Authorized purpose: AI Segmentation version 1.0 is a static, cloud-hosted web application that generates initial CT organ-at-risk contours for head and neck, thorax, abdomen, and pelvis for review and approval in Eclipse treatment-planning workflows; this release does not include manual editing tools.
Clinical role
Static cloud-based deep-learning and classical organ-at-risk contour generation with web review.
Images and patients
Radiotherapy Planning Imaging · Multi-region
Key limitation
Keep in mind: The release has no manual editing tools and does not provide clinical decisions, medical advice, or plan evaluation. Every contour requires expert review and physician approval in Eclipse; no animal or clinical study was performed.
Clinical detailsPurpose, workflow fit, evidence, and safety record
Workflow navigation pilot
Workflow role has not yet been reviewed for this navigation pilot.
A tag identifies a documented role; it does not establish compatibility or local acceptance. Methods and sources
What does this software do?Authorized purpose: AI Segmentation version 1.0 is a static, cloud-hosted web application that generates initial CT organ-at-risk contours for head and neck, thorax, abdomen, and pelvis for review and approval in Eclipse treatment-planning workflows; this release does not include manual editing tools.
Which images or clinical context are in scope?Modality: Radiotherapy Planning Imaging Anatomy or clinical context: Multi-region Input: CT images for use in radiation therapy treatment planning.
Who uses it?Intended users: Qualified expert radiation-therapy treatment planners and approving physicians.
What does the software produce?Output: Reviewed contours selected for export into Eclipse Treatment Planning System.
What is its most important limitation?Key limitation: The release has no manual editing tools and does not provide clinical decisions, medical advice, or plan evaluation. Every contour requires expert review and physician approval in Eclipse; no animal or clinical study was performed.
Clinical takeaway. Clinical role: AI Segmentation version 1.0 is a static, cloud-hosted web application that generates initial CT organ-at-risk contours for head and neck, thorax, abdomen, and pelvis for review and approval in Eclipse treatment-planning workflows; this release does not include manual editing tools.
Evidence takeaway. Evidence from the reviewed source record: K203469 reports major-level software verification and validation for static nonadaptive segmentation algorithms. The summary discloses no clinical study, sample size, organ-level endpoint, or numerical performance result.
Evidence context
Evidence context not reviewed for this FDA record.
Public-label constraints
Label constraints have not been reviewed for this exact FDA record. Unknown is not all ages or evidence of unsuitability.
Public-label constraints, not patient-level eligibility or a medical recommendation. Training and evaluation populations are separate. Read the original labeling and confirm the exact release and protocol.
Purpose
AI Segmentation version 1.0 is a static, cloud-hosted web application that generates initial CT organ-at-risk contours for head and neck, thorax, abdomen, and pelvis for review and approval in Eclipse treatment-planning workflows; this release does not include manual editing tools.
Exact FDA submission
Checked 2026-09-19
Clinical-use display mirrors the exact FDA-supported purpose reconciled from the decision-summary packet.
The release has no manual editing tools and does not provide clinical decisions, medical advice, or plan evaluation. Every contour requires expert review and physician approval in Eclipse; no animal or clinical study was performed.
Exact FDA submission
Checked 2026-09-19
Exact FDA decision-summary packet reviewed on 2026-09-19; existing wording is supported without expansion.
Metrics are shown only when they are tied to a source, endpoint, population, and tested product version. Candidate literature without exact product and version linkage is not shown as product evidence.
Evidence summary
K203469 reports major-level software verification and validation for static nonadaptive segmentation algorithms. The summary discloses no clinical study, sample size, organ-level endpoint, or numerical performance result.
Sensitivity is not the primary applicable endpoint for this acquisition, reconstruction, segmentation, planning, guidance, or quantitative-biomarker function. Use the task-specific endpoints and tested population reported below.
Reported specificity
Not applicable
Not applicable
Not applicable
Checked 2026-09-03
Specificity is not the primary applicable endpoint for this acquisition, reconstruction, segmentation, planning, guidance, or quantitative-biomarker function. Use the task-specific endpoints and tested population reported below.
No contextualized exact-version metric has completed evidence review. Regulatory-document values, when available, are shown above with their limitations.
K203469 FDA performance package for AI Segmentation
DesignManufacturer nonclinical software and functional verification
PopulationCT organ-at-risk contouring across head and neck, thorax, abdomen, and pelvis
Scopeexact submission
Tested versionVarian AI Segmentation version 1.0
IndependenceSponsor or vendor study
K203469
Manufacturer evidence submitted for substantial equivalence; local clinical, technical, and workflow acceptance remains necessary.
