How AI Works in cvi42: Secure, Smart, and Fully Local

Local Processing for Complete Data Security

When cvi42 processes imaging data, everything takes place within the customer’s secure environment. All image data and derived results are managed locally, whether on a hospital workstation or through a customer-managed server installation. No data is ever transmitted outside the institution.

This architecture ensures compliance with strict hospital IT policies and data protection frameworks. For clinical users, this means AI-powered results without any compromise to data privacy or network security.

The Circle AI Engine: Trained, Validated, and Frozen

“Each of the AI models powering cvi42 is architected and developed within Circle’s controlled research and development environment. Circle’s data science and clinical AI research teams use diverse and representational datasets to train and validate each algorithm. The process typically involves supervised learning, where the AI learns to recognize patterns and structures such as the left ventricle, myocardium, or aortic root by comparing its results to expert-annotated data.

Once performance meets clinical and regulatory standards, the AI model is locked, “frozen” and encrypted during its integration within cvi42. This means the model’s behavior is fixed, it does not continue to learn or change once deployed at a customer site. The model you use in cvi42 is the validated version approved for clinical use, ensuring consistent and reproducible results across all installations.

No Learning from Customer Data

It is important to clarify: the AI in cvi42 does not learn from any data processed at the customer site. The algorithm applies its pre-trained parameters to each image set locally. It does not store patient data, send information externally, or modify its internal model based on what it sees or whether a user edits its outputs. Each analysis is isolated, ensuring the AI’s decisions remain consistent and the patient’s information stays protected within the facility’s network.

How the AI Analyzes Medical Images

At a technical level, cvi42’s AI is a deep learning-based image analysis engine trained to recognize and segment cardiac anatomy on MR and CT images. Primarily using convolutional neural networks, it performs pixel- or voxel-level classification to delineate key structures, including the endocardial and epicardial borders. These segmentations enable the measurements of clinically relevant metrics such as chamber volumes, ejection fraction, and myocardial mass.

This process mimics how expert readers would interpret the same dataset, but it happens in seconds and with objective consistency across cases.

Designed for Trust, Built for Performance

AI in cvi42 is designed to automate routine analysis while keeping clinicians fully in control. Users can review, adjust, and approve AI-generated contours as needed, ensuring that results always meet their clinical standards. Combined with local data processing, frozen AI models, and Circle’s rigorous training pipeline, this approach delivers accuracy and reliability without ever compromising patient privacy.

Artificial intelligence (AI) is transforming cardiovascular imaging, helping clinicians analyze complex data faster and with greater consistency. Circle Cardiovascular Imaging’s cvi42 integrates advanced AI models to automate tasks such as segmentation, measurement, and contouring across cardiac MR and CT scans. But just as important as what the AI does is how it works behind the scenes: where the data is processed, what happens to that data, and how the AI itself behaves in the clinical environment.

If You Can Read 10 Plaque Studies a Month, You Can Be Your Own Plaque Lab

By Jonathan Draper • August 13, 2026

Part 5 of 5 in Circle's Coronary Plaque series. Also read: Part 1 — How Advanced Plaque Analysis Changes the Clinic al Calculus Part 2 — Th e IT Infrastructure Behind CCTA Plaque Analysis Part 3 — The Financial Case for Coronary Plaque Services Part 4 — D elivering Plaque Analysis Without Disrupting Your Department You have watched the trajectory. Twelve months ago, the conversation about coronary plaque analysis was happening at conferences. Six months ago, it was happening in your referring cardiologists' offices. Now it is happening in your reading room — which lesions are vulnerable, what the total plaque burden is, whether coronary plaque tells a different story than the stenosis grade. That part is good news. Your patients are getting better assessments and the evidence base is catching up to the clinical intuition. On January 1, 2026, the financial case caught up too: the AMA retired the Category III plaque codes (0623T–0626T) and replaced them with a single Category I code, CPT 75577 , for AI-enabled coronary plaque assessment ( ACC Coding Corner ). Plaque analysis is no longer an emerging-technology line item. It is a national fee-schedule procedure. The harder question is operational: is your program set up to deliver it on its own — or to send the studies out and watch most of the reimbursement leave with them? For programs already running CCTA at any meaningful scale, becoming your own plaque lab is more accessible than most assume. It is a workflow choice, not a capital project.

Circle CVI Advances Cardiovascular Imaging Innovation with cvi42 v6.5

August 5, 2026

cvi42 v6.5 automates 4D Flow preprocessing, streamlines CT plaque and calcium workflows, and enhances reporting — from acquisition to insight, faster.

Four people in a modern office meeting around a desk with multiple computer monitors.

CCTA Plaque Analysis Is Now a Clinical Expectation. Here's How to Deliver It Without Breaking Your Department.

June 25, 2026

Part 4 of 5 in Circle's Coronary Plaque series. Also read: Part 1 — How Advanced Plaque Analysis Changes the Clinical Calculus Part 2 — The IT Infrastructure Behind CCTA Plaque Analysis Part 3 — The Financial Case for Coronary Plaque Services It's Monday morning review. Throughput is off target again. Two radiologists are working through a backlog of CCTA studies from Friday. Your most experienced cardiac CT tech just submitted a PTO request for a week in July that you can't cover without asking someone else to come in. And now cardiology has sent a note asking why the plaque analysis reports are taking so long. This scenario is not unique to your department. It is the operational reality facing most cardiac imaging programs as CCTA volume grows and clinical expectations evolve faster than workflows do. Coronary plaque analysis has moved from a research capability to a clinical standard — driven by updated ACC/AHA Chest Pain Guidelines , 10-year SCOT-HEART outcomes and the ongoing SCOT-HEART 2 trial , and a growing population of patients and referring physicians who know what to ask for. Meeting that expectation with a manual workflow built for a simpler era of CCTA reporting is not a sustainable operating model. The question is not whether to offer plaque analysis. The question is how to build the workflow to deliver it without adding to a backlog that's already under pressure.

Person in green examines a glowing green sphere beside a white control panel in a green-toned room.

Coronary Plaque Analysis Is a Reimbursable Service. Is Your Program Built to Capture It?

June 16, 2026

Part 3 of 5 in Circle's Coronary Plaque series. Also read: Part 1 — How Advanced Plaque Analysis Changes the Clinical Calculus Part 2 — The IT Infrastructure Behind CCTA Plaque Analysis The cardiology service line is under familiar financial pressure: rising volumes, tighter margins, growing competition from outpatient and independent imaging centers, and a capital environment that demands every major investment justify itself with a clear return. Against that backdrop, coronary plaque analysis has emerged as a meaningful financial opportunity — one with a growing reimbursement pathway, expanding referral demand, and the kind of clinical differentiation that drives patient retention. But the financial case only materializes if the program is set up to deliver the service efficiently and at scale. This is not an investment in a research capability. It is an investment in a billable, guideline-supported clinical service with a documented and growing payer footprint.