Radiology AI Directory

FDA-cleared profile

MAGNETOM Vida; MAGNETOM Lumina; MAGNETOM Aera; MAGNETOM Skyra; MAGNETOM Prisma; MAGNETOM Prisma fit

Siemens Medical Solutions USA, Inc.

MAGNETOM Aera, Skyra, Prisma, Prisma fit, Vida, and Lumina with syngo MR XA60A are 1.5T and 3T magnetic resonance diagnostic systems that produce cross-sectional images, spectroscopic images or spectra, and derived physical parameters of the head, body, or extremities for trained-physician interpretation. K231560 adds or migrates model-specific hardware and software, including Deep Resolve Boost HASTE and Deep Resolve Boost EPI Diffusion on Vida and Lumina.

MRI workflow
Evidence status: each field shows source quality, applicability, and review date. Research pending, information not established in reviewed sources, and vendor documentation pending are distinct outcomes.

Clinical fit

What this tool is for

Start with the authorized purpose, then verify how it fits your service line and reading workflow.

Exact purpose
MAGNETOM Aera, Skyra, Prisma, Prisma fit, Vida, and Lumina with syngo MR XA60A are 1.5T and 3T magnetic resonance diagnostic systems that produce cross-sectional images, spectroscopic images or spectra, and derived physical parameters of the head, body, or extremities for trained-physician interpretation. K231560 adds or migrates model-specific hardware and software, including Deep Resolve Boost HASTE and Deep Resolve Boost EPI Diffusion on Vida and Lumina.
FDA source Exact FDA submission Checked 2026-09-02
Intended users
Healthcare professionals familiar with and responsible for magnetic resonance image acquisition and post-processing operate the systems; trained physicians interpret the images, spectra, and derived physical parameters. The AI reconstruction features support image production and do not autonomously diagnose a patient.
FDA source Exact FDA submission Checked 2026-09-02
Care setting and population
Professional MRI facilities with the MR safety, siting, patient screening, contrast governance, protocol management, image interpretation, service, and quality-assurance controls required for 1.5T or 3T diagnostic systems. MAGNETOM Aera may also be configured as Aera Mobile, and the systems may support imaging during compatible interventional procedures.
FDA source Exact FDA submission Checked 2026-09-02
Workflow role
The systems acquire and reconstruct MRI examinations within the scanner workflow. Deep Resolve Boost uses deep-learning reconstruction to denoise and sharpen accelerated HASTE or EPI diffusion acquisitions on the supported Vida and Lumina configurations; other XA60A functions vary by model and include new or modified pulse sequences, physiologic logging, Open Recon, MR Fingerprinting, beat sensing, and myExam angiography assistance.
FDA source Exact FDA submission Checked 2026-09-02
Required input
Raw MRI acquisition data, patient and examination demographics, user-selected protocols and pulse-sequence parameters, coil and patient setup, optional physiologic signals, and contrast-agent information when applicable. Deep Resolve inputs are undersampled or lower-signal MRI data from supported HASTE, TSE, or EPI diffusion workflows.
FDA source Exact FDA submission Checked 2026-09-02
Output and human action
Transverse, sagittal, coronal, or oblique cross-sectional images; spectroscopic images or spectra; and derived physical parameters for trained-physician interpretation. Supported Deep Resolve workflows output denoised and sharpened reconstructed images, while Open Recon and research reconstruction outputs require configuration-specific review before clinical use.
FDA source Exact FDA submission Checked 2026-09-02
Limitations
Features are model- and license-specific: the K231560 summary lists Deep Resolve Boost HASTE and EPI Diffusion for Vida and Lumina, not for every named system. FDA did not require a new clinical trial for substantial equivalence, did not report demographic attributes for the AI datasets, and did not define clinical subgroups. Product-family studies are single-center, include Siemens-affiliated authors, and show that accelerated reconstruction can change ADC values or produce a minority of images rated worse, so each protocol and quantitative use requires local validation.
Public source Product family Checked 2026-09-02

Regulatory identity

FDA record and catalog context

The FDA listing establishes the regulatory identity. It does not by itself establish local workflow fit, pricing, security, or performance in your environment.

