Radiology AI Directory

FDA-cleared profile

AutoContour (RADAC V5)

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 initial machine-learning contours for user review and modification; it does not independently approve a contour or treatment plan.

Radiotherapy planning
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
AutoContour Model RADAC V5 assists radiation treatment planners with contouring and reviewing structures in medical images for radiation therapy treatment planning. It produces initial machine-learning contours for user review and modification; it does not independently approve a contour or treatment plan.
FDA source Exact FDA submission Checked 2026-09-04

Added in P2 round17 from the exact FDA decision material; later product-family claims remain separate.

Intended users
Radiation treatment planners who are qualified to select, review, edit, and export contours. Procurement and governance should include radiation oncologists, dosimetrists, medical physicists, radiation therapists, and clinical IT according to local role assignments.
FDA source Exact FDA submission Checked 2026-09-02
Care setting and population
Professional radiation oncology treatment-planning workflows using DICOM-compatible imaging and treatment-planning systems.
FDA source Exact FDA submission Checked 2026-09-02
Workflow role
Receives CT or MR image sets, generates initial structure contours, supports manual or automatic rigid registration and automatic deformable registration, presents contours for review and editing, and exports DICOM RTSTRUCT, REGISTRATION, and DOSE objects to the treatment-planning workflow.
FDA source Exact FDA submission Checked 2026-09-02
Required input
DICOM CT or MR images for contouring or registration and fusion; PET/CT for registration or fusion only; and DICOM RTSTRUCT and REGISTRATION objects as supported inputs.
FDA source Exact FDA submission Checked 2026-09-02
Output and human action
User-reviewed and editable contours plus DICOM RTSTRUCT, REGISTRATION, and DOSE files for downstream review in a treatment-planning or independent registration-QA system. The FDA summary states that the device has no built-in reporting.
FDA source Exact FDA submission Checked 2026-09-02
Limitations
Every generated contour and registration must be reviewed and edited as needed before planning use. FDA performance is model- and structure-specific: aggregate DSC and reviewer averages do not remove weak outliers, and several structure-level lower confidence bounds fall below the nominal size-category threshold. The summary describes training anatomy from adult male and female patients while its comparison table says any patient type with relevant scan data; pediatric, postsurgical, unusual-anatomy, positioning, contrast, and local-guideline performance therefore require local validation. Current vendor claims for CBCT and other v2.7 functions should not be assumed to be within this exact clearance unless confirmed against the applicable labeling.
Public source Exact FDA submission 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
K260509
FDA source Exact FDA submission Checked 2026-08-31
Modality
Radiotherapy Planning Imaging
FDA source Exact FDA submission Checked 2026-09-02
Anatomy
Multi-region
FDA source Exact FDA submission Checked 2026-09-02

The FDA summary lists head and neck, thorax, abdomen, and pelvis models rather than a single organ or disease site.

Clearance type
510(k)
FDA source Exact FDA submission Checked 2026-08-31
Decision date
2026-03-19
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
The FDA-cleared architecture uses DICOM 3.0 data over TCP/IP, a Windows .NET client, a Windows agent that can monitor network storage for new CT or MR datasets, and a Linux-compatible cloud contouring service. Current AutoContour v2.7 materials also describe direct Eclipse read/write through ESAPI and standalone DICOM workflows; each interface and object type needs site acceptance testing.
FDA source Exact product version Checked 2026-09-02
Deployment and data flow
K260509 describes a Windows client and local Windows agent connected to a Linux-compatible cloud automatic-contouring service. Current v2.7 marketing also offers cloud-based or local compute resources, but the selected commercial architecture, capacity, network path, and support boundary must be confirmed in the quote and deployment design.
FDA source Exact product version Checked 2026-09-02
Security and privacy
Radformation's current license terms state that cloud-processing configurations transmit selected CT or MR images, structures, plan, and dose data after software anonymization, encrypt the data in transit, and delete the imaging-plan data after returning results. The terms place responsibility on the customer to prevent PHI disclosure. Public materials reviewed do not establish the exact V5 authentication, at-rest encryption, retention logging, vulnerability, backup, or incident-response controls for a proposed deployment.
Vendor supplied Product family Checked 2026-09-02

Obtain a current security package and contract exhibits, validate anonymization with representative DICOM objects, and document identity, access, encryption, logging, retention, subprocessor, recovery, and breach-response controls.

