(115 days)
Not Found
Yes
The document explicitly states the use of "Supervised deep learning-based algorithms" and "Deep learning-based algorithms" in the "Mentions AI, DNN, or ML" section. Deep learning is a subset of machine learning.
No.
The device's intended use is to provide automatic 3D segmentation and label anatomical landmarks of the Aorta from CT Angiography images. It is an image processing software that assists trained professionals in making patient management decisions and does not directly provide therapy or treatment.
No
The device description explicitly states: "The device does not alter the original input data and does not provide a diagnosis."
Yes
The device is explicitly described as "software as a medical device (SaMD)" and an "image processing software device". It is deployed as a containerized application running on off-the-shelf hardware or a cloud platform, indicating it does not include proprietary hardware.
Based on the provided information, TeraRecon Aorta.CT is not an In Vitro Diagnostic (IVD) device.
Here's why:
- IVD Definition: In Vitro Diagnostic devices are used to examine specimens (like blood, urine, or tissue) taken from the human body to provide information about a person's health. This testing is performed outside of the body.
- TeraRecon Aorta.CT Function: TeraRecon Aorta.CT processes medical images (CT Angiography) taken from the human body. It performs image segmentation and landmarking. It does not analyze biological specimens.
- Intended Use: The intended use clearly states it's for processing CT Angiography images and providing segmentation and landmarking results to be used in conjunction with other patient information by trained professionals. It explicitly states it "does not provide a diagnosis."
Therefore, TeraRecon Aorta.CT falls under the category of medical image processing software or a Software as a Medical Device (SaMD), not an In Vitro Diagnostic device.
No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device. The provided text indicates "Control Plan Authorized (PCCP) and relevant text Not Found".
Intended Use / Indications for Use
TeraRecon Aorta.CT is intended to provide an automatic 3D segmentation and label anatomical landmarks of the Aorta. The results of TeraRecon Aorta.CT are intended to be used in conjunction with other patient information by trained professionals who are responsible for making any patient management decision per the standard of care. TeraRecon Aorta.CT is a software as a medical device (SaMD) deployed as a containerized application. The device inputs areCT Angiography with contrast DICOM images. The device outputs are DICOM result files which may be viewed utilizing DICOM-compliant systems. The device does not alter the original input data and does not provide a diagnosis.
TeraRecon Aorta.CT is indicated to generate results from aortic CT Angiography scans taken of adult patients except patients with pre-existing aortic device, bicuspid aortic valve anomaly, aortic dissection, aortic rupture, and abdominal metallic devices. The device is not specific to any gender, ethnic group, or clinical condition.
Product codes
QIH
Device Description
The TeraRecon Aorta.CT algorithm is an image processing software device that can be deployed as a containerized application (e.g., Docker container) that runs on off-the-shelf hardware or on a cloud platform.
The device provides an automatic 3D segmentation of the aorta and landmarks of important aortic anatomy. When TeraRecon Aorta.CT results are used in external viewer devices such as TeraRecon's Intuition or Eureka Clinical Al medical devices, all the standard features offered by the external viewer are employed.
The TeraRecon Aorta.CT algorithm is not intended to replace the skill and judgment of a qualified medical practitioner and should only be used by individuals that have been trained in the software's function, capabilities, and limitations.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
CT Angiography with contrast DICOM images
Anatomical Site
Aorta
Indicated Patient Age Range
adult patients
Intended User / Care Setting
trained professionals
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
For testing the lumen and aorta segmentation, we selected 170 studies which matched the inclusion exclusion criteria. The final manufacturer distribution was 77 Siemens, 33 GE, 35 Philips, and 25 Canon. All collected datasets were checked and were found acceptable to use by a US board certified radiologist, who is currently practicing in the United States and reads similar scans.