FDA submission
K231560
FDA source Exact FDA submission Checked 2026-08-31
Modality
MRI
FDA source Exact FDA submission Checked 2026-09-02
Anatomy
Multi-region
FDA source Exact FDA submission Checked 2026-09-02
Clearance type
510(k)
FDA source Exact FDA submission Checked 2026-08-31
Decision date
2023-10-23
FDA source Exact FDA submission Checked 2026-08-31
FDA status
FDA-cleared
FDA source Exact FDA submission Checked 2026-08-31

Implementation

Questions for IT, informatics, and operations

Use these fields to structure a vendor demo, security review, and implementation estimate.

Integration
K231560 identifies DICOM PS 3.1 through PS 3.20 (2021e) as a conformance standard. Siemens publishes syngo MR XA60A DICOM conformance statements for the relevant 1.5T and 3T MAGNETOM systems, and the XA60 operator manual covers patient and study management, DICOM node configuration, encrypted DICOM connections, imports, exports, archiving, and interoperability versus enhanced-image export profiles.
Public source Exact product version Checked 2026-09-02

Use the conformance statement for the installed model and build, then test worklist, patient reconciliation, series and derived-image metadata, enhanced versus interoperability export, routing, archive, storage commitment, failure recovery, and downstream quantitative behavior end to end.

Deployment and data flow
On-premises 1.5T or 3T MRI systems running syngo MR XA60A, with modified host computers on all named models and model-specific changes to the measurement and reconstruction system, coils, beat sensor, or image-calculation hardware. Deployment may be fixed-site or an Aera Mobile configuration. Vida product-family planning data list a 70 cm bore, 7.35-ton operating weight, and a 31 square meter minimum room, but those figures must not be transferred to the other models.
Public source Product family Checked 2026-09-02

Require a model- and serial-number-specific site plan covering shielding, structural load, power, cooling, quench venting, emergency routes, network, coils, licenses, acceptance testing, downtime, service access, and mobile-operation controls where applicable.

Security and privacy
The syngo MR XA60 administration manual documents role-based authorization, explicit authentication controls, certificate-based encrypted DICOM connections, HTTPS options, patient-data minimization for export, audited remote Expert-i sessions, local audit records, and optional encrypted forwarding to an external Syslog server. It warns against exposing HTTP or HTTPS ports directly to the Internet and notes that the syngo audit trail does not capture actions performed in Windows or third-party software.
Public source Exact product version Checked 2026-09-02

Confirm which controls are enabled on the installed system, obtain the current security white paper and component inventory, restrict privileged roles, validate certificates and remote access, forward and retain audit records, document patch governance, and assess operating-system and third-party logging gaps.

Training and support
The XA60 operator manual requires personnel to have the necessary expertise and read the complete operator manual before use. Siemens Academy lists model-specific Vida and Lumina XA60 upgrade training and MR Deep Resolve content, while the US MRI education portfolio offers protocol preparation, onsite education, classroom and virtual training, and protocol-building workshops for technologists.
Public source Product family Checked 2026-09-02

Document role-based competency for operators, radiologists, physicists, MR safety personnel, clinical administrators, IT administrators, and service staff, including Deep Resolve artifact recognition, quantitative-measurement effects, fallback, recall actions, and post-upgrade revalidation.

Monitoring and change control
syngo MR XA60 provides a Message Viewer for component, timestamp, severity, and message details; SaveLog collection; a configurable audit trail for patient-data access, network transfer, logon, security changes, software updates, service sessions, and DICOM-node changes; local audit storage; status monitoring; and optional secure Syslog forwarding. The manual documents local audit-log size thresholds and automatic deletion, making external retention and alerting operational requirements.
Public source Exact product version Checked 2026-09-02

Monitor system and reconstruction errors, DICOM failures, protocol and software changes, Deep Resolve settings, image-quality complaints, quantitative drift, repeats and aborted scans, acquisition and room time, downtime, audit forwarding, storage thresholds, service actions, and completion of open recall corrections by model and serial number.

Model and feature configuration matrix

K231560 covers six scanner families with syngo MR XA60A, but hardware and software changes differ by model. Deep Resolve Boost HASTE and EPI Diffusion are listed for Vida and Lumina, while GRE_PC, physiologic logging, Open Recon, MR Fingerprinting, beat sensing, myExam angiography assistance, and the Aera Flex Loop Large coil have different model coverage.

exact submission · checked 2026-09-02

Tie every clinical, interoperability, security, and service claim to scanner model, serial number, field strength, XA60A build, hardware revision, coil, and licensed option before contracting or validation.

