TeraRecon
TeraRecon, a ConcertAI company, sells advanced visualization and AI workflow software for radiology and cardiology. TeraRecon AV (registered as Intuition outside the US) is vendor neutral 2D, 3D and 4D visualization, measurement and reporting across CT, MR and other modalities, with modules for cardiac, structural heart, perfusion and neuro work. The AI Framework, built on the Eureka Clinical AI platform, runs TeraRecon's own algorithms, third party algorithms and a site's in house models through one PACS integration. Physicians review and accept or reject AI results before they reach the report. TeraRecon's own AI devices include Aorta.CT, Cardiac.Chambers.MR and Cardiovascular.Calcification.CT, which segment anatomy and calcium on CT and MR.
TeraRecon says more than 2,000 hospitals use its software and publishes indications for use, IHE, DICOM and HL7 conformance statements. It announced ISO 27001:2022 certification in 2023. Headquarters are in Fremont, California. No price, performance figures for its own algorithms, or current list of third party partners are published. ConcertAI's real world evidence business is a separate product and not assessed here.
Capability Axes
An AI Health Index grade measures what a buyer can verify from public sources on the date shown. It is not a rating of how good the product is. A vendor can build an excellent system and grade low on an axis because it publishes nothing an outsider can check. How grades read
TeraRecon builds models as well as hosting them. Its regulatory page publishes indications for its own AI software devices: Aorta.CT segments the aorta and labels landmarks on CT angiography, and Cardiac.Chambers.MR segments the heart's chambers. Cardiovascular.Calcification.CT segments calcified coronary plaque. Each is a containerised medical device. The AI Framework runs TeraRecon's algorithms, third party algorithms and a site's own in house models through one integration.
The platform also carries value without the models. TeraRecon AV (Intuition) is advanced visualization software for 2D, 3D and 4D review, measurement and reporting across CT, MR and other modalities, and it works without AI. So the models are the engine of a core module, not the whole product.
The oversight structure is described. The AI Framework page says physicians control and review AI findings before committing them to the patient record or reporting system. The Eureka Clinical AI indication says users can accept or reject AI metadata, that the platform does not alter the original image, and that it is not intended to give a diagnosis or measurements used for decisions. Each of TeraRecon's own algorithms has an indication with exclusions; Aorta.CT, for example, excludes patients with aortic devices, dissection or rupture.
The missing part is the per algorithm view a site needs when it runs several models, including third party and in house ones, through one interface. Nothing published says what threshold each flags at or how differences between models are shown to the reader.
The software is described by function, not by model. The regulatory page gives indications for TeraRecon's algorithms (automatic 3D segmentation of the aorta, cardiac chambers and coronary calcium) and says they run as containerised medical devices returning DICOM results. The AI Framework describes running TeraRecon, third party and in house algorithms, comparing several on one study, and monitoring usage and performance.
Nothing is identified beyond that: no architecture, training data, version or update practice for TeraRecon's own models, and the current pages no longer name the third party algorithm partners.
The architecture is described and the other parties are not named. The AI Framework runs TeraRecon's own algorithms, third party algorithms and a site's in house models, and the Eureka indication describes routing images to hosted external systems for processing. The current pages do not name the third party algorithm vendors, the cloud host or any subprocessor.
A site running partner models is sending imaging to parties it cannot see from the published material.
The evidence published is scale and satisfaction, not performance. TeraRecon says more than 2,000 hospitals use its imaging software, reports over 20 years in advanced visualization and a five year customer net promoter score, and has been named a KLAS Category Leader for advanced visualization. Those describe adoption and customer views. The site publishes no performance figures for TeraRecon's own algorithms, no reader study and no outcome evidence.
General assurances only. The footer links a privacy policy and a Data Privacy Framework policy for EU to US transfers, and a RACI matrix for TeraRecon Cloud services, none of which sets out what happens to imaging. The Eureka indication says the platform sends images to hosted external systems for processing according to routing rules the user defines.
The company publishes nothing on how long studies are kept in the cloud, whether imaging routed to third party algorithms is retained by those vendors, or whether customer imaging trains TeraRecon's models. TeraRecon is part of ConcertAI, whose business supplies real world evidence to life sciences companies, and nothing says whether any imaging or derived data can reach the parent.
No HIPAA status or business associate agreement is stated on the company's site. The footer links a privacy policy and a Data Privacy Framework policy, which cover EU to US personal data transfers, and a RACI matrix dividing cloud service responsibilities between TeraRecon and the customer.
The routing design raises the contractual question. The Eureka platform sends images to hosted external systems, including third party algorithms, and nothing says whether one agreement with TeraRecon covers those partners or each needs its own.
TeraRecon announced in May 2023 that TeraRecon Inc. was certified to ISO 27001:2022, naming the standard and version for the operating company rather than the parent. Its regulatory page also links quality management system certificates.
No trust center or security page publishes the certificate, its scope or its current status, and the 2023 certificate is on a three year cycle, so nothing shows whether it is still current. No SOC 2 report is named. The cloud service's division of responsibilities is set out in a RACI matrix linked from the footer.
TeraRecon publishes indications for use for its regulated software on a Regulatory Resources page. They cover the Eureka Clinical AI platform (medical device software for viewing images and AI metadata, not for diagnosis), Intuition advanced visualization and its modules, and its own AI devices Aorta.CT, Cardiac.Chambers.MR and Cardiovascular.Calcification.CT. The footer says offerings depend on regulatory clearance that varies by country, and that TeraRecon AV is registered as Intuition in other markets.
