(263 days)
Yes
The document explicitly states "Machine learning based contouring" and mentions validating the "generalizability of the machine learning model."
No
The device aids in contouring structures for radiation therapy planning, but it does not directly treat or diagnose a disease; it is a tool for treatment preparation.
No
The device is intended to assist in contouring structures for radiation therapy treatment planning, which is a part of treatment preparation, not diagnosis. It produces initial contours and allows for review, editing, and export of structure sets, all of which support treatment planning rather than identifying a medical condition or disease.
Yes
The device description explicitly states it consists of an "agent" service running on Windows, a cloud-based service, and a web application. These are all software components. While it interacts with medical images (data), it does not describe any hardware components that are part of the device itself.
Based on the provided information, this device is NOT an IVD (In Vitro Diagnostic).
Here's why:
- Intended Use: The intended use is to "assist radiation treatment planners in contouring structures within medical images in preparation for radiation therapy treatment planning." This is a tool for medical image processing and planning, not for performing tests on biological samples to diagnose or monitor a disease or condition.
- Device Description: The description details a software system for image processing and contouring, not a device that analyzes biological specimens.
- Input: The input is medical imaging data (CT, MR, PET), not biological samples like blood, urine, or tissue.
- Function: The core function is image contouring and registration, which are steps in the radiation therapy planning workflow, not diagnostic testing.
IVD devices are specifically designed to perform tests on samples taken from the human body to provide information for diagnosis, monitoring, or screening. AutoContour's function falls outside of this definition.
No
The provided text does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device. The closest related mention is "As with the Predicate Devices, no clinical trials were performed for AutoContour. Nonclinical tests were performed according to Radformation's AutoContour Complete Test Protocol and Report, which demonstrates that AutoContour performs as intended per its indications for use. Further tests were performed on independent datasets from those included in training and validation sets in order to validate the generalizability of the machine learning model. Verification and validation tests were performed to ensure that the software works as intended and pass/fail criteria were used to verify requirements." This is not an explicit statement that the PCCP has been authorized by the FDA.
Intended Use / Indications for Use
AutoContour is intended to assist radiation treatment planners in contouring structures within medical images in preparation for radiation therapy treatment planning.
Product codes
QKB
Device Description
AutoContour consists of 3 main components:
-
- An "agent" service designed to run on the Windows Operating System that is configured by the user to monitor a network storage location for new CT datasets that are to be automatically uploaded to:
-
- A cloud-based AutoContour automatic contouring service that produces initial contours and
-
- A web application accessed via web browser which allows the user to perform registration with other image sets as well as review, edit, and export the structure set containing the contours.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Machine learning based contouring
Input Imaging Modality
CT input for contouring or manual registration/fusion. MR, PET input for manual registration/fusion only.
Anatomical Site
Not Found
Indicated Patient Age Range
Any patient type for whom relevant modality scan data is available.
Intended User / Care Setting
Trained radiation oncology personnel
Description of the training set, sample size, data source, and annotation protocol
Not Found
Description of the test set, sample size, data source, and annotation protocol
Further tests were performed on independent datasets from those included in training and validation sets in order to validate the generalizability of the machine learning model.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Nonclinical tests were performed according to Radformation's AutoContour Complete Test Protocol and Report, which demonstrates that AutoContour performs as intended per its indications for use. Verification and validation tests were performed to ensure that the software works as intended and pass/fail criteria were used to verify requirements.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Not Found
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
0
Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
October 30, 2020
Radformation, Inc. % Mr. Kurt Sysock Co-founder/CEO 335 Madison Avenue, 16th Floor NEW YORK NY 10017
Re: K200323
Trade/Device Name: AutoContour Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: QKB Dated: September 19, 2020 Received: September 22, 2020
Dear Mr. Sysock:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part
1
801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4. Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known)
Device Name AutoContour
Indications for Use (Describe)
AutoContour is intended to assist radiation treatment planners in contouring structures within medical images in preparation for radiation therapy treatment planning.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)
| Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
3
Section 5. 510(k) Summary
4
This 510(k) Summary has been created per the requirements of the Safe Medical Device Act (SMDA) of 1990, and the content is provided in conformance with 21 CFR Part 807.92.
