Normalized claim
Active locations: 10,000 locations increase
By late April 2026, that number had grown to over 10,000, a 43-times increase, with more than 9 million X-rays processed and weekly volumes averaging 1.5 million and growing.
Real-time dental image verification on Amazon SageMaker AI
Use case typeComputer vision inspectionUpdated Jul 10, 2026
Henry Schein One built Image Verify, an AI-powered quality verification system that evaluates dental X-ray quality at the point of capture. The system uses Amazon SageMaker AI and Amazon EKS to return an immediate quality score so clinicians can retake poor images while the patient is still present.
- Organization
- Henry Schein One
- Industry
- Healthcare
- Location
- United States
- Published
- July 2026
Reported outcomes
Active locations: More than 10,000 locations
Adoption & scale
X-rays processed: More than 11,000,000 x-raysWeekly x-ray volume: More than 1,500,000 x-rays per weekMedian latency: 1.4 secondsP90 latency: 2.2 seconds
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
X-rays processed: 11,000,000 x-rays increase
The system went from concept to over 10,000 active locations within months and has already processed over 11 million X-rays and growing at 1.5 million per week.
Normalized claim
Weekly x-ray volume: 1,500,000 x-rays per week increase
The system went from concept to over 10,000 active locations within months and has already processed over 11 million X-rays and growing at 1.5 million per week.
Normalized claim
Median latency: 1.4 seconds decrease
The entire round trip, from image capture to quality score displayed on screen, takes a median of 1.4 seconds with a P90 of 2.2 seconds.
Normalized claim
P90 latency: 2.2 seconds decrease
The entire round trip, from image capture to quality score displayed on screen, takes a median of 1.4 seconds with a P90 of 2.2 seconds.
Normalized claim
Gpu fleet reduction: 33% decrease
Meanwhile, the fleet consolidated from 15 instances down to 10, a 33 percent reduction in GPU infrastructure with improved response times.
Normalized claim
Location growth: 4,300% increase
Within weeks of launch, it was live in 250 practices. By late April 2026, that number had grown to over 10,000, a 43-times increase.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Henry Schein One
- Provider
- AWS
- Maturity
- Production
- Linked source
- AWS Machine Learning Blog
Deployed to over 10,000 active locations within months, up from 250 practices at launch
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 2 of 2
- 1Computer vision inspection
- 2Quality management
- Built Image Verify on Amazon SageMaker AI to perform real-time X-ray quality assessment at the point of capture.
- Used a multi-model inference pipeline to identify image type, evaluate sharpness, alignment, coverage, and completeness, and aggregate the results into a 1-to-5 quality score.
- Ran the application layer on Amazon Elastic Kubernetes Service and used SageMaker AI async inference, GPU optimization, and zero-downtime A/B deployments to improve scale and efficiency.
- Used AWS Cloud WAN for consistent multi-region deployment across the United States, Europe, Canada, and Asia Pacific.
- Deployed to over 10,000 active locations within months, up from 250 practices at launch.
- Processed over 11 million X-rays, growing at about 1.5 million per week.
- Achieved a median round-trip latency of 1.4 seconds and a P90 of 2.2 seconds.
- Reduced GPU infrastructure from 15 instances to 10, a 33% reduction, while improving response times.
- Enabled point-of-capture quality feedback that helps reduce callbacks, produce cleaner claims, and accelerate reimbursement.
Architecture
Henry Schein One runs Image Verify on Amazon SageMaker AI for inference and Amazon Elastic Kubernetes Service for application orchestration. Incoming dental X-rays are routed through a multi-model pipeline that first classifies image type, then evaluates quality dimensions with specialized models, and finally aggregates the results to a 1-to-5 score returned to the practice application. The stack uses SageMaker AI async inference, GPU instance optimization, zero-downtime A/B testing, and AWS Cloud WAN for multi-region deployment, with production rollback and scaling managed through AWS-native infrastructure.
Sources & evidence1
Evidence: Medium50/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Quantified outcome available
- Technical implementation details available
Type: Blog PostPublished: Jul 10, 2026Publisher: AWSEvidence: VendorConfidence: Medium
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
AI patterns
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.