(131 days)
Not Found
Yes
The document explicitly states that the software implements "artificial intelligence (AI) including non-adaptive machine learning algorithms".
No.
This device is a software tool used in radiation treatment planning to identify anatomical structures. It does not directly treat or diagnose a disease.
No
The device is intended to derive contours of anatomical structures for input to a radiation treatment planning system. It processes CT studies to identify "organs at risk" (OAR) for radiation therapy. This function is for planning treatment, not for diagnosing a disease or condition.
Yes
The device description explicitly states "Automatic Anatomy Recognition product for radiation therapy planning (AAR) is a software-only medical device". The description of its function and deployment on a cloud-based platform further supports this. While it processes CT studies and outputs contours for use in other systems, it does not include any hardware components.
Based on the provided information, this device is not an IVD (In Vitro Diagnostic).
Here's why:
- IVD Definition: In vitro diagnostics are tests performed on samples taken from the human body, such as blood, urine, or tissue, to detect diseases, conditions, or infections. They are used to provide information for diagnosis, monitoring, or screening.
- Device Function: The described device, Automatic Anatomy Recognition (AAR), is a software-only medical device that processes computed tomography (CT) studies (medical images) to derive contours of anatomical structures. It does not analyze biological samples from the body.
- Intended Use: The intended use is for radiation treatment planning, specifically to identify "organs at risk" (OAR) from CT images. This is a process that occurs after a diagnosis has been made and is part of the treatment planning workflow, not the diagnostic process itself.
The device falls under the category of radiological image processing software, which is distinct from in vitro diagnostics.
No
The letter does not state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
Automatic Anatomy Recognition (AAR) is a software-only medical device intended for use by technicians and trained physicians to derive contours of anatomical structures from computed tomography studies for input to a radiation treatment planning system. It is only intended to work for anatomical structures in the head & neck and thoracic body regions. It is not for use on patients below 18 years of age and it relies on third party treatment planning systems to display and edit the contours.
Product codes
QKB
Device Description
Automatic Anatomy Recognition product for radiation therapy planning (AAR) is a software-only medical device and is deployed on a cloud-based platform. AAR is intended to be used on adults undergoing treatment that requires the identification of anatomical structures in the body considered to be "organs at risk" (OAR). AAR is intended to be used in the head and thoracic body regions.
AAR operates independently from the treatment plan that is subsequently created based on AARgenerated contours. Therefore, AAR is agnostic to the method of radiation treatment delivery such as photons, protons, or other, to the modality of radiation treatment such as three-dimensional conformal radiation therapy (3D-CRT), intensity modulated radiation therapy (IMRT), or other, and to the intent of radiation treatment such as definitive (curative), neoadjuvant, adjuvant, or palliative.
AAR is also agnostic to the disease process being treated in the head and neck or thoracic body regions, For example, the identification of OARs is required during the treatment of head and neck cancers such as squamous cell carcinoma, brain cancer, and lymphoma. The identification of OARs is also required during the treatment of thoracic cancers such as lung cancer, breast cancer, esophageal cancer, lymphoma, and thymoma, just to name a few.
AAR automatically processes computed tomography (CT) studies and produces contours with no human intervention. AAR does not provide the capability to modify contours. If adjustments are required, they must be performed on another system.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
Computed Tomography
Anatomical Site
Head & neck, thoracic body regions
Indicated Patient Age Range
Not for use on patients below 18 years of age (i.e. 18 years of age and older)
Intended User / Care Setting
Technicians and trained physicians
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
Not Found
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Segmentation Performance Test: Evaluated automated segmentation accuracy non-inferiority using DICE similarity coefficients. Software Verification and Validation testing.
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/10 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: a seal on the left and the FDA acronym with the full name of the agency on the right. The seal features an eagle with its wings spread, surrounded by text that reads "DEPARTMENT OF HEALTH & HUMAN SERVICES-USA". The right side of the logo displays the acronym "FDA" in blue, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in a larger, bolder font, also in blue.
Quantitative Radiology Solutions, LLC % Mary Vater 510(k) Consultant Medical Device Academy 345 Lincoln Hill Rd. SHREWSBURY, VT 05738
Re: K203610
Trade/Device Name: Automatic Anatomy Recognition (AAR) Regulation Number: 21 CFR 892.2050 Regulation Name: Picture Archiving And Communications System Regulatory Class: Class II Product Code: QKB Dated: March 22, 2021 Received: March 23, 2021
Dear Mary Vater:
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
April 20, 2021
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,
For
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) K203610
Device Name Automatic Anatomy Recognition System
Indications for Use (Describe)
Automatic Anatomy Recognition (AAR) is a software-only medical device intended for use by technicians and trained physicians to derive contours of anatomical structures from computed tomography studies for input to a radiation treatment planning system. It is only intended to work for anatomical structures in the head & neck and thoracic body regions. It is not for use on patients below 18 years of age and it relies on third party treatment planning systems to display and edit the contours.
