Capsule endoscopy · Small-bowel evaluation
From thousands of frames to focused clinical review.
AI-assisted detection, differentiation and hemorrhagic-risk stratification of pleomorphic lesions in capsule endoscopy examinations.
CAPSULE / SMALL-BOWEL REVIEW AI REVIEW ACTIVE
VASCULARDETECTED
PROTRUDINGDETECTED
ULCERDETECTED
EROSIONDETECTED
BLOODDETECTED
NORMAL
01 · Intended use
AI assistance for acquired capsule endoscopy videos.
Deep Capsule® supports post-procedural review of small bowel capsule endoscopy examinations.
It detects and differentiates lesions, stratifies hemorrhagic potential and brings clinically relevant frames into focus for physician validation.
AI
The clinical challenge
Long examinations can conceal important findings.
Capsule endoscopy is minimally invasive, but prolonged reading times and the risk of missing clinically significant lesions can limit its diagnostic potential.
“The objective is not simply to read faster. It is to bring every relevant lesion into focus.”
02
How it works
One continuous path from video to validated finding.
Deep Capsule® supports the clinician across the complete review process while keeping final interpretation in expert hands.
Exam acquisition
A previously acquired capsule endoscopy video enters the review workflow.
Frame analysis
The AI examines the complete study and separates normal mucosa from relevant findings.
Lesion detection
Pleomorphic small bowel lesions are automatically located across the examination.
Differentiation
Findings are characterized and stratified by their hemorrhagic potential.
Focused review
Clinicians review prioritized frames and validate findings in their clinical context.
AI capabilities
Designed for comprehensive small bowel lesion review.
96.1%
Validated lesion-detection rate
Pleomorphic lesion detection
Identifies vascular and protruding lesions, ulcers, erosions, blood and other clinically relevant findings.
Lesion differentiation
Moves beyond detection to characterize multiple small bowel lesion types.
Bleeding-risk stratification
Supports automatic stratification of hemorrhagic potential using a validated scale.
Multi-device interoperability
Validated with full-length videos acquired from three different capsule endoscopy devices.
Rapid assisted review
Clinical validation reported a mean AI-assisted reading time of 203 seconds per examination.
03
Scientific validation
Prospectively validated in real clinical practice.
Real‑Life Clinical Validation of Artificial Intelligence‑Assisted Detection and Differentiation of Pleomorphic Lesions in Capsule Endoscopy
Mascarenhas Saraiva M, et al. · The American Journal of Gastroenterology
Read publication ↗Clinical benefits
More findings in focus. Less time lost to review.
01
Improved detection of clinically relevant small bowel lesions
↗02
Faster review of long capsule endoscopy examinations
↗03
Reduced risk of overlooking findings across thousands of frames
↗04
Consistent lesion characterization and hemorrhagic-risk stratification
↗Deep Capsule®
See deeper. Diagnose more. Treat better.
Talk to our team ↗Availability and regulatory status may vary by market. Contact DigestAID for current product and regulatory information.