Cardiology · Cardiac MRI quantification
Cardio AI (Tempus Pixel Cardio)
Arterys (Tempus AI)
Arterys Cardio DL was the first cloud-and-deep-learning medical imaging application the FDA ever cleared, in January 2017, and the clearance line has stayed continuous through the Arterys MICA platform to the 2025 Tempus Pixel update that adds inline T1 and T2 maps. Independent validation found its automated left-ventricular ejection fraction tracked expert manual measurement closely. The honest limit is the evidence base: most published studies are manufacturer-affiliated and concentrated in one academic group, with genuinely independent validation of the commercial product still thin — which, against a broad regulatory footprint, places it at two marks.
Performance Metrics
Clinical Evidence
The most-cited clinical evidence for the commercial Arterys algorithm is a validation study of deep-learning cardiac ventricular volumetry (Radiology: Artificial Intelligence 2020) using the FDA-cleared Cardio DL 2.3 algorithm. Because the algorithm was not trained on data from the validating institution, the study is framed as an independent test of the commercial product; automated left-ventricular ejection fraction agreed closely with expert manual measurement (reported correlation around r=0.94 for LV EF in a cohort of roughly 200 patients), and the study emphasised the role of expert supervision — that is, clinician review and correction of the automated contours. The broader literature on the Arterys cardiac product is largely manufacturer-affiliated and concentrated in a single academic group, with additional work on automated plane prescription and deep-learning strain analysis. Genuinely independent, multi-centre validation of the commercial cardiac product remains comparatively thin, a limitation worth stating plainly: the device's regulatory footprint is broad and long-standing, but the published evidence base is narrower than the clearance history alone might suggest. Functionally the value proposition is consistent: the software automates the laborious parts of cardiac MRI quantification — chamber segmentation, volume and ejection-fraction computation, flow — and presents editable contours for clinician review. It is decision-support; the clinician supervises and corrects, and the measurements they sign out are the clinical record.
| Study | Design | n | Sensitivity | Specificity | AUC | Published |
|---|---|---|---|---|---|---|
| Cardiac ventricular volumetry validation (UCSD group; Arterys-affiliated) | RetrospectiveRetrospective | 200 | — | — | LV EF r≈0.94 vs expert manual | Radiology: Artificial Intelligence, 2020; independent test of Cardio DL 2.3 |
| Automated plane-prescription study (manufacturer-affiliated) | RetrospectiveRetrospective | 0 | — | — | — | Radiology: Artificial Intelligence, 2019 |
| Deep-learning strain analysis (manufacturer-affiliated) | RetrospectiveRetrospective | 0 | — | — | — | Radiology: Cardiothoracic Imaging, 2023; DLSS strain AUC 0.90 |
Clinical Pulse
Verified clinician sentiment
Verified clinician reviews launching · Apply to contribute →
Reviews are signed by clinicians verified against their regulator's public register.
Inside the Auris+ Listing
Six more sections complete this device’s Auris+ Listing.
Inside the algorithm
ProPro unlocks the five-stage editorial walkthrough of how this device's AI reaches a verdict — model architecture, training data, inference latency, and where the clinician stays in the loop.
Decision Ledger
ProPro unlocks a private, cross-vendor log of every case you read on this device — what the AI called, what you concluded, and a one-line reason if you overrode it. Ready for the EU AI Act's deployer logging obligations when they land in 2028.
Clinical Evidence Deep Dive
ProPro unlocks the structured clinical-evidence summary — study count, target patient population, and a tabular accuracy-metrics view drawn from peer-reviewed sources.
Peer-Reviewed Publications
ProPro unlocks the curated peer-reviewed publication list with PubMed cross-links — the citation backbone of every editorial verdict.
Post-Market & Regulatory Conditions
ProPro unlocks the post-market surveillance summary, recall record, and the conditions of approval that bound real-world use.
AI Algorithm Version History
ProPro unlocks the chronological record of algorithm version changes — what changed when, drawn from manufacturer changelogs and regulatory filings.
Regulatory Approvals
K252539
Class II
Safety Record
No Arterys recall or FDA safety communication was identified in publicly available sources as of June 2026; this is "none found in public reporting" rather than an exhaustive MAUDE audit, which could not be queried directly from this environment (a MAUDE search on "Arterys" returned no events on the last attempt before access was blocked). As an editable post-processing tool the software proposes measurements that the clinician reviews and corrects, which limits the harm surface relative to an autonomous reader; the principal documented risk is accepting an automated contour or measurement without adequate supervision, which the validation literature specifically frames as the clinician's responsibility.
Intended Use & Indications
Arterys Cardio AI (cleared as Arterys Cardio DL, evolving through the Arterys MICA platform to the current Tempus Pixel) is a Class II medical image management and processing system for the post-processing of cardiac MRI. It provides automated segmentation of the cardiac chambers and computes functional measurements — left- and right-ventricular volumes, ejection fraction and mass — from cine acquisitions, and supports 4D/2D flow, perfusion, delayed enhancement and, in the latest Tempus Pixel update, inline T1 and T2 parametric maps. The system was the first FDA-cleared medical imaging application to use cloud computing with deep learning. Its deep-learning contours are editable by design: the clinician reviews and adjusts the proposed segmentation, and final measurement and interpretation remain the clinician's responsibility.