For testing the aorta landmarking, we selected 170 studies which matched the inclusion criteria, but we found that the number of landmarks outside the field of view was higher than expected: 40-45% actual vs 30% expected. The annotators were unable to provide annotations for these images, and we had a range of between 55-60 annotatable landmarks per landmark target. Additionally, sections of many images contained image artifacts which made annotation impossible. These artifacts included motion artifacts, occluded vessels, and lack of contrast in the aortic arch and heart. We increased the number of studies to achieve our target of 70 annotatable landmarks, according to our power calculations. We added 29 additional studies to the initial total. After adding 29 supplemental studies, we averaged 73 annotatable landmarks per landmark target with a minimum of 63. Thus, we stopped increasing the sample size.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
The TeraRecon Aorta.CT device underwent a retrospective cohort study where ground truth was established and compared to the output of the device as described below:
At least 50% of the ground truth data is of US patients from 3 geographical regions in the United States. Each ground truth scan will also pass through the subject device. 170 adult patients are included in the cohort meeting the following inclusion criteria: Patients must be 18 or older, must have had a CT Angiography scan for cardiac or CT Angiographic scan for abdomen or for both covering cardiac and abdominal aorta, and the validation data should be enriched with data from patients with clinical diagnosis of aortic dilation/aneurysm and/or aortic valve disease.
The following results will be compared between the ground truth and device results, Lumen Segmentation: Comparison of Aorta Jumen segmentation results from the medical device to aorta lumen segmentation from ground truth. Aorta wall segmentation: The test will compare the results from ground truth to medical device output representing for aorta wall to wall segmentation. This aorta wall to wall segmentation includes aorta lumen + wall for the comparison. The lumen and aorta wall (including lumen) segmentations are important for extracting measurements that can be used by the clinicians for procedure planning. Landmarking results: The 22 anatomical landmarks for aorta will be compared from the device output to the ground truth.
For each CTA scan we will record aortic lumen segmentation DICE score and aorta segmentation DICE score for the subject device vs each of the ground truths. Our acceptance criteria for lumen and aorta segmentation accuracy are for average DICE score >= 80%.
For each CTA scan, we will also examine the subject device landmarking locations compared to each ground truth annotation. The Common Left and Right Iliac Arteries, Left and Right Femoral Arteries (4 landmarks) will be evaluated by whether or not the subject device correctly identified the vessel in accordance with ground truth. In a typical clinical workflow, these landmarks need only identify any point in the center of the vessel, thus the identification of the overall anatomic location is of greatest importance, rather than exact location.
The remaining landmarks except for the aortic bifurcation (17 landmarks) will be assessed using Euclidean distance between ground truth annotation and medical device output locations. We will determine whether the Euclidean distance is within 5mm.
Finally, for the aortic bifurcation (1 landmark), the exact location is not clearly defined, and a general area is sufficient in typical clinical practice. We will determine whether the Euclidean distance is within 2cm compared to ground truth.
Our acceptance criteria for the landmarks are whether each of the 22 landmarks independently pass the class-specific criteria in 80% of the cases. To provide evidence of precision, we will assess whether the lower bound of the 95% exact binomial confidence interval (binom.confint from the R power library) is greater than or equal to 70% (~ acceptance level - 10%). A sample size of 100 CTA scans was chosen since during power simulations of 10.000 simulated runs, an actual case-wise pass rate of 90% resulted in power of 81% to pass all 24 tests after accounting for 30% loss of cases due to some landmarks being outside of field of view. Power calculation code displayed in appendix.
Following execution of the study, it was determined that the TeraRecon Aorta.CT device passed the acceptance criteria established in the study based on the following results:
Our acceptance criteria for lumen and segmentation is to confirm a mean DICE score of >=80%. The lumen segmentation results passed with a mean DICE score of 88%. The aorta segmentation results passed with a mean DICE score of 90%.
Our acceptance is to assess whether each of the 22 landmarks independently pass evaluation in 80% of the cases. To provide evidence of precision we assess whether the lower bound of the 95% exact binomial confidence interval (binom.confint from the R power library) is greater than or equal to 70% (~ acceptance level - 10%). All landmarks passed the acceptance criteria, all 95% confidence intervals were at least 70%.
The test results support the conclusion that the TeraRecon Aorta.CT device is as safe, as effective and performs as well as the predicate device cleared under K220039.
Key Metrics
Mean DICE score of 88% for lumen segmentation.
Mean DICE score of 90% for aorta segmentation.
All 22 landmarks passed the acceptance criteria, all 95% confidence intervals were at least 70%.
