A clinically validated 3D deep learning approach for quantifying vascular invasion in pancreatic cancer.
Source check: Source checked. Not independent scientific confirmation.
Finding / tested result: PAN-VIQ segmented pancreatic tumors and five vessels on CT and quantified three-dimensional vessel encasement. It was trained and internally validated on 2,130 cases, externally validated with accuracy above 90%, and prospectively tested in 202 patients; it outperformed junior radiologists and matched senior radiologists in reported accuracy and recall.
Technology: PAN-VIQ deep-learning framework for CT tumor/vessel segmentation and 3D vascular-involvement quantification.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- PAN-VIQ deep-learning framework for CT tumor/vessel segmentation and 3D vascular-involvement quantification.
- Limitation / still unknown
- The prospective cohort supports assessment performance, not improved surgical outcomes or patient benefit.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.nature.com/articles/s41746-025-02260-3
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.