Endoscopic ultrasound · Pancreatic cyst evaluation
See the cyst. Grade the risk.
AI-assisted identification and differentiation of pancreatic cystic lesions during live and previously acquired endoscopic ultrasound images.
PANCREATIC CYST · EUS LIVE AI
CYST SEGMENTED2 cm4 cm
AI DIFFERENTIATIONCYSTIC LESION
LOW-GRADE DYSPLASIA
HIGH-GRADE DYSPLASIA
01 · Intended use
AI assistance for pancreatic cystic lesions.
Smart Cyst® is a deep-learning technology developed to assist identification and differentiation of pancreatic cystic lesions during endoscopic ultrasound.
It analyzes live and previously acquired EUS images, supports sampling-target selection and generates standardized AI-driven diagnostic reports.
AI
The clinical challenge
Cyst appearance alone may not reveal its biological risk.
Pancreatic cystic lesions can share overlapping EUS characteristics. Distinguishing lower-risk from higher-risk dysplasia is essential for timely surveillance, sampling and treatment decisions.
“The critical step is transforming subtle cyst features into a consistent risk assessment.”
02
How it works
One continuous path from ultrasound to targeted sampling.
Smart Cyst® supports the EUS workflow while keeping sampling strategy and final interpretation in expert hands.
EUS acquisition
Live or previously acquired endoscopic ultrasound images enter the analysis workflow.
Cyst localization
The AI identifies a pancreatic cystic lesion and segments its visible boundaries.
Feature analysis
The cyst wall, internal structures and sonographic patterns are assessed across frames.
Dysplasia grading
The model supports differentiation between lower- and higher-risk cystic patterns.
Report and sampling
Bounding-box guidance and a standardized AI report support expert decision-making.
AI capabilities
Designed for focused pancreatic‑cyst assessment.
>95%
Diagnostic accuracy target for Smart Cyst®
Cystic-lesion identification
Automatically identifies pancreatic cystic lesions in endoscopic ultrasound images.
Dysplasia-grade differentiation
Analyzes cyst patterns to assist differentiation between lower- and higher-risk findings.
Real-time and retrospective analysis
Works during live EUS and with previously acquired examinations.
Sampling-target guidance
Places bounding boxes around relevant tissue to support precise sampling.
Standardized AI reporting
Generates a structured AI-driven diagnostic report for expert validation.
03
Scientific validation
Multicenter evidence for AI‑assisted dysplasia grading.
Artificial intelligence for pancreatic cyst dysplasia grading: a multicenter endoscopic ultrasound study
iGIE · 2026 · 51,046 EUS images from 5 centers
Read publication ↗Clinical benefits
Earlier clarity. Better‑targeted sampling.
01
Earlier and more accurate pancreatic cyst diagnosis
↗02
Fewer unnecessary procedures through more focused decision-making
↗03
Target selection for sampling with bounding-box guidance
↗04
Real-time and post-procedural EUS analysis in one workflow
↗05
Standardized AI-driven diagnostic reporting
↗Smart Cyst®
See the cyst. Grade with clarity.
Talk to our team ↗This technology is part of DigestAID's research and development pipeline. Availability and regulatory status may vary by market.