scoliosis. Existing methods face several issues such as the need of expensive annotations on the vertebral landmarks and being sensitive to the image quality. It is challenging to achieve robust estimation and obtain interpretable results, especially for low-quality images which are blurry and hazy. In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images. Given a low-quality input, a novel SegRefine network which employs the unpaired image-to-image translation is proposed to generate a high quality spine mask from the initial segmentation result. Next, a novel mask-based B-spline prediction model is proposed to predict the B-spline curve for the spine centerline. Finally, the Cobb angles are estimated by a hybrid approach which combines the curve slope analysis and a curve-based regression model. We conduct quantitative and qualitative comparisons with the representative and SOTA learning-based methods on the public AASCE2019 dataset and our new proposed CJUH-JLU dataset which contains more challenging low-quality images. The superior performance on both datasets shows our method can achieve both robustness and interpretability for spinal curvature estimation.