Training and support
Radformation's current support terms include online educational materials, videos, and a remote training session with new access. NICE states that trained professionals must always review and edit AI autocontours and maintain manual contouring skills. Local training should therefore cover model selection, contouring-guideline alignment, review and editing, unusual-anatomy failure modes, registration QA, DICOM routing, downtime, and escalation.
Vendor supplied Product family Checked 2026-09-02
Monitoring and change control
Monitor performance by exact software and model version, anatomy, structure, scanner and protocol, patient position, contrast, unusual or postsurgical anatomy, reviewer role, edit time, unusable or missing contours, DICOM transfer failures, registration and dose-export QA, incidents, and adverse events. NICE calls for ongoing error and adverse-event reporting, while independent AutoContour studies show that geometric averages can conceal clinically important outliers and contouring-guideline mismatches.
Public source Product family Checked 2026-09-02

Define signed acceptance thresholds and a revalidation trigger for model, software, scanner, protocol, routing, or local contouring-guideline changes.

Exact cleared model scope

K260509 lists 420 CT-based and 62 MR-based contouring models for head and neck, thorax, abdomen, and pelvis. The current product page advertises 480 models across CT, MR, and CBCT; those counts and modality categories are not interchangeable.

exact submission · checked 2026-09-02

Create an enabled-model inventory tied to the installed build, FDA labeling, local anatomy, local contour definitions, and acceptance status.

SourceSource

DICOM and treatment-planning integration

The exact FDA architecture supports CT and MR contouring, PET/CT registration or fusion, DICOM RTSTRUCT and REGISTRATION inputs, and RTSTRUCT, REGISTRATION, and DOSE exports over TCP/IP. Current v2.7 materials add direct Eclipse and standalone DICOM workflow descriptions.

exact product version · checked 2026-09-02

Test each scanner, TPS, service class, object mapping, frame of reference, naming rule, routing path, retry, and failure-recovery workflow.

SourceSource

Human review and local commissioning

The device produces initial contours for review and modification. NICE and independent studies support model-by-model commissioning, trained review, retained manual skills, and special attention to small structures, unusual anatomy, contrast, positioning, and local contouring conventions.

product family · checked 2026-09-02

Commission with representative local cases and predefine accept, edit, reject, and manual-fallback criteria for each enabled model.

SourceSourceSourceSource

Cloud imaging-data governance

Current terms describe software anonymization, encrypted transmission, processing by Radformation, return of results, and deletion of imaging-plan data, while making the customer responsible for preventing PHI disclosure.

product family · checked 2026-09-02

Validate the behavior technically and contractually, including DICOM private tags, burned-in annotations, logs, support access, deletion evidence, and exception handling.

Source

Economic evaluation

The vendor uses quote-based licensing. NICE found autocontouring economics depend on technology cost, professional grade, review and edit time, and true net time saved, with published time endpoints varying substantially.

product family · checked 2026-09-02

Model costs per completed plan and measure total hands-on and elapsed time, edit burden, rejected contours, downstream rework, throughput, and avoided overtime.

SourceSourceSource

Lifecycle monitoring

Current support terms condition support on current releases and installed updates, while NICE calls for ongoing error and adverse-event reporting. Monitoring must remain version-, model-, and anatomy-specific.

product family · checked 2026-09-02

Use controlled update review, regression cases, release acceptance, incident trending, recall surveillance, downtime drills, and rollback criteria.