5.1. Submitter's Information
| Table 1 : Submitter's Information | |
|---|---|
| Submitter's Name: | Kurt Sysock |
| Company: | Radformation, Inc. |
| Address: | 335 Madison Avenue, 16th Floor |
| New York, NY 10017 | |
| Contact Person: | Alan Nelson |
| Chief Science Officer, Radformation | |
| Phone: | 518-888-5727 |
| Fax: | ---------- |
| Email: | anelson@radformation.com |
| Date of Summary Preparation | 9/16/2020 |
5.2. Device Information
| Table 2 : Device Information | |
|---|---|
| Trade Name: | AutoContour |
| Common Name: | AutoContour, AutoContouring, AutoContour Agent, |
| AutoContour Web Application | |
| Classification Name: | Class II |
| Classification: | Picture archiving and communications system |
| Regulation Number: | 892.2050 |
| Product Code: | QKB |
| Classification Panel: | Radiology |
5.3. Predicate Devices Information
Mirada RTx (K130393) & Workflow Box (K181572)
5
5.4. Device Description
AutoContour consists of 3 main components:
-
- An "agent" service designed to run on the Windows Operating System that is configured by the user to monitor a network storage location for new CT datasets that are to be automatically uploaded to:
-
- A cloud-based AutoContour automatic contouring service that produces initial contours and
-
- A web application accessed via web browser which allows the user to perform registration with other image sets as well as review, edit, and export the structure set containing the contours.
5.5. Indications for Use
AutoContour is intended to assist radiation treatment planners in contouring and reviewing structures within medical images in preparation for radiation therapy treatment planning.
5.6. Technological Characteristics
AutoContour (Subject Device) makes use of a Predicate Devices, Mirada RTx (K130393) & Workflow Box (K181572) for substantial equivalence comparison. Note that Workflow Box utilizes Mirada RTx as its predicate device.
5.6.1. AutoContour vs. Mirada RTx (K130393) & Workflow Box (K181572)
RTx is "intended to display and visualize 2D & 3D multi-modal medical image data" and "supports the loading and saving of DICOM RT objects and allows the user to define, import, display, transform, store and export such objects including regions of interest structure and dose volumes to radiation therapy planning systems" (https://www.accessdata.fda.gov/cdrh docs/pdf13/K130393.pdf, accessed 1/20/2020).
Workflow Box "is a system designed to allow users to route DICOM-compliant data to and from automated processing components... [including] processing components for automatically contouring imaging data using … machine learning based algorithms."
(https://www.accessdata.fda.gov/cdrh docs/pdf18/K181572.pdf, accessed 1/20/2020)
| Table 3: Substantial Equivalence AutoContour vs. RTx & Workflow Box | |||
|---|---|---|---|
| Characteristic | Subject Device: | ||
| AutoContour | |||
| Radformation | Predicate Device: | ||
| Workflow Box (K181572) | Predicate Device: Mirada | ||
| RTx (K130393) | |||
| Target | |||
| Population | Any patient type for | ||
| whom relevant modality | |||
| scan data is available. | Any patient type for | ||
| whom relevant | |||
| modality scan data is | Any patient type for whom | ||
| relevant modality scan data | |||
| is available. | |||
| (Substantially | |||
| Equivalent) | available. | ||
| Energy Used | |||
| and/or | |||
| Delivered | None - software only | ||
| application. The software | |||
| application does not | |||
| deliver or depend on | |||
| energy delivered to or | |||
| from patients | |||
| (Substantially | |||
| Equivalent) | None - software only | ||
| application. The | |||
| software application | |||
| does not deliver or |
| None - software only
application. The software
application does not
deliver or depend on
energy delivered to or from
patients |
| Intended users | Trained radiation
oncology personnel
(Substantially
Equivalent) | Designed to be used by
trained clinicians | Designed to be used by
trained clinicians |
| Design: Data
Visualisation/Gr
aphical User
Interface | Contains both an
automated processing
component and Data
Visualisation / Graphical
User Interface
(Substantially
Equivalent) | None - the proposed
device has no data
visualization
functionality. All data
processing is
automated and does
not require user
interaction. A control
interface is provided for
system administration
and configuration only | Yes. |
| Design: View
manipulation
and Volume
rendering | Window and level, pan,
zoom, cross-hairs, slice
navigation, fused views.