No separate named-product Medicare payment was identified in the reviewed CMS radiation-oncology material. Evaluate net planning or delivery value within the radiotherapy service line.
IT implementationDeployment, interfaces, data handling, and support
System and version relationships
Match the AI release, system build, configuration and region. Source documentation does not establish acceptance of an installed system.
No specific system/version pairing has completed review for this FDA record. A broad DICOM or product-family statement does not establish a named viewer build's support.
Public source context, not tested interoperability. Each hop needs its own release/configuration evidence. Missing or unavailable routes are not documented incompatibility. All local tests are planned, not passed; no installed-system acceptance is recorded.
Acquisition/source → routing → AI processing → returned objects → viewer/worklist/report → support owner
No specific route context has been source-reviewed for this record. Obtain both endpoint builds and documents; this is not a finding of incompatibility.
Acquisition/source
Source context, not route validation: CT images for use in radiation therapy treatment planning.
Scope: Exact FDA submission. The exact packet states CT images but does not state DICOM in this submission text.
Confirm scanner/model, protocol, series completeness and both software builds.
Source context, not route validation: Software-only cloud application with a web interface and Eclipse integration; exact hosting and security controls require vendor confirmation.
Scope: Exact FDA submission.
Confirm processing location, queue ownership, exclusions and exact AI build.
Unresolved route: Reviewed contours selected for export into Eclipse Treatment Planning System.
Scope: Exact FDA submission. Exact FDA decision-summary packet reviewed on 2026-09-19; existing wording is supported without expansion.
Confirm the named viewer/worklist/report build, display behavior and report transfer. Output support alone does not establish this endpoint. The displayed source describes output, not validated end-to-end delivery.
Unresolved route: Not established for the exact route.
Scope: Scope not established.
Name the local, platform and AI supplier support owners and escalation path.
Planned local route tests
No tests below have been performed or accepted.
Patient/study identity (planned). Use approved non-patient test data to verify identifiers, accession and result-to-study linkage at every hop.
Study completeness (planned). Test missing views/series, partial transfer, late arrivals, priors and unsupported acquisition inputs; confirm explicit refusal or fallback.
Ordering and duplicates (planned). Send out-of-order, repeated and corrected studies; verify worklist order, deduplication and no misleading stale results.
Report transfer (planned). Verify output object types, annotations, units, report content, destination and availability of original images.
Access (planned). Verify authorized roles, audit trail, denied access and support ownership at each destination.
Latency and failures (planned). Agree a workload and turnaround target; test queues, timeouts, missing results and fallback reading.
Updates and rollback (planned). Define version change control, revalidation triggers, stop-use criteria and a tested rollback route.
Local implementation checklist
Agree the evidence and acceptance owner with your team and suppliers. Checkmarks apply to this page only and are not acceptance receipts.
Siemens Healthineers' corporate cybersecurity page states a Secure Development Lifecycle addressing pre-market and post-market phases for products under development and a range of existing offerings; a Cybersecurity Management Service maintaining a product security inventory (over 1,000 product versions and over 21,000 monitored software components) with security whitepapers, SBOMs and vulnerability assessments available to customers via teamplay Fleet; incident and vulnerability management channels; and that Siemens Healthineers AG maintains an independent certification of its global Cybersecurity Management System to ISO/IEC 27001:2022 extended by ISO/IEC 27701:2019, with the certificate referenced to the SGS directory. Vendor statement; no certificate or report was read.
Vendor-wide
Checked 2026-10-26
Vendor statement, not an attestation. Identity bridge: Siemens Healthineers' own press release (/press/releases/varian-closing) states it completed the acquisition of Varian Medical Systems, Inc. Corporate program statement; exact-release scope is not established.
Only qualified expert radiation-therapy treatment planners and approving physicians. should operate or interpret the system. Local onboarding should cover the exact release, supported population, limitations, failure examples, escalation, downtime, and competency documentation.
Monitor by exact hardware, software and model version, patient population, anatomy, protocol, operator, input quality, output edits or overrides, failed studies, repeat acquisition or rework, downstream impact, downtime, incidents, recalls, and updates. Track the limits that matter for this product: The release has no manual editing tools and does not provide clinical decisions, medical advice, or plan evaluation. Every contour requires expert review and physician approval in Eclipse; no animal or clinical study was performed.