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
January 23, 2025
Image /page/0/Picture/1 description: The image contains 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.
TeraRecon, Inc. Michael Sosebee Director, Regulatory Affairs and Quality Assurance 4309 Emperor Boulevard, Suite 310 Durham, North Carolina 27703
Re: K243158
Trade/Device Name: TeraRecon Aorta.CT (1.1.0) Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH Dated: September 30, 2024 Received: January 7, 2025
Dear Michael Sosebee:
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 (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 available 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.
1
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review. the OS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
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 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Re"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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
2
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,
Samul for
Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
3
Indications for Use
Submission Number (if known)
Device Name
TeraRecon Aorta.CT (1.1.0)
Indications for Use (Describe)
TeraRecon Aorta.CT is intended to provide an automatic 3D segmentation and label anatomical landmarks of the Aorta. The results of TeraRecon Aorta.CT are intended to be used in conjunction with other patient information by trained professionals who are responsible for making any patient management decision per the standard of care. TeraRecon Aorta.CT is a software as a medical device (SaMD) deployed as a containerized application. The device inputs are CT Angiography with contrast DICOM images. The device outputs are DICOM result files which may be viewed utilizing DICOM-compliant systems. The device does not alter the original input data and does not provide a diagnosis.
TeraRecon Aorta.CT is indicated to generate results from aortic CT Angiography scans taken of adult patients except patients with pre-existing aortic device, bicuspid aortic valve anomaly, aortic dissection, aortic rupture, and abdominal metallic device is not specific to any gender, ethnic group, or clinical condition.
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."
4
Image /page/4/Picture/0 description: The image shows the logo for "TERARECON", with the "RA" in the middle of the word in a gradient from teal to blue. Below the logo, in a smaller font, is the text "A ConcertAI Company", also in blue. The logo is simple and modern, with a clean font and a clear message. The use of color in the logo is effective, and the overall design is professional and eye-catching.
4309 Emperor Boulevard, Suite 310 | Durham, NC 27703 Tel 650.372.1100 Fax 650.372.1101 www.terarecon.com | info@terarecon.com
TeraRecon Aorta.CT 1.1.0 510(k) Summary
Image /page/4/Picture/3 description: The image shows the alphanumeric string "K243158". The string is written in a serif font. The characters are all the same size and are evenly spaced.
510(k) Number: Prepared on:
K243158 23Jan2025
Contact Details
Device Name
Device Trade Name: Common Name: Classification Name: Regulation Number: Product Code(s):
TeraRecon Aorta.CT (1.1.0) Medical image management and processing system Automated Radiological Image Processing Software 892.2050 QIH
Legally Marketed Predicated Device
| Predicate #: | K220039 |
|---|---|
| Predicate Trade Name: | AutoSeg-H |
| Product Code: | LLZ |
Device Description Summary
The TeraRecon Aorta.CT algorithm is an image processing software device that can be deployed as a containerized application (e.g., Docker container) that runs on off-the-shelf hardware or on a cloud platform.
The device provides an automatic 3D segmentation of the aorta and landmarks of important aortic anatomy. When TeraRecon Aorta.CT results are used in external viewer devices such as TeraRecon's Intuition or Eureka Clinical Al medical devices, all the standard features offered by the external viewer are employed.
The TeraRecon Aorta.CT algorithm is not intended to replace the skill and judgment of a qualified medical practitioner and should only be used by individuals that have been trained in the software's function, capabilities, and limitations.
5
Image /page/5/Picture/0 description: The image shows the logo for TeraRecon, a ConcertAI company. The TeraRecon text is in a bold, sans-serif font, with a gradient color scheme transitioning from dark blue to light blue. Below the TeraRecon text, in a smaller font size, is the text "A ConcertAI Company", also in blue.
Intended Use/Indications for Use
TeraRecon Aorta.CT is intended to provide an automatic 3D segmentation and label anatomical landmarks of the Aorta. The results of TeraRecon Aorta. CT are intended to be used in conjunction with other patient information by trained professionals who are responsible for making any patient management decision per the standard of care. TeraRecon Aorta.CT is a software as a medical device (SaMD) deployed as a containerized application. The device inputs are CT Angiography with contrast DICOM images. The device outputs are DICOM result files which may be viewed utilizing DICOMcompliant systems. The device does not alter the original input data and does not provide a diagnosis.