(Subject Device
functionality is a subset
of Predicate Devices) | None - Not applicable | Window and level, pan,
zoom, cross-hairs, slice
navigation. Maximum or
minimum intensity projection
(MIP), volume rendering,
color rendering, surface
rendering, multi-planar
reconstruction (MPR), fused
views, gallery views. |
| Design: Image
registration | Manual Rigid
registration.
(Subject Device
functionality is a subset
of Predicate Devices) | Registration for the
purposes of
replanning/re-contouring
and atlas based
contouring. The
algorithms used for
image registration are
the same for both
predicate and proposed
devices. | Manual and Landmark
Rigid. Automatic multi-modal
rigid. Mono-modal and
multi-modal deformable
registration. Motion correction
in hybrid scans and gated
scans. Registration for the
purposes of
re-planning/recontouring and
atlas based contouring. |
| Regions and
Volumes of
interest (ROI) | Machine learning based
contouring and manual
ROI manipulation.
(Subject Device | Atlas Based contouring,
registration based
re-contouring, machine | 2D and 3D ROIs,
semi-automatic ROI
definition, isocontour ROIs
using threshold and |
| | functionality is a subset
of Predicate Devices) | learning based
contouring | percentage of maximum,
one-click seed-pointing
contouring, manual ROI
manipulation , ROI
transformation, Atlas-based
contouring. |
| Design:
Region/volume
of interest
measurements
and size
measurements | None - not applicable
(Substantially
Equivalent) | None - not applicable | Intensity, Hounsfield units,
activity and SUV
measurements including min,
max, mean, peak, standard
deviation, total glycolytic
activity, median, histogram,
max and mean ratio to
reference region. Gray for RT
Dose. Size measurements
include 2D and 3D
measurements including
rulers and volume, line
profile. |
| Design:
Region/Volume
Quantification | None - not applicable
(Substantially
Equivalent) | None - not applicable | Regions table with charting
supports analysis of
measurement over multiple
studies using standard
protocols such as RECIST,
PERCIST and WHO |
| Design:
Supported
modalities | CT input for contouring
or manual
registration/fusion.
MR, PET input for
manual
registration/fusion only.
DICOM RTSTRUCT for
output
(Minor differences) | CT, MR, DICOM
RTSTRUCT for image
processing. Any valid
DICOM data for data
routing | Static and gated CT and
PET , and static MR, SPECT,
NM, DICOM RT |
| Design:
Reporting and
data routing | No built-in reporting,
supports exporting
DICOM RTSTRUCT file.
(Minor differences) | Supports routing and
distribution of images to
other DICOM nodes
including to custom
executables determined
by the user. | Yes- Distribution of DICOM
compliant Images into other
DICOM compliant systems.
Built-in basic reporting |
| Compatibility
with the
environment
and other
devices | Compatible with data
from any DICOM
compliant scanners for
the applicable modalities.
Agent Uploader
component compatible
with Microsoft Windows. | Compatible with data
from any DICOM
compliant scanners for
the applicable
modalities. Compatible
with Microsoft
Windows . Integration
with Mirada DBx | Compatible with data from
any DICOM compliant
scanners for the applicable
modalities. Compatible
with Microsoft Windows .
Integration with Mirada DBx
application launcher and data
browser. |
| | Cloud-based automatic
contouring service
compatible with Linux.
Web application Server
based application
compatible with Linux
with frontend compatible
with all modern web
browsers..
(Minor differences) | application launcher and
data browser | |
| Communication
s/Networking | TCP/IP
(Subject Device
functionality is a subset
of Predicate Devices) | TCP/IP and SCP | TCP/IP and SCP |
| Computer
platform &
operating
system | Agent Uploader
supporting Microsoft
Windows 10 (64-bit) and
Microsoft Windows
Server 2016.
