TopoGate: Quality-Aware Topology-Stabilized Gated Fusion for Longitudinal Low-Dose CT New-Lesion Prediction

TL;DR

TopoGate is a novel, quality-aware model that stabilizes fusion of longitudinal low-dose CT images to improve new lesion prediction, effectively handling noise and registration variability.

Contribution

It introduces a learned gating mechanism based on image quality, registration, and topology to enhance lesion detection accuracy in longitudinal CT analysis.

Findings

Improves ROC AUC from 0.62 to 0.68 after quality filtering.

Reduces Brier score from 0.14 to 0.12 with quality-based filtering.

Gate adapts to image degradation, emphasizing appearance when noise increases.

Abstract

Longitudinal low-dose CT follow-ups vary in noise, reconstruction kernels, and registration quality. These differences destabilize subtraction images and can trigger false new lesion alarms. We present TopoGate, a lightweight model that combines the follow-up appearance view with the subtraction view and controls their influence through a learned, quality-aware gate. The gate is driven by three case-specific signals: CT appearance quality, registration consistency, and stability of anatomical topology measured with topological metrics. On the NLST--New-Lesion--LongCT cohort comprising 152 pairs from 122 patients, TopoGate improves discrimination and calibration over single-view baselines, achieving an area under the ROC curve of 0.65 with a standard deviation of 0.05 and a Brier score of 0.14. Removing corrupted or low-quality pairs, identified by the quality scores, further increases the area under the ROC curve from 0.62 to 0.68 and reduces the Brier score from 0.14 to 0.12. The gate responds predictably to degradation, placing more weight on appearance when noise grows, which mirrors radiologist practice. The approach is simple, interpretable, and practical for reliable longitudinal LDCT triage.