Topology-Guided Biomechanical Profiling: A White-Box Framework for Opportunistic Screening of Spinal Instability on Routine CT
This work addresses the challenge of opportunistic screening for spinal instability in cancer patients, offering a significant improvement over manual methods but is incremental as it builds on existing SINS criteria with new geometric innovations.
The paper tackled the problem of automating spinal instability screening from routine CT scans, which is hindered by metastatic osteolysis causing topological ambiguity, and proposed a white-box framework called Topology-Guided Biomechanical Profiling (TGBP) that achieved 90.2% accuracy in stability triage and outperformed medical oncologists in a blinded study with kappa scores of 0.857 vs. 0.570 for complex features.
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.