Type of Use (Select one or both, as applicable) | |||
---|---|---|---|
X 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
510(k) SUMMARY
This summary of 510(k) safety and effectiveness information is submitted in accordance with the requirements of 21 CFR §807.92:
- SUBMITTER Quantitative Radiology Solutions, LLC 3675 Market Street, Suite 200 Philadelphia, PA 19104 | USA Tel: +1.973.590.8574
Contact Person: Steve Owens Date Prepared: December 9, 2020
II. DEVICE | |
---|---|
Name of Device: | Automatic Anatomy Recognition |
Classification Name: | Picture Archiving And Communications System |
Regulation: | 21 CFR §892.2050 |
Regulatory Class: | Class II |
Product Classification Code: | QKB |
Ⅲ. PREDICATE DEVICE
Predicate Manufacturer: | Xiamen Manteia Technology LTD. |
---|---|
Predicate Trade Name: | AccuContour™ |
Predicate 510(k): | K191928 |
No reference devices were used in this submission.
IV. DEVICE DESCRIPTION
...
Automatic Anatomy Recognition product for radiation therapy planning (AAR) is a software-only medical device and is deployed on a cloud-based platform. AAR is intended to be used on adults undergoing treatment that requires the identification of anatomical structures in the body considered to be "organs at risk" (OAR). AAR is intended to be used in the head and thoracic body regions.
AAR operates independently from the treatment plan that is subsequently created based on AARgenerated contours. Therefore, AAR is agnostic to the method of radiation treatment delivery such as photons, protons, or other, to the modality of radiation treatment such as three-dimensional conformal radiation therapy (3D-CRT), intensity modulated radiation therapy (IMRT), or other, and to the intent of radiation treatment such as definitive (curative), neoadjuvant, adjuvant, or palliative.
AAR is also agnostic to the disease process being treated in the head and neck or thoracic body regions, For example, the identification of OARs is required during the treatment of head and neck cancers such as squamous cell carcinoma, brain cancer, and lymphoma. The identification of OARs is also required during the treatment of thoracic cancers such as lung cancer, breast cancer, esophageal cancer, lymphoma, and thymoma, just to name a few.
AAR automatically processes computed tomography (CT) studies and produces contours with no human intervention. AAR does not provide the capability to modify contours. If adjustments are required, they must be performed on another system.
4
V. INDICATIONS FOR USE
Automatic Anatomy Recognition (AAR) is a software-only medical device intended for use by technicians and trained physicians to derive contours of anatomical structures from computed tomography studies for input to a radiation treatment planning system. It is only intended to work for anatomical structures in the head & neck and thoracic body regions. It is not for use on patients below 18 years of age and it relies on third party treatment planning systems to display and edit the contours.
COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE VI. PREDICATE DEVCE
The following characteristics were compared between the subject device and the predicate device in order to demonstrate substantial equivalence:
- Indications for Use The predicate and subject device have identical indications for use. .
- . Materials - The predicate and subject device are both software-only medical devices.
- Design The predicate and subject device both utilize deep learning contouring to . automatically contour the organ-at-risk for the head, neck, and thorax.
- . Energy Source - The predicate and subject device both run within the users' existing computer system.
- Other Design Features The predicate device has additional features such as patient . management, review of processed images, automatic image registration, manual contouring functionality, and segmentation in the abdomen and pelvic regions. This additional functionality is not required to achieve the intended use for the subject device.
- . Performance Testing - The predicate and subject device conducted segmentation performance tests to evaluate the automated segmentation accuracy using DICE similarity coefficients. These tests were further supported by additional tests using a mean 95% Hausdorff Distance (HD) calculation.