SourceSource

Evidence

Performance evidence

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

Evidence summary
V5 has an exact FDA technical-validation package and independent product-family evidence from earlier versions. The evidence supports assisted contour generation with mandatory review; it does not establish autonomous use, universal generalizability, reduced toxicity, improved tumor control, or other patient outcomes.
Public source Exact FDA submission Checked 2026-09-02
Reported sensitivity
Not applicable
Not applicable Not applicable Checked 2026-09-02

Sensitivity is not an applicable endpoint for this contour-generation device. Review the structure-specific DSC, distance, clinician-review, and local edit-burden evidence instead.

Reported specificity
Not applicable
Not applicable Not applicable Checked 2026-09-02

Specificity is not an applicable endpoint for this contour-generation device. Review the structure-specific DSC, distance, clinician-review, and local edit-burden evidence instead.

FDA-listed CT contouring models

420 models

CT-based machine-learning contouring models listed for RADAC V5 in Head and neck, thorax, abdomen, and pelvis structures in the K260509 comparison table.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

FDA-listed MR contouring models

62 models

MR-based machine-learning contouring models listed for RADAC V5 in MR structure models in the K260509 comparison table.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

External CT mean DSC, small structures

0.73 DSC

Mean Dice similarity coefficient across externally reviewed small CT structures in External CT image sets described in the K260509 validation summary.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

External CT mean DSC, medium structures

0.84 DSC

Mean Dice similarity coefficient across externally reviewed medium CT structures in External CT image sets described in the K260509 validation summary.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

External CT mean DSC, large structures

0.93 DSC

Mean Dice similarity coefficient across externally reviewed large CT structures in External CT image sets described in the K260509 validation summary.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

External CT reviewer average

4.37 points on 1-5 scale

Average clinical-expert rating across CT structure models; 5 meant no edits and 1 meant full manual re-contouring in External CT review image sets in the K260509 validation summary.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

External MR mean DSC, small structures

0.71 DSC

Mean Dice similarity coefficient across externally reviewed small MR structures in External MR brain, pelvis, and HDR structure image sets described in K260509.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

External MR mean DSC, medium structures

0.78 DSC

Mean Dice similarity coefficient across externally reviewed medium MR structures in External MR brain, pelvis, and HDR structure image sets described in K260509.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

External MR reviewer average

4.3 points on 1-5 scale

Average clinical-expert rating across MR structure models; 5 meant no edits and 1 meant full manual re-contouring in External MR review image sets in the K260509 validation summary.

Tested version: AutoContour Model RADAC V5 cleared in K260509
Source

Older-version mean contouring time saved

36.6 minutes

Mean time saved across the tested breast, head-and-neck, lung, and prostate contour sets after correction in Timing subset of three cases from an 80-patient, five-vendor evaluation.

Tested version: AutoContour v1.0.25.0 tested in April 2022; not RADAC V5
Source

Older-version average physician score

1.96 points on 1-5 scale

Average physician score for Radformation contours; lower scores indicated fewer required changes in Sixteen organs from 47 patients, reviewed by at least three physicians.

Tested version: AutoContour v2.2.8; not RADAC V5
Source

K260509 AutoContour Model RADAC V5 verification and validation

Manufacturer nonclinical validation using held-out training-test partitions, external CT and MR datasets, size-stratified DSC criteria, clinical-expert Likert review, and existing-model regression tests · CT and MR structures across head and neck, thorax, abdomen, and pelvis, with data from several institutions and countries

exact submission · Tested version: AutoContour Model RADAC V5; regression tables identify AutoContour v2.7 · Sponsor or vendor study

K260509

The FDA summary reports favorable category averages but also structure-level variability, one external MR structure below its DSC criterion, and no patient-outcome study.

Source

A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy

Independent single-center multi-vendor benchmark against manually drawn expert contours with geometric metrics and correction-time measurement · 80 patients: 20 breast, 20 head and neck, 20 lung, and 20 prostate; 45 structures

product family · Tested version: AutoContour v1.0.25.0 tested in April 2022 · n=80 · 1 site · Independent study

PMID 37601695

The authors reported no commercial or financial conflicts and acknowledged vendor support and guidance. Timing estimates used a three-patient subset and cannot be transferred to V5 or another site.

