National multi-center validation: AUC 0.95
Scroll to watch the AUC curve draw — PANCREASaver® reaches 0.95 area under the curve detecting small <2cm tumors.
Figure source: Radiology 2023 (220152) Fig. 3 — nationwide multicenter validation (n=1,473) ｜Article ↗
Every number, sourced
Five international publications, nine awards, approvals in two markets — PANCREASaver® speaks in verifiable evidence.
International publications
5 peer-reviewed papers in Lancet Digital Health, Radiology and other top journals — real clinical validation led by National Taiwan University Hospital.
View 5 papersFDA Breakthrough Device
Breakthrough Device Designation from the U.S. FDA, recognizing technology that can significantly improve early detection of a life-threatening disease. FDA official program page ↗ Media coverage: FDA breakthrough designation ↗
TFDA clearance (Taiwan)
Device license No. 007946 — the first licensed pancreatic cancer AI-assisted detection device in Taiwan.
Intellectual Property Portfolio
10 invention patents across Taiwan (6) and the US (4), written at both system and method level, covering algorithms, imaging and clinical workflow.
View 10 patents9 national recognitions
From fundamental research to clinical care
Prof. Wang (NTU) and Prof. Liao (NTUH) launch early pancreatic cancer imaging AI research
NTU research team begins multi-center clinical validation
PanCAD.ai Co., Ltd. founded; technology licensed for commercialization
First Margulis Award for Taiwan at RSNA; SNQ, Taipei BioTech, National Innovation Awards
FDA Breakthrough designation; TFDA license No. 007946
Deployed at medical centers, regional hospitals and health centers; 2,000+ cases
Every step, published
Lancet Digital Health
Multi-center validation of AI for early pancreatic cancer detection
Radiology
Deep learning for pancreatic lesion detection on CT
Other international journals
5 papers total, covering algorithms, clinical validation and workflow
Four weeks, contract to go-live
A dedicated project manager throughout; radiologist and technologist training included.
Week 1 · Assessment
Review equipment (CT model, PACS version) and workflow; define report format and alert rules.
Week 2 · Integration
AI server setup and PACS/RIS interfacing; automatic DICOM routing; zero extra steps for radiology.
Week 3 · Validation & training
Validation on institutional data plus training for radiologists and technologists (online course included).
Week 4 · Go-live
Go-live, pilot run, performance dashboard delivered. Monthly quality reports thereafter.
What leading editors say about the science
Verbatim third-party statements on the peer-reviewed studies behind PANCREASaver®. Quotes are about the research — not the product — and each carries its original source.
“
…accurate detection of pancreatic cancer on CT scans, especially for tumors smaller than 2 cm. Early detection… greatly increases the chances of survival.
“
This deep learning–based tool had very good accuracy, and sensitivity approaching that of subspecialist radiologists… Tools such as this promise to benefit routine workflow and patient care.
“
These promising results show that CNN as a second reader can reduce misdiagnosis of pancreatic cancer and possibly lead to improved patient outcomes.