TeraRecon Aorta.CT is indicated to generate results from aortic CT Angiography scans taken of adult patients except patients with pre-existing aortic device, bicuspid aortic valve anomaly, aortic dissection, aortic rupture, and abdominal metallic devices. The device is not specific to any gender, ethnic group, or clinical condition.
Indications for Use Comparison
Indications for Use (Subject Device) - TeraRecon Aorta.CT
TeraRecon Aorta.CT is intended to provide an automatic 3D segmentation and label anatomical landmarks of the Aorta. The results of TeraRecon Aorta.CT are intended to be used in conjunction with other patient information by trained professionals who are responsible for making any patient management decision per the standard of care. TeraRecon Aorta.CT is a software as a medical device (SaMD) deployed as a containerized application. The device inputs are CT Angiography with contrast DICOM images. The device outputs are DICOM result files which may be viewed utilizing DICOMcompliant systems. The device does not alter the original input data and does not provide a diagnosis.
TeraRecon Aorta.CT is indicated to generate results from aortic CT Angiography scans taken of adult patients except patients with pre-existing aortic device, bicuspid aortic valve anomaly, aortic dissection, aortic rupture, and abdominal metallic devices. The device is not specific to any gender, ethnic group, or clinical condition.
Indications for Use (Predicate Device) - AugoSeq-H, K220039
AutoSeg-H is medical imaging software that is intended to provide trained medical professionals with tools to aid them in reading, interpreting, and treatment planning. AutoSeg-H accepts DICOM compliant medical images acquired from imaging device (Computed Tomography).
AutoSeg-H provides the tools for specific analysis applications which provide custom UI, targeted measurements and reporting functions including:
-
Coronary Artery Analysis for CT coronary arteriography images: which is intended for the qualitative and quantitative analysis of coronary arteries.
-
Valve Analysis: which is intended for automatic extraction of the heart and aorta regions, automatic detection of the contour of the aorta and valves, measurement of the vicinity of the valves.
-
4-Chamber Analysis: which is intended for automatic extraction of the left atrium, left ventricle, right atrium, and right ventricle from CT.
Comparison of the Indications for Use:
The differences in the two indications for use statement do not raise different safety and effectiveness questions because the differences are summarized as additional functionality that is offered by the predicate device in comparison to the subject device. The similarities in the two indications for use statements show that the same modality, Computed Tomography DICOM images and automated segmentation of the aorta are employed to provide similar device output.
6
Image /page/6/Picture/0 description: The image contains the logo for "TERAIRECON", with the letters in a bold, sans-serif font. The color of the letters transitions from a dark blue on the left to a lighter teal on the right. Below the main logo, in a smaller font size, is the text "A ConcertAI Company", indicating that TERAIRECON is affiliated with ConcertAI.
Technological Comparison
| Subject Device | Predicate Device | ||
|---|---|---|---|
| TeraRecon Aorta.CT | AutoSeg-H | Comparison | |
| K243158 | K220039 | ||
| Indications | |||
| for Use | TeraRecon Aorta.CT is | ||
| intended to provide an | |||
| automatic 3D segmentation | |||
| and label anatomical | |||
| landmarks of the Aorta. The | |||
| results of TeraRecon | |||
| Aorta.CT are intended to be | |||
| used in conjunction with | |||
| other patient information by | |||
| trained professionals who | |||
| are responsible for making | |||
| any patient management | |||
| decision per the standard of | |||
| care. TeraRecon Aorta.CT | |||
| is a software as a medical | |||
| device (SaMD) deployed as | |||
| a containerized application. | |||
| The device inputs are CT | |||
| Angiography with contrast | |||
| DICOM images. The device | |||
| outputs are DICOM result | |||
| files which may be viewed | |||
| utilizing DICOM-compliant | |||
| systems. The device does | |||
| not alter the original input | |||
| data and does not provide a | |||
| diagnosis. |
TeraRecon Aorta.CT is
indicated to generate results
from aortic CT Angiography
scans taken of adult
patients except patients with
pre-existing aortic device,
bicuspid aortic valve
anomaly, aortic dissection,
aortic rupture, and
abdominal metallic devices.