Source

Evaluation of multiple-vendor AI autocontouring solutions

Independent single-center blinded physician review and geometric comparison of three commercial CT autocontouring systems against approved physician contours · Sixteen organs, ten patients per organ, 47 distinct patients, and at least three physician reviewers per contour

product family · Tested version: AutoContour v2.2.8 · n=47 · 1 site · Independent study

PMID 38822385

The study found generally comparable performance but documented poor results with unusual anatomy and local contour-definition differences. It informed implementation across five facilities, but it did not test V5.

Source

Evaluation and failure analysis of four commercial deep learning-based autosegmentation software for abdominal organs at risk

Independent retrospective multi-vendor geometric evaluation with explicit outlier and failure-mode analysis · 111 abdominal cases evaluating liver, stomach, and kidney contours

product family · Tested version: AutoContour v1.7.11 · n=111 · 1 site · Independent study

PMID 39946266

Radformation outliers included liver spill into heart or stomach, incomplete stomach contours with barium, and kidney differences driven by whether the renal pelvis was included. The authors reported no conflicts.

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 AutoContour Model RADAC V5 was found on the reviewed product page. Radformation's license agreement places fees in a customer quote, treats pricing as confidential, and allows additional charges for special support. A quote should separate license basis, delivery-system count, implementation, local or cloud compute, storage and network needs, training, support, upgrades, and renewal terms.
Vendor supplied Product family Checked 2026-09-02
Reimbursement and coding
No separate named-product Medicare payment for AutoContour was identified in the reviewed CMS Radiation Oncology Model material. Economic value should be evaluated within the radiation-therapy planning service line using net staff time saved after review and editing, implementation and recurring costs, throughput effects, rework, and downstream plan-quality measures.
Public source Not applicable Checked 2026-09-02

No product-specific code

No separate named-product payment identified in the reviewed CMS Radiation Oncology Model page

Medicare · United States

This is service-line payment context, not a comprehensive coding, coverage, or procurement determination.

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
The 2026-09-02 openFDA device-recall snapshot contained no record matched to K260509 by exact submission identifier.
Public source Exact FDA submission Checked 2026-09-02

A zero-result exact-identifier search does not prove that no recall, correction, MAUDE report, or other safety signal exists under a model, catalog, software-version, or product-family identifier. Maintain ongoing FDA and vendor surveillance.

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
26Fields reviewed
14Source classes checked
20Reviewed PubMed leads
0Reviewed trial leads
0Unreviewed FDA recall leads

Twenty PubMed records were screened. PMID 38822385 concerns AutoContour v2.2.8 rather than RADAC V5/K260509, and the other records do not establish exact release linkage. No evidence was promoted, and all 20 candidates remain quarantined. The current discovery snapshot contains 20 PubMed and 0 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, vendor product page, vendor legal documentation, peer reviewed publication, health technology guidance, trial registry, reimbursement policy, fda device recall, fda decision material, literature index, pubmed, clinical trials, openfda device recall

Sources

Source ledger

Sources accessed through 2026-09-02.

Alternatives

Related tools to compare

FDA-cleared K253091

ART-Plan+ (v3.1.0)

Therapanacea Sas

ART-Plan+ assists trained radiation-therapy professionals with multimodal image review, registration, contouring, and the release-specific planning functions described in K253091....

Modality
Radiotherapy Planning Imaging
Anatomy
Multi-region
Decision
2025-12-23
Breast imagingRadiotherapy planningProstate imaging
FDA-cleared K242748

Oncospace

Oncospace, Inc.

Oncospace supports trained radiation therapy professionals with protocol configuration, machine-learning achievable-dose prediction, planning-objective exchange, and plan review...

Modality
Radiotherapy Planning Imaging
Anatomy
Multi-region
Decision
2025-04-11
Radiotherapy planning