VerteNet -- A Multi-Context Hybrid CNN Transformer for Accurate Vertebral Landmark Localization in Lateral Spine DXA Images

TL;DR

VerteNet is a novel deep learning model combining CNN and Transformer architectures to accurately locate vertebral landmarks in diverse, low-contrast lateral spine DXA images, aiding fracture assessment.

Contribution

This study introduces a dual-resolution self- and cross-attention model that improves landmark localization accuracy across multiple DXA scanner models.

Findings

Achieved a normalized mean error of 4.92 pixels, outperforming baseline methods.

Attained 100% accuracy in abdominal aorta crop detection during validation.

Enhanced inter-reader agreement with generated intervertebral guides.

Abstract

This aims to develop and validate a deep learning model that can accurately locate vertebral landmarks in lateral spine Dual energy X-ray Absorptiometry (DXA) scans. Accurate vertebral landmark localization is critical for reliable fracture assessment and scoring of abdominal aortic calcification using the Kauppila 24-point method; however, DXA lateral spine images are low-contrast, artifact-prone, and manufacturer-dependent, while manual annotation is time-consuming and reader-dependent. This study aimed to address these challenges by developing a dual-resolution self- and cross-attention model for robust vertebral landmark localization using lateral spine DXA scans from four different scanner models. Ground-truth vertebral corner landmarks (T12 to L5) were manually annotated, and performance was evaluated using normalized mean and median localization errors against baseline and state-of-the-art methods. The proposed framework achieved superior localization accuracy across all four DXA scanner models, with a normalized mean error of 4.92 pixels and a median error of 2.35 pixels, outperforming baseline methods. The abdominal aorta crop detection algorithm achieved 100% accuracy in validation and 96% accuracy (sensitivity 0.93, specificity 0.98) in an independent test set. Generated intervertebral guides further improved inter-reader agreement, reflected by higher Cohens weighted kappa and inter-reader correlation. The proposed deep learning framework enables accurate and robust vertebral landmark localization in lateral spine DXA images across heterogeneous imaging systems to support clinically relevant downstream analyses. The code for this work can be found at: https://github.com/zaidilyas89/VerteNet