The device is not specific to
any gender, ethnic group, or
clinical condition. | AutoSeg-H is medical
imaging software that is
intended to provide trained
medical professionals with
tools to aid them in reading,
interpreting, reporting, and
treatment planning.
AutoSeg-H accepts DICOM
compliant medical images
acquired from imaging
device (Computed
Tomography).
AutoSeg-H provides the
tools for specific analysis
applications which provide
custom UI, targeted
measurements and
reporting functions
including:
- Coronary Artery Analysis
for CT coronary
arteriography images: which
is intended for the
qualitative and quantitative
analysis of coronary
arteries. - Valve Analysis: which is
intended for automatic
extraction of the heart and
aorta regions, automatic
detection of the contour of
the aorta and valves,
measurement of the vicinity
of the valves. - 4-Chamber Analysis:
which is intended for
automatic extraction of the
left atrium, left ventricle,
right atrium, and right
ventricle from CT. | Differences:
The subject device does not include
functionality to provide professionals with
tools to read, interpret, report or treatment
plan.
The predicate device provides analysis tools
for coronary artery analysis and 4-chamber
analysis that the subject device does not
provide.
The predicate device provides measurements
of the vicinity of the cardiac valves which the
subject device does not provide.
The subject device includes landmarks of the
aorta that the predicate device does not.
The subject device indicates that it is not for
use on images of adult patients with pre-
existing aortic device, bicuspid aortic valve
anomaly, aortic dissection, aortic rupture, and
abdominal metallic devices. The predicate
device does not mention similar non use
scenarios.
Similarities:
The subject and predicate devices are both
indicated for use with Computed Tomography
(CT) DICOM images.
The subject and predicate devices are both
indicated for use on images of adult patients.
The subject and predicate devices both
provide segmentation results.
Summary:
The noted differences do not render the
subject device NSE because the identified
differences do not raise different safety and
effectiveness questions. The similarities show
that similar device output is provided based
on the same technology utilized in the
devices. |
| Modality | Computed Tomography
(CT) | Computed Tomography
(CT) | Same |
| Algorithm
Technology | Supervised deep learning-based algorithms | Deep learning-based
algorithms | Same |
| | Subject Device
TeraRecon Aorta.CT
K243158 | Predicate Device
AutoSeg-H
K220039 | Comparison |
| Device
Outputs | DICOM Seg and DICOM
CoF | Results in form of 2D
Images, 3D Images,
Information and Results | Differences:
The predicate device outputs measurement
results that are not available in the subject
device.
Similarities:
Both the subject and predicate devices
output results following the DICOM
standard.
Summary:
The noted differences do not render the
subject device NSE because the identified
differences do not raise different safety and
effectiveness questions. The similarities
show that similar device output is provided
based on the same technology utilized in
the devices. |
| Installation
Methods | Application installed on a
computer | Application installed on a
computer | Same |
7
Image /page/7/Picture/0 description: The image shows the logo for TeraRecon, a ConcertAI company. The logo consists of the word "TERARECON" in a bold, sans-serif font. The "A" in TeraRecon is a gradient of green and blue. Below the company name is the text "A ConcertAI Company" in a smaller, lighter font.
Non-Clinical and/or Clinical Tests Summary & Conclusions
The TeraRecon Aorta.CT device underwent a retrospective cohort study where ground truth was established and compared to the output of the device as described below:
At least 50% of the ground truth data is of US patients from 3 geographical regions in the United States. Each ground truth scan will also pass through the subject device. 170 adult patients are included in the cohort meeting the following inclusion criteria: Patients must be 18 or older, must have had a CT Angiography scan for cardiac or CT Angiographic scan for abdomen or for both covering cardiac and abdominal aorta, and the validation data should be enriched with data from patients with clinical diagnosis of aortic dilation/aneurysm and/or aortic valve disease.