The page does not list clearance numbers, and third party algorithms run through the AI Framework carry their own status, which the platform does not show.
Robustness is asserted with no groups or counts. TeraRecon's algorithm indications state that each model "is not specific to any gender, ethnic group or clinical condition", but no results by group are published. The AI Framework offers analytics on usage, performance and productivity so a site can assess algorithms before adopting them as standard of care, which is useful local tooling rather than a published evaluation.
No bias evaluation or governance framework is published, and nothing sets requirements for third party models admitted to the platform. TeraRecon is part of ConcertAI, a real world evidence company, and nothing published states where clinical imaging stops and data products begin.
A clinician can challenge each output. The AI Framework puts physician review and control of AI findings before anything is committed to the record or report, and the Eureka indication lets users accept or reject AI metadata. TeraRecon's algorithm outputs are DICOM files viewed alongside the unchanged original images.
Nothing stands behind the output: no error rate is published for TeraRecon's own algorithms, and no warranty, indemnity or remedy is described. For third party models, the answer depends on each partner.
Standards support is published in detail. TeraRecon's regulatory page links IHE integration statements, a DICOM conformance statement and an HL7 conformance statement for its connector. The AI Framework shares results with the site's reporting system by DICOM and HL7 and integrates with PACS once for many algorithms. The platform is vendor agnostic across scanners and PACS, and TeraRecon says more than 2,000 hospitals use it.
No record system or PACS product is named as a live integration, and no marketplace listing or bidirectional record integration is documented.
Two delivery models are implied, with location unstated. TeraRecon describes a cloud enabled imaging platform with centralized updates, and publishes a RACI matrix for its cloud SaaS services. Intuition is installed visualization software, and the Eureka indication describes sending images to hosted external systems for processing.
No cloud provider, region, residency commitment or tenant isolation is described, and where third party algorithms run is not stated.
No price is published. The site shows how the offer is structured: TeraRecon AV (Intuition) for advanced visualization, TR Neuro, DETECT and the AI Framework, sold through a demo request and delivered installed or as a cloud service with professional services for integration.
Coverage is named broadly. Advanced visualization spans CT, MR, PET, nuclear medicine, angiography, ultrasound and mammography, with modules for cardiac, structural heart, perfusion, tissue mapping and neuro work (TR Neuro for stroke perfusion). TeraRecon says more than 2,000 hospitals use its software worldwide.
Validation stands behind part of it. Each TeraRecon algorithm has a defined population, for example adult aortic CT angiography excluding dissection, rupture and devices, but no validation results are published. Third party models' coverage is theirs, and the partners are no longer named on the site.
Product updates
Material product, regulatory, evidence and commercial changes at TeraRecon, each verified against a live source and tagged to the capability axis it bears on. Funding rounds and awards are not product changes and are not logged.
TeraRecon released TeraRecon Neuro, a new software package designed to assist clinicians in diagnosing and treating neurovascular emergencies such as stroke. The application processes brain perfusion images from CT or MRI scanners to calculate perfusion parameters and generate 2D and 3D visualizations, including penumbra and umbra maps.
Alternatives to TeraRecon
Vendors in the same categories as TeraRecon whose graded profiles look most alike, with a line on what each product does.
Similar is not the same, so check that each one does the job you need. No vendor pays for placement.
Genius AI Detection is the breast imaging AI software line of Hologic, Inc. of Marlborough, Massachusetts; this record covers the software a breast imaging buyer licenses, not Hologic's…
Lithuanian radiology AI developer based in Vilnius, part of Sectra, the enterprise imaging company, since 2026.
Generative AI for radiology reporting and follow up.
DeepHealth is RadNet's digital health business and the entity that contracts RadNet's clinical AI and imaging informatics software to third party providers.
HOPPR builds infrastructure for making medical imaging AI and, separately, a layer that delivers AI results into radiology reporting.
Beijing based imaging AI company whose InferRead line detects findings on CT and radiographs (lung nodules on chest CT, chest abnormalities on radiographs, coronary stenosis on CTA…
Ordered by how closely the graded profiles match across the fifteen axes, inside the same categories. See how each axis is graded in the methodology.
Compared With
Each comparison carries a written verdict, the buyer conditions that favor each vendor, and a graded side by side. Pairs that cross a category boundary are grouped separately, and their verdicts state where the boundary sits rather than manufacturing a head to head.
Pricing
Vendor-published figures are labeled as such. Figures labeled “Estimated” are derived from third-party sources and have not been confirmed by the vendor.
| Entry Price | Pricing Basis | BAA Tier | Implementation | Source |
|---|---|---|---|---|
|
Not published
|
Not published; visualisation platform, AI Framework and TeraRecon algorithms sold through a sales conversation | Not published. Establish specifically whether one agreement with TeraRecon covers downstream third party algorithm providers or whether each partner requires its own, since the platform intermediates between the site and several model vendors. | Not disclosed. Professional services integrate the platform with the site's IT; the AI Framework integrates with PACS once for many algorithms, using DICOM and HL7. | Vendor Published |
No price is published. TeraRecon sells advanced visualisation (TeraRecon AV, registered as Intuition outside the US), TR Neuro, DETECT and the AI Framework, installed or as a cloud service, through a demo request. Ask what each component costs, whether third party algorithms are resold under TeraRecon's contract or bought from each partner, and whether charges are per study, per site or by subscription.