Source

Deep Resolve protocol validation

The FDA summary and clinical literature support denoising, sharpening, and faster supported acquisitions, but the literature also reports ADC shifts and some worse-rated image pairs.

product family · checked 2026-09-02

Validate each anatomy, sequence, acceleration, coil, contrast condition, field strength, pathology mix, artifact pattern, lesion task, and quantitative measurement with radiologist and physicist approval.

SourceSourceSourceSource

DICOM and data export controls

Siemens provides XA60A conformance statements for the relevant 1.5T and 3T systems. The operator manual distinguishes interoperability and enhanced export profiles and provides data-minimization options for removable-media export.

exact product version · checked 2026-09-02

Test local RIS, worklist, PACS, VNA, viewers, quantitative tools, routing, archive, and recovery using both routine and derived images. Confirm whether older destinations preserve enhanced MR content.

SourceSourceSource

Security and audit operations

XA60 documents role controls, authentication, DICOM encryption, HTTPS, remote-session auditing, local audit records, and secure Syslog forwarding, together with known Windows and third-party audit gaps.

exact product version · checked 2026-09-02

Test the installed configuration against hospital identity, certificate, segmentation, remote-access, SIEM, time-synchronization, vulnerability, patch, backup, retention, and incident-response requirements.

Source

Throughput measurement

Product-family studies report material sequence-level time savings, but they do not establish room-time, daily-capacity, staffing, or financial gains for a new site.

product family · checked 2026-09-02

Measure acquisition time and total room time separately by examination type, including setup, coils, contrast, repeats, reconstruction latency, turnover, staffing, demand, and whether saved minutes produce additional completed examinations.

SourceSourceSource

Training and change control

Public Siemens resources include XA60 upgrade, model-specific, Deep Resolve, onsite, virtual, and protocol-building education options.

product family · checked 2026-09-02

Include training scope, protected education time, competency records, protocol ownership, post-upgrade regression testing, user acceptance, and refresher support in the implementation plan and contract.

SourceSource

Evidence

Performance evidence

Metrics are shown only when they are tied to a source, endpoint, population, and tested product version.

Evidence summary
K231560 provides unusually detailed exact-submission AI dataset provenance but no new clinical trial, demographic breakdown, subgroup analysis, or public diagnostic-accuracy endpoint. The cited and later product-family studies support protocol-specific image-quality and acquisition-time benefits while also showing ADC shifts and a minority of worse-rated images. These findings support local protocol evaluation, not a blanket claim across six models, every anatomy, or every quantitative workflow.
Public source Product family Checked 2026-09-02
Reported sensitivity
Research pending
Needs research Exact FDA submission Checked 2026-08-31

This field has not been curated yet.

Reported specificity
Research pending
Needs research Exact FDA submission Checked 2026-08-31

This field has not been curated yet.

Deep Resolve Boost EPI Diffusion training and validation data

1000000 slices, more than

Disclosed training and validation dataset scale in MRI data spanning body parts, contrasts, fat-suppression techniques, orientations, and 1.5T and 3T field strengths; demographics were not recorded.

Tested version: Deep Resolve Boost EPI Diffusion in K231560
Source

Abdominal diffusion acquisition-time reduction

39.5 % reduction calculated from reported means

Mean DL DWI acquisition time of 216.87 seconds versus 358.69 seconds for conventional DWI in 74 consecutive patients undergoing 3T abdominal MRI.

Tested version: Deep-learning EPI diffusion reconstruction on a Siemens 3T system; exact commercial software build not reported in the abstract
Source

Single-breath-hold deep-learning HASTE acquisition time

16 seconds

Acquisition time versus 90 seconds for conventional multiple-breath-hold HASTE and 240 seconds for respiratory-triggered BLADE in 66 patients undergoing 1.5T liver MRI.

Tested version: Deep-learning HASTE research implementation on a Siemens 1.5T system; exact commercial software build not reported in the abstract
Source

Knee DL-TSE maximum scan-time reduction

52 % faster, up to

Accelerated research DL-TSE versus conventional TSE, with at least 45% higher image resolution in 232 paired conventional and deep-learning knee TSE image sets acquired on a 3T MAGNETOM Vida.

