VertXNet: An Ensemble Method for Vertebrae Segmentation and Identification of Spinal X-Ray

TL;DR

VertXNet is an ensemble pipeline combining U-Net and Mask R-CNN models with a rule-based approach to automatically segment and label vertebrae in spinal X-ray images, outperforming individual models and generalizing well across datasets.

Contribution

The paper introduces VertXNet, a novel ensemble method with a rule-based label inference system for improved vertebrae segmentation and labeling in spinal X-ray images.

Findings

VertXNet achieved a mean Dice score of 0.90 on test data.

It outperformed individual SOTA models U-Net and Mask R-CNN.

Demonstrated strong generalization across multiple datasets.

Abstract

Reliable vertebrae annotations are key to perform analysis of spinal X-ray images. However, obtaining annotation of vertebrae from those images is usually carried out manually due to its complexity (i.e. small structures with varying shape), making it a costly and tedious process. To accelerate this process, we proposed an ensemble pipeline, VertXNet, that combines two state-of-the-art (SOTA) segmentation models (respectively U-Net and Mask R-CNN) to automatically segment and label vertebrae in X-ray spinal images. Moreover, VertXNet introduces a rule-based approach that allows to robustly infer vertebrae labels (by locating the 'reference' vertebrae which are easier to segment than others) for a given spinal X-ray image. We evaluated the proposed pipeline on three spinal X-ray datasets (two internal and one publicly available), and compared against vertebrae annotated by radiologists. Our experimental results have shown that the proposed pipeline outperformed two SOTA segmentation models on our test dataset (MEASURE 1) with a mean Dice of 0.90, vs. a mean Dice of 0.73 for Mask R-CNN and 0.72 for U-Net. To further evaluate the generalization ability of VertXNet, the pre-trained pipeline was directly tested on two additional datasets (PREVENT and NHANES II) and consistent performance was observed with a mean Dice of 0.89 and 0.88, respectively. Overall, VertXNet demonstrated significantly improved performance for vertebra segmentation and labeling for spinal X-ray imaging, and evaluation on both in-house clinical trial data and publicly available data further proved its generalization.