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

2026-03-17

AI Summary

Metastatic osteolytic lesions often obscure spinal anatomical boundaries on CT, impeding accurate application of the Spinal Instability Neoplastic Score (SINS). This work proposes an interpretable white-box framework that addresses posterior-lateral boundary ambiguity through vertebral canal–referenced partitioning and achieves precise geometric modeling via covariance-guided bounding boxes. The approach further integrates radiomics with a large language model for end-to-end SINS assessment, incorporating a context-aware morphological normalization strategy to establish an auditable and interpretable automated evaluation system. Validated on a multicenter, multicancer cohort of 482 patients, the method achieved 90.2% accuracy in three-class stability triage. Blinded reader evaluations demonstrated its significant superiority over oncologists in assessing complex structural involvement (Kappa = 0.857) and estimating total SINS scores (Kappa = 0.625).

Technology Category

• Machine Learning: Evaluation and Analysis
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

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 ($κ=0.857$ vs.\ $0.570$) and prevented compounding errors in Total Score estimation ($κ=0.625$ vs.\ $0.207$), democratizing expert-level opportunistic screening.

Problem

• spinal instability
• SINS
• topological ambiguity
• opportunistic screening
• metastatic osteolysis

Innovation

• Topology-Guided Biomechanical Profiling
• Spinal Instability Neoplastic Score
• oriented bounding box
• white-box framework
• vertebral collapse quantification