Cloud-based Server
based automatic
contouring application
compatible with Linux.
Web application Server
based application
compatible with Linux
with frontend compatible
with all modern web
browsers.
(Minor differences) | Server based application
supporting Microsoft
Windows 10 (64-bit) and
Microsoft Windows
Server 2016. | Workstation and Server
based application supporting
Windows Server 2008 R2,
SP1 and Windows 7 (64-bit) |
| Support for
radiation
treatment
planning | AutoContour is intended
to assist radiation
treatment planners in
contouring and reviewing
structures within medical
images in preparation for
radiation therapy
treatment planning
(Subject Device intended
use is a subset of
predicate devices) | "Contours generated by
Workflow Box may be
used as an input to
clinical workflows
including, but not limited
to, radiation therapy
treatment planning" | "RTx supports the loading
and saving of DICOM RT
objects and allows the user to
define, import, display,
transform, store and export
such objects including
regions of interest structures
and dose volumes to
radiation therapy planning
systems." |
6
7
8
Source for RTx & Workflow Box: (https://www.accessdata.fda.gov/cdrh_docs/pdf18/[K181572](https://510k.innolitics.com/search/K181572).pdf, accessed 1/20/2020)
As shown in Table 3, almost all technological characteristics are either substantially equivalent or a subset of the predicate devices' technological characteristics.
9
5.7. Discussion of differences
Subset of the Predicate Device
The comparison table above shows that several features of AutoContour are a subset of the features of the predicate device. This is because AutoContour's indication for use is narrower in scope than the predicate device in that it is intended only "to assist radiation treatment planners in contouring and reviewing structures within medical images in preparation for radiation therapy treatment planning". The design of AutoContour reflects that narrower scope and the features not shared between AutoContour are such that they can operate independently of the features that are not shared with the predicate devices, and therefore these differences do not create new questions regarding the safety and effectiveness of the device relative to the predicate devices.
Minor differences
The following minor differences exist, but do not represent any significant additional risks or decreased effectiveness for the device for its intended use:
- . Design: Supported modalities: AutoContour only supports CT image sets as inputs specifically for the contouring feature, while MR and PET image set inputs are only supported for registration purposes. In the predicate devices, all modalities are available for the workflows. This does not affect the safety and effectiveness of the device as it relates to its indications for use as the vast majority of radiation treatment planning is performed on CT images, and where MR or PET modalities are necessary for localization, AutoContour does support manual registration with those modalities which can be used to guide the contouring of the CT image set.
- . Design: Reporting and data routing: AutoContour does not include reporting features or direct data-routing with DICOM compliant systems instead AutoContour simply produces a DICOM compliant RT Structure Set file that the user may import into a DICOM compliant treatment planning system. This does not raise new questions regarding the safety and effectiveness of the device since the scope of AutoContour's indication for use is limited to making the contoured structures available for radiation treatment planning purposes and does not include managing or routing of the image data to various systems. The feature of managing or routing of the image data in this way is not a necessary component to achieve this goal, so not having this feature does not affect the safety or effectiveness of the device.
- Compatibility with the environment and other devices / Computer platform & operating system: AutoContour utilizes different computer platform & operating system for its 3 components, but this does not raise new questions regarding the safety and effectiveness of the device relative to the predicate device.
10
5.7. Performance Data
As with the Predicate Devices, no clinical trials were performed for AutoContour. Nonclinical tests were performed according to Radformation's AutoContour Complete Test Protocol and Report, which demonstrates that AutoContour performs as intended per its indications for use. Further tests were performed on independent datasets from those included in training and validation sets in order to validate the generalizability of the machine learning model.
Verification and validation tests were performed to ensure that the software works as intended and pass/fail criteria were used to verify requirements.
5.8. Conclusion
AutoContour is deemed substantially equivalent to the Predicate Devices, Mirada RTx (K130393) & Workflow Box (K181572). Verification and Validation testing and Hazard Analysis demonstrate that AutoContour is as safe and effective as the Predicate Devices. The minor technological differences between AutoContour and the Predicate Devices with regard to the intended use do not raise any questions on the safety and effectiveness of the Subject Device.