The following results will be compared between the ground truth and device results, Lumen Segmentation: Comparison of Aorta Jumen segmentation results from the medical device to aorta lumen segmentation from ground truth. Aorta wall segmentation: The test will compare the results from ground truth to medical device output representing for aorta wall to wall segmentation. This aorta wall to wall segmentation includes aorta lumen + wall for the comparison. The lumen and aorta wall (including lumen) segmentations are important for extracting measurements that can be used by the clinicians for procedure planning. Landmarking results: The 22 anatomical landmarks for aorta will be compared from the device output to the ground truth.
For each CTA scan we will record aortic lumen segmentation DICE score and aorta segmentation DICE score for the subject device vs each of the ground truths. Our acceptance criteria for lumen and aorta segmentation accuracy are for average DICE score >= 80%.
For each CTA scan, we will also examine the subject device landmarking locations compared to each ground truth annotation. The Common Left and Right Iliac Arteries, Left and Right Femoral Arteries (4 landmarks) will be evaluated by whether or not the subject device correctly identified the vessel in accordance with ground truth. In a typical clinical workflow, these landmarks need only identify any point
8
Image /page/8/Picture/0 description: The image shows the logo for TeraRecon, a ConcertAI company. The logo is in a dark blue color, with the letters "TERA" in a solid, bold font. The letters "RECON" are in a gradient of blue and green, with the "R" being the darkest blue and the "N" being the lightest green. Below the logo, in a smaller font, is the text "A ConcertAI Company".
in the center of the vessel, thus the identification of the overall anatomic location is of greatest importance, rather than exact location.
The remaining landmarks except for the aortic bifurcation (17 landmarks) will be assessed using Euclidean distance between ground truth annotation and medical device output locations. We will determine whether the Euclidean distance is within 5mm.
Finally, for the aortic bifurcation (1 landmark), the exact location is not clearly defined, and a general area is sufficient in typical clinical practice. We will determine whether the Euclidean distance is within 2cm compared to ground truth.
Our acceptance criteria for the landmarks are whether each of the 22 landmarks independently pass the class-specific criteria in 80% of the cases. To provide evidence of precision, we will assess whether the lower bound of the 95% exact binomial confidence interval (binom.confint from the R power library) is greater than or equal to 70% (~ acceptance level - 10%). A sample size of 100 CTA scans was chosen since during power simulations of 10.000 simulated runs, an actual case-wise pass rate of 90% resulted in power of 81% to pass all 24 tests after accounting for 30% loss of cases due to some landmarks being outside of field of view. Power calculation code displayed in appendix.
Following execution of the study, it was determined that the TeraRecon Aorta.CT device passed the acceptance criteria established in the study based on the following results:
For testing the lumen and aorta segmentation, we selected 170 studies which matched the inclusion exclusion criteria. The final manufacturer distribution was 77 Siemens, 33 GE, 35 Philips, and 25 Canon. All collected datasets were checked and were found acceptable to use by a US board certified radiologist, who is currently practicing in the United States and reads similar scans.
Our acceptance criteria for lumen and segmentation is to confirm a mean DICE score of >=80%. The lumen segmentation results passed with a mean DICE score of 88%. The aorta segmentation results passed with a mean DICE score of 90%.
For testing the aorta landmarking, we selected 170 studies which matched the inclusion criteria, but we found that the number of landmarks outside the field of view was higher than expected: 40-45% actual vs 30% expected. The annotators were unable to provide annotations for these images, and we had a range of between 55-60 annotatable landmarks per landmark target. Additionally, sections of many images contained image artifacts which made annotation impossible. These artifacts included motion artifacts, occluded vessels, and lack of contrast in the aortic arch and heart. We increased the number of studies to achieve our target of 70 annotatable landmarks, according to our power calculations. We added 29 additional studies to the initial total. After adding 29 supplemental studies, we averaged 73 annotatable landmarks per landmark target with a minimum of 63. Thus, we stopped increasing the sample size.
Our acceptance is to assess whether each of the 22 landmarks independently pass evaluation in 80% of the cases. To provide evidence of precision we assess whether the lower bound of the 95% exact binomial confidence interval (binom.confint from the R power library) is greater than or equal to 70% (~ acceptance level - 10%). All landmarks passed the acceptance criteria, all 95% confidence intervals were at least 70%.
The test results support the conclusion that the TeraRecon Aorta.CT device is as safe, as effective and performs as well as the predicate device cleared under K220039.