FDA-cleared profile
Limbus AI Inc.
Limbus Contour assists trained radiation oncologists, dosimetrists, and physicists by generating anatomical contours from CT and MR images for radiation-treatment planning. Version 1.8.0 added CT and MR structures, increased the stated RAM requirement to 16 GB, and retained local Windows deployment and file-system DICOM exchange.
Clinical fit
Start with the authorized purpose, then verify how it fits your service line and reading workflow.
Regulatory identity
The FDA listing establishes the regulatory identity. It does not by itself establish local workflow fit, pricing, security, or performance in your environment.
Implementation
Use these fields to structure a vendor demo, security review, and implementation estimate.
Request the current security package and contract controls for the proposed deployment.
Version 1.8.0 added CT and MR structures, increased the stated RAM requirement to 16 GB, and retained local Windows deployment and file-system DICOM exchange. Procurement should map the installed build, modules, models, anatomies, inputs, and outputs to K241837 before acceptance.
exact submission · checked 2026-09-03Later product-family features are not evidence that an earlier cleared release includes them.
File-system import of DICOM images and export of DICOM RT Structure Sets to treatment-planning systems or DICOM viewers without a required proprietary plug-in.
exact submission · checked 2026-09-03Test representative imports, exports, identifiers, orientation, geometry, structure names, units, failure handling, and round trips in the local environment.
Use a signed local test set spanning supported anatomies, scanners, protocols, unusual or postsurgical anatomy, and small or complex structures. Measure edit burden, rejection, downstream plan effects, and reviewer agreement rather than relying only on average overlap metrics.
product family · checked 2026-09-03Define stop-use, escalation, rollback, and revalidation triggers before production use.
Model total annual and per-plan cost against hands-on and elapsed time after review, correction, failed transfers, rework, support, upgrades, downtime, and any effect on plan quality or throughput.
product family · checked 2026-09-03Vendor time-saving results are scenario inputs, not guaranteed local savings.
Monitor by exact software and model version, anatomy, structure, scanner and protocol, patient position, contrast, unusual or postsurgical anatomy, reviewer role, edit time, rejected outputs, DICOM-transfer failures, downstream plan effects, incidents, recalls, and updates. Revalidate after material workflow or model changes.
product family · checked 2026-09-03Trend failures and edits by exact software version, model, anatomy, scanner, protocol, and site.
Evidence
Metrics are shown only when they are tied to a source, endpoint, population, and tested product version.
Sensitivity is not an applicable primary endpoint for this radiation-planning software. Review structure-, model-, workflow-, and release-specific geometric, clinical-review, dosimetric, and edit-burden evidence instead.
Specificity is not an applicable primary endpoint for this radiation-planning software. Review structure-, model-, workflow-, and release-specific geometric, clinical-review, dosimetric, and edit-burden evidence instead.
Eligible CNS, head-and-neck, and prostate cases described in the FDA-cited implementation investigation in Limbus Contour testing described in K241837.
Tested version: Limbus Contour v1.8.0Clinical surveys collected in the FDA-cited implementation investigation in Limbus Contour testing described in K241837.
Tested version: Limbus Contour v1.8.0Mean DSC described for most evaluated automatic contours in Limbus Contour testing described in K241837.
Tested version: Limbus Contour v1.8.0Mean 95% Hausdorff distance described for most evaluated automatic contours in Limbus Contour testing described in K241837.
Tested version: Limbus Contour v1.8.0Time saved to produce clinically acceptable contours in 15 prostate-plus-nodes cases.
Tested version: Limbus Contour v1.6.0Time saved to produce clinically acceptable contours in 15 prostate-only cases.
Tested version: Limbus Contour v1.6.0All reported contours exceeded this DSC value in 30-patient v1.6.0 study.
Tested version: Limbus Contour v1.6.0Manufacturer automatic-contouring verification and release-specific structure-model validation · Release-specific CT and MR anatomical structure models described in the FDA summary
exact submission · Tested version: Limbus Contour v1.8.0 · Sponsor or vendor studyK241837
Manufacturer evidence submitted for substantial equivalence. Version 1.8.0 added CT and MR structures, increased the stated RAM requirement to 16 GB, and retained local Windows deployment and file-system DICOM exchange.
Independent clinical timing, geometric, and dosimetric evaluation by three clinical oncologists · 30 prostate radiotherapy patients, half with prostate-only and half with prostate-plus-nodes planning
product family · Tested version: Limbus Contour v1.6.0 · n=30 · 1 site · Independent studyPMID 38627245 · PMCID PMC11135797
Five of 20 plans optimized using unedited AI structures unnecessarily compromised target coverage, reinforcing expert review.
Economics and lifecycle
These are common procurement questions; unknown values remain visible until a source supports them.
No public list price for the exact cleared release was found. Obtain a written quote separating license basis, sites or users, enabled modules or models, implementation, interfaces, compute, storage, training, support, upgrades, renewal, and exit costs.
No separate named-product payment identified in reviewed CMS material
Centers for Medicare & Medicaid Services · United StatesBuild a local total-cost and value model; do not infer reimbursement from FDA clearance.
Safety and lifecycle
Recall and adverse-event records are shown only after product matching. Adverse-event reports do not establish incidence or causality.
A zero-result exact-identifier search does not prove that no recall, correction, adverse-event report, or product-family safety signal exists. Maintain ongoing FDA and vendor surveillance.
Buyer worksheet
Research record
This audit distinguishes completed source review from fields that have not yet been researched.
Recovered from the prior exact-submission extraction and normalized under the current provenance rules. Exact FDA decision materials, current product-family materials, directly relevant clinical literature, reimbursement context, and exact-identifier recall candidates were reviewed. Pricing, final security architecture, contracted services, enabled modules or models, interoperability, and local acceptance remain organization-specific evidence. Automated exact-name discovery found 5 PubMed and 0 ClinicalTrials.gov candidate records. Candidates require human product and version matching; zero candidates is not evidence that no studies exist. Native FDA recall identifiers produced 0 postmarket candidate records; 0 have been reviewed (0 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, vendor product page, peer reviewed publication, health technology guidance, reimbursement policy, fda device recall, pubmed, clinical trials, openfda device recall
Sources
Sources accessed through 2026-09-03.
Alternatives
Radformation, Inc.
AutoContour Model RADAC V5 assists radiation treatment planners with contouring and reviewing structures in medical images for radiation therapy treatment planning. It produces...
Elekta Solutions AB
The EMLA family delivers external-beam radiation therapy for adult and pediatric patients with benign, malignant, or metastatic disease. Authorized techniques vary by model:...
Therapanacea Sas
ART-Plan+ assists trained radiation-therapy professionals with multimodal image review, registration, contouring, and the release-specific planning functions described in K253091....
Oncospace, Inc.
Oncospace supports trained radiation therapy professionals with protocol configuration, machine-learning achievable-dose prediction, planning-objective exchange, and plan review...