Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.17855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917283810508800 |
|---|---|
| author | Cho, Seungik |
| author_facet | Cho, Seungik |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17855 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TopoGate: Quality-Aware Topology-Stabilized Gated Fusion for Longitudinal Low-Dose CT New-Lesion Prediction Cho, Seungik Image and Video Processing Computer Vision and Pattern Recognition Machine Learning 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. |
| title | TopoGate: Quality-Aware Topology-Stabilized Gated Fusion for Longitudinal Low-Dose CT New-Lesion Prediction |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2602.17855 |