Tested version: Research DL-TSE sequence on MAGNETOM Vida 3T; not identified as the exact K231560 commercial build
Source

K231560 nonclinical verification, image-quality assessment, and AI training and validation summary

Manufacturer software verification and validation, sample clinical-image review, comparison imaging, physiologic-logging verification, coil bench testing, and AI dataset characterization · 1.5T and 3T MRI data spanning multiple body regions, contrasts, fat-suppression techniques, and orientations; demographics were not recorded and clinical subgroups were not defined

exact submission · Tested version: MAGNETOM Aera, Skyra, Prisma, Prisma fit, Vida, and Lumina with syngo MR XA60A · Sponsor or vendor study

K231560

FDA reports that the verification and validation supported substantial equivalence. No new clinical test was conducted; sample clinical images and publications were supplied, and public diagnostic-accuracy, subgroup, site, reader, and patient-outcome results are not reported.

Source

Clinical feasibility of accelerated diffusion weighted imaging of the abdomen with deep learning reconstruction

Retrospective single-center intraindividual comparison of conventional and deep-learning reconstructed abdominal DWI, with two-radiologist qualitative review and ADC measurements · 74 consecutive patients undergoing 3T abdominal MRI

product family · Tested version: Deep-learning EPI diffusion reconstruction on a Siemens 3T system; exact commercial software build not reported in the abstract · n=74 · 1 site · Sponsor or vendor study

PMID 35797791

Three authors were affiliated with Siemens. DL DWI was faster and scored higher for qualitative image quality, but liver and focal-lesion ADC values were lower than with conventional DWI, requiring local quantitative validation.

Source

Diagnostic Confidence and Feasibility of a Deep Learning Accelerated HASTE Sequence of the Abdomen in a Single Breath-Hold

Retrospective single-center comparison of deep-learning single-breath-hold HASTE, conventional multiple-breath-hold HASTE, and respiratory-triggered BLADE with two-reader qualitative assessment · 66 patients undergoing 1.5T liver MRI

product family · Tested version: Deep-learning HASTE research implementation on a Siemens 1.5T system; exact commercial software build not reported in the abstract · n=66 · 1 site · Sponsor or vendor study

PMID 33208596

Two authors were affiliated with Siemens. The 16-second sequence was successfully acquired in all patients, with diagnostic confidence and lesion assessment similar to BLADE but overall image quality statistically inferior to BLADE.

Source

Evaluation of deep-learning TSE images in clinical musculoskeletal imaging

Prospective clinical comparison of one repeated research DL-TSE knee sequence per consenting patient against the corresponding conventional clinical TSE sequence, with blinded reporting-radiologist preference assessment · 232 paired knee TSE image sets acquired on one 3T MAGNETOM Vida

product family · Tested version: Research DL-TSE sequence on MAGNETOM Vida 3T; not identified as the exact K231560 commercial build · n=232 · 1 site · Sponsor or vendor study

PMID 38837669

The image-pair count is used because the abstract does not separately state the unique-participant count. Siemens affiliations were present. Smaller structures were rated worse in 21 of 232 pairs, and the study did not use an independent diagnostic reference standard.

Source

Economics and lifecycle

Budget and ongoing governance

These are common procurement questions; unknown values remain visible until a source supports them.

Pricing and total cost
No public list price for a K231560 MAGNETOM system, XA60A upgrade, or Deep Resolve license was stated on the Siemens product and education pages reviewed. Procurement should obtain a configuration-specific capital and lifecycle quote that separates scanner or upgrade price, coils and options, construction and siting, applications and service training, service coverage, cybersecurity support, software upgrades, and downtime commitments.
Public source Product family Checked 2026-09-02
Reimbursement and coding
CMS NCD 220.2 addresses coverage of medically necessary MRI and MRA services performed on FDA-authorized equipment within its labeling; it does not establish separate payment for a MAGNETOM scanner, syngo MR XA60A, or Deep Resolve. Coverage, coding, payment, and prior authorization remain examination-, payer-, site-, and patient-specific.
Public source Not applicable Checked 2026-09-02

No product-specific code

No separate named-product payment identified in CMS NCD 220.2

Medicare · United States

The NCD provides MRI and MRA coverage context and does not assign payment to XA60A or Deep Resolve. Verify the ordered examination, medical necessity, current code set, site of service, payer contract, and local coverage rules.

Source

Safety and lifecycle

Postmarket record

Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.

