Topology-Guided Biomechanical Profiling: A White-Box Framework for Opportunistic Screening of Spinal Instability on Routine CT

TL;DR

This paper introduces TGBP, a transparent framework that automates spinal instability assessment on routine CT scans by leveraging geometric innovations, outperforming experts in complex feature evaluation and enabling effective opportunistic screening.

Contribution

TGBP is a novel white-box approach that decouples anatomical perception from structural reasoning, improving interpretability and accuracy in spinal instability screening on CT images.

Findings

Achieved 90.2% accuracy in stability triage on multi-center data.

Outperformed medical oncologists in complex structural feature assessment.

Significantly improved reliability in total score estimation.

Abstract

Routine oncologic computed tomography (CT) presents an ideal opportunity for screening spinal instability, yet prophylactic stabilization windows are frequently missed due to the complex geometric reasoning required by the Spinal Instability Neoplastic Score (SINS). Automating SINS is fundamentally hindered by metastatic osteolysis, which induces topological ambiguity that confounds standard segmentation and black-box AI. We propose Topology-Guided Biomechanical Profiling (TGBP), an auditable white-box framework decoupling anatomical perception from structural reasoning. TGBP anchors SINS assessment on two deterministic geometric innovations: (i) canal-referenced partitioning to resolve posterolateral boundary ambiguity, and (ii) context-aware morphometric normalization via covariance-based oriented bounding boxes (OBB) to quantify vertebral collapse. Integrated with auxiliary radiomic and large language model (LLM) modules, TGBP provides an end-to-end, interpretable SINS evaluation. Validated on a multi-center, multi-cancer cohort ($N=482$), TGBP achieved 90.2\% accuracy in 3-tier stability triage. In a blinded reader study ($N=30$), TGBP significantly outperformed medical oncologists on complex structural features ($\kappa=0.857$ vs.\ $0.570$) and prevented compounding errors in Total Score estimation ($\kappa=0.625$ vs.\ $0.207$), democratizing expert-level opportunistic screening.