What challenges did Henry Schein One face before AI implementation?

Up to 20% of dental insurance claims were initially denied, with missing or low-quality images among the leading causes. Quality assessment had traditionally been manual and happened hours or days after capture, causing callbacks, retakes, delays, and frustration. The solution needed sub-three-second feedback, support for tens of thousands of locations, and cost-efficient GPU inference.

What was the impact of the AI solution?

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.

Source

Real-time dental image verification on Amazon SageMaker AI

Use case typeComputer vision inspectionUpdated 3 days ago

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

−33%

gpu fleet reductionOther quantified impact

10,000 locationsactive locations11,000,000 x-raysx-rays processed1,500,000 x-rays per weekweekly x-ray volume1.4 secondsmedian latency2.2 secondsp90 latency

Strategic outcomes

Other strategic outcomeReduced callbacks and produced cleaner claimsOther strategic outcomeAvoided return visits for retakesScale & capacityValidated a path to 40,000 locations globally

Primary read

Use case focus

Showing 2 of 2

1Computer vision inspection
2Quality management

Up to 20% of dental insurance claims were initially denied, with missing or low-quality images among the leading causes.
Quality assessment had traditionally been manual and happened hours or days after capture, causing callbacks, retakes, delays, and frustration.
The solution needed sub-three-second feedback, support for tens of thousands of locations, and cost-efficient GPU inference.

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.

Technologies

Amazon SageMaker AI Amazon Elastic Kubernetes Service AWS Cloud WAN

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

Groundedness: 5/5Type: Blog PostPublished: Jul 10, 2026Publisher: AWSEvidence: VendorConfidence: Medium

Primary source

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Customer evidence