Postmarket safety review
FDA recall Z-2658-2025 includes MAGNETOM Lumina model 11344916 because ice may block the magnet venting system. A quench could then produce pressure buildup, rupture the helium containment system, and leak helium into the scan room. FDA lists the recall as open and classified. FDA recall Z-2659-2025 includes MAGNETOM Prisma model 10849582 because ice may block the magnet venting system. A quench could then produce pressure buildup, rupture the helium containment system, and leak helium into the scan room. FDA lists the recall as open and classified. FDA recall Z-2660-2025 includes MAGNETOM Skyra model 10432915 because ice may block the magnet venting system. A quench could then produce pressure buildup, rupture the helium containment system, and leak helium into the scan room. FDA lists the recall as open and classified. FDA recall Z-2667-2025 includes MAGNETOM Vida model 11060815 because ice may block the magnet venting system. A quench could then produce pressure buildup, rupture the helium containment system, and leak helium into the scan room. FDA lists the recall as open and classified.
FDA source Exact FDA submission Checked 2026-09-04

Each published event was manually matched to the exact FDA submission and affected product or version; a recall does not establish an AI-algorithm defect or current site exposure unless the event states that scope.

recall: Z-2658-2025

Open, Classified

2025-09-30

Native K231560 and exact Lumina model match. This is a magnet, quench-venting, and facility-safety issue, not a Deep Resolve defect; verify serial-number scope, inspection or correction status, emergency routes, and the current Siemens safety notice.

Source

recall: Z-2659-2025

Open, Classified

2025-09-30

Native K231560 and exact Prisma model match. This is a magnet, quench-venting, and facility-safety issue, not a Deep Resolve defect; verify serial-number scope, inspection or correction status, emergency routes, and the current Siemens safety notice.

Source

recall: Z-2660-2025

Open, Classified

2025-09-30

Native K231560 and exact Skyra model match. This is a magnet, quench-venting, and facility-safety issue, not a Deep Resolve defect; verify serial-number scope, inspection or correction status, emergency routes, and the current Siemens safety notice.

Source

recall: Z-2667-2025

Open, Classified

2025-09-30

Native K231560 and exact Vida model match. This is a magnet, quench-venting, and facility-safety issue, not a Deep Resolve defect; verify serial-number scope, inspection or correction status, emergency routes, and the current Siemens safety notice. The four reviewed K231560 records do not identify Aera or Prisma fit.

Source

Buyer worksheet

Open questions to take to the vendor

Open evaluation checklist

Research record

What has been checked

This audit distinguishes completed source review from fields that have not yet been researched.

Human reviewedStatus
2026-09-04Last searched
22Fields reviewed
13Source classes checked
20Unreviewed PubMed leads
10Unreviewed trial leads
0Unreviewed FDA recall leads

Recovered from the prior exact-submission extraction and normalized under the current provenance rules. The exact FDA summary, XA60 administration manual, Siemens XA60A DICOM indexes, product and education pages, CMS MRI coverage policy, PubMed and ClinicalTrials.gov candidates, three clinically relevant product-family studies, and all four exact-identifier FDA recall candidates were manually reviewed. The dossier separates the six-model XA60A clearance from model-specific Deep Resolve availability and marks the clinical studies as single-center product-family evidence with Siemens affiliations. Automated exact-name discovery found 20 PubMed and 10 ClinicalTrials.gov candidate records. Candidates require human product and version matching; zero candidates is not evidence that no studies exist. 4 FDA recall candidates were manually reviewed: 4 published and 0 rejected as a neighboring or otherwise inapplicable version. Native FDA recall identifiers produced 4 postmarket candidate records; 4 have been reviewed (4 published, 0 rejected) and 0 remain unreviewed.

Candidate leads remain unpublished until a human confirms the exact product and tested version.

Source classes: fda ai list, fda decision summary, peer reviewed publication, trial registry, vendor product page, vendor operator manual, vendor interoperability, vendor training, reimbursement policy, fda device recall, pubmed, clinical trials, openfda device recall

Sources

Source ledger

Sources accessed through 2026-09-04.

Alternatives

Related tools to compare

FDA-cleared K260746

S-scan Open (100001800)

Esaote, S.p.A.

S-scan Open is an Esaote MR system for diagnostic image acquisition, reconstruction, display, and professional interpretation within the labeled scanner, coil, sequence, and...

Modality
MRI
Anatomy
Multi-region
Decision
2026-03-27
MRI workflow
FDA-cleared K252379

AIR Recon DL

Ge Medical Systems, LLC

AIR Recon DL adds a deep-learning phase-correction and reconstruction option to supported GE 1.5T, 3T, and 7T MR workflows for all labeled anatomies and ages to reduce noise or...

Modality
MRI
Anatomy
Multi-region
Decision
2025-12-23
MRI workflow