Use a signed local test set for the supported population and workflow. Include common and difficult cases, exclusions, acquisition variation, failed or low-quality inputs, reviewer overrides, and downstream effects. The release has no manual editing tools and does not provide clinical decisions, medical advice, or plan evaluation. Every contour requires expert review and physician approval in Eclipse; no animal or clinical study was performed.
exact submission · checked 2026-09-03
Define stop-use, escalation, rollback, and revalidation triggers before production use.
Model capital and recurring cost against net staff time after review, throughput, repeat imaging or rework, room time, consumables, infrastructure, training, service, downtime, upgrade, and replacement costs.
product family · checked 2026-09-03
Vendor productivity claims are scenario inputs, not guaranteed local savings.
Monitor by exact hardware, software and model version, patient population, anatomy, protocol, operator, input quality, output edits or overrides, failed studies, repeat acquisition or rework, downstream impact, downtime, incidents, recalls, and updates. Track the limits that matter for this product: The release has no manual editing tools and does not provide clinical decisions, medical advice, or plan evaluation. Every contour requires expert review and physician approval in Eclipse; no animal or clinical study was performed.
exact submission · checked 2026-09-03
Revalidate after material software, hardware, model, protocol, interface, or clinical-policy changes.
Sources & review detailsFDA identity, research record, source ledger, and history
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.
This audit distinguishes completed source review from fields that have not yet been researched.
Exact FDA record reviewedStatus
2026-09-20Last searched
27Fields reviewed
10Source classes checked
20Screened PubMed leads
5Screened trial leads
0Unreviewed FDA recall leads
The refreshed discovery snapshot contains 20 PubMed and 5 ClinicalTrials.gov candidate records. Discovery metadata alone does not establish exact tested-product, version, population, and endpoint applicability, so all candidates remain quarantined and none was promoted. The current discovery snapshot contains 20 PubMed and 5 ClinicalTrials.gov candidate records; its dated, count-matched human screening remains current. Unlinked candidates remain quarantined. Native FDA recall identifiers produced 0 postmarket candidate records; 0 have been reviewed (0 published, 0 rejected) and 0 remain unreviewed.
Candidate leads were screened against the exact product and tested version. Unlinked records remain quarantined.
Source classes: fda ai list, fda decision summary, reimbursement policy, fda device recall, fda decision summary packet, literature index, trial registry, pubmed, clinical trials, openfda device recall
Field review details
Recorded state, verification date, notes and sources for fields without a publishable value. Conflicting records stay explicitly unsettled here; no plain settled value is shown for them.
Public pricing: Not publicly available - checked 2026-09-03 - Exact FDA submission
No public list price for the exact cleared configuration was found. Obtain a written quote separating hardware or license basis, enabled features, implementation, interfaces, infrastructure, training, service, upgrades, renewal, consumables, and exit costs.
Authorized purpose: DeepContour uses deep-learning CT processing to generate editable organ contours and RTSTRUCT objects for selected adult radiation-treatment planning workflows, with quantitative statistics, registration, and three-dimensional visualization; it does not contour tumors.
Authorized purpose: Auto Segmentation generates initial DICOM RT Structure Set contours for 40 organs or subregions from adult contrast or noncontrast CT across head and neck, thorax, abdomen, and pelvis; qualified radiotherapy staff must review labels and edit contours before planning.
Authorized purpose: RayStation 12A is configurable software for radiation therapy and medical oncology that proposes treatment plans from user input. Authorized users may use reviewed and approved plans to support treatment administration; the system includes image handling, contouring, treatment planning and optimization, dose calculation and evaluation, machine commissioning, treatment interfaces, and machine-learning segmentation or planning functions.
Authorized purpose: AI Segmentation version 2.0 is a cloud web application that generates initial CT organ-at-risk contours for head and neck, thorax, abdomen, and pelvis for review, editing, and approval in Eclipse treatment-planning workflows; it does not provide clinical decisions or evaluate treatment plans.
Copy this public context and add the field, proposed wording and original source before sending. Nothing here is submitted automatically. Form-specific prefill has not been verified.
Permission to display a submission is not evidence verification. A submission enters editorial review; it does not approve a public change. Form availability, data entry, receipt, review and publication are separate steps. Data entry and receipt remain unverified.
Accepted repository change history
No entry has been added to this scoped change history for this record. This is not proof that the record never changed.