Table 1: Proposed Predicate Device | |||
---|---|---|---|
Subject Device | Proposed Predicate Device | Rationale for SE | |
Device Name | Automatic Anatomy Recognition | ||
(AAR) | AccuContourTM | N/A | |
Applicant | Quantitative Radiology Solutions | Xiamen Manteia Technology LTD. | N/A |
510(k) Number | TBD | K191928 | N/A |
Decision Date | TBD | 02/28/2020 | N/A |
Regulation | |||
Number | 892.2050 | 892.2050 | Same |
Regulation Name | Picture archiving and | ||
communication system | Picture archiving and communication | ||
system | Same | ||
Device | Radiological Image Processing | ||
Software for Radiation Therapy | Radiological Image Processing | ||
Software for Radiation Therapy | Same | ||
Regulatory | |||
Definition | To provide semi-automatic-or fully- | ||
automated radiological image | |||
process and analysis tools for | |||
radiation therapy. Software | |||
implementing artificial intelligence | |||
(AI) including non-adaptive | |||
machine learning algorithms trained | |||
with clinical and/or artificial | |||
radiological images. In these | |||
devices, the algorithm training | |||
images typically impact device. | To provide semi-automatic or fully- | ||
automated radiological image | |||
process and analysis tools for | |||
radiation therapy. Software | |||
implementing artificial intelligence | |||
(AI) including non-adaptive machine | |||
learning algorithms trained with | |||
clinical and/or artificial radiological | |||
images. In these devices, the | |||
algorithm training images typically | |||
impact device performance. AI based | Both the subject | ||
device and the | |||
predicate fall under | |||
the regulatory | |||
definition for | |||
892.2050, product | |||
code QKB. | |||
Product Code | |||
performance. AI based radiological | |||
image processing software is | |||
intended to be used in the workflow | |||
of radiation therapy. Adaptive AI | |||
algorithms are not within the scope | |||
of this product code. Primary | |||
radiation dose calculation or plan | |||
optimization for treatment planning | |||
are not within scope of the product | |||
code. | radiological image processing | ||
software is intended to be used in the | |||
workflow of radiation therapy. | |||
Adaptive AI algorithms are not | |||
within the scope of this product code. | |||
Primary radiation dose calculation or | |||
plan optimization for treatment | |||
planning are not within scope of the | |||
product code. | |||
Product Code | QKB | QKB | Same |
Classification | Class II | Class II | Same |
510(k) Review | |||
Panel | Radiology | Radiology | Same |
Combination | |||
Product? | No | No | Same |
Rx or OTC? | RX | RX | Same |
Intended Use / | |||
Indications for Use | Automatic Anatomy Recognition | ||
(AAR) is a software-only medical | |||
device intended for use by | |||
technicians and trained physicians | |||
to derive contours of anatomical | |||
structures from computed | |||
tomography studies for input to a | |||
radiation treatment planning system. | |||
It is only intended to work for | |||
anatomical structures in the head & | |||
neck and thoracic body regions. It is | |||
not for use on patients below 18 | |||
years of age and it relies on third | |||
party treatment planning systems to | |||
display and edit the contours. | It is used by radiation oncology | ||
department to register multimodality | |||
images and segment (non-contrast) | |||
CT images, to generate needed | |||
information for treating planning, | |||
treatment evaluation and treatment | |||
adaptation. | Same | ||
Image process | |||
functions | 1) Deep learning contouring: it | ||
can automatically contour | |||
anatomical structures, including | |||
head and neck, thorax (for both | |||
male and female). | 1) Deep learning contouring: it can | ||
automatically contour the organ- | |||
at-risk, including head and neck, | |||
thorax, abdomen and pelvis (for | |||
both male and female); |
- Automatic Registration, and
- Manual Contour | Same. AAR contains
only Deep Learning
contouring |
| General
Functionalities | Receive, add/edit/delete,
transmit, input/export, medical
images and DICOM data | Receive, add/edit/delete,
transmit, input/export, medical
images and DICOM data;Patient management;Review of processed images;Open and Save of files. | Same. AAR only
receives,
adds/edits/deletes,
transmits,
inputs/exports
medical images and
DICOM data |
| Operating Systems | Linux | Windows | QRS utilizes Linux as
this OS is more
secure as compared
to Windows |
| Segmentation Features | | | |
| Algorithm | Deep Learning | Deep Learning | Same |
| Compatible
Modality | Non-Contrast CT | Non-Contrast CT | Same |
| Compatible
Scanner Models | No limitation on scanner model,
DICOM 3.0 compliance required | No limitation on scanner model,
DICOM 3.0 compliance required | Same |
| Compatible
Treatment
Planning System | No limitation on TPS model,
DICOM 3.0 compliance required. | No limitation on TPS model, DICOM
3.0 compliance required. | Same |
| Contraindications | AAR is not intended for use on
patients below 18 years of age; | None | AAR is intended for
use in adults |
| Segmentation Features | | | |
| Performance
Testing | Segmentation Performance Test
Evaluated automated
segmentation accuracy non-
inferiority using DICE
similarity coefficients. Software Verification and
Validation testing | Segmentation Performance Test
Evaluated automated
segmentation accuracy non-
inferiority using DICE similarity
coefficients. Registration Performance Test | Segmentation
Performance Testing
is equivalent.
Registration
performance test is
N/A because the
subject device does
not do registration. |
5
6
VII. PERFORMANCE DATA
The following performance data were provided in support of the substantial equivalence determination.
Sterilization & Shelf-life Testing
Not Applicable (Standalone Software)
Biocompatibility Testing
Not Applicable (Standalone Software)
Electrical safety and electromagnetic compatibility (EMC)
Not Applicable (Passive Device)
Software Verification and Validation Testing
Software Verification and Validation Testing included testing at the unit, integration, and system level per IEC 62304 standard.
Mechanical and acoustic Testing
Not Applicable (Standalone Software)
Animal Study
Animal performance testing was not required to demonstrate safety and effectiveness of the device.
Human Clinical Performance Testing
Clinical testing was not required to demonstrate the safety and effectiveness of the device.
VIII. CONCLUSIONS
Based on the comparison and analysis above, the proposed devices are determined to be Substantially Equivalent (SE) to the predicate devices.