HeartSee K171303 Software for cardiac positron emission tomography (PET) is indicated for determining regional and global absolute rest and stress myocardial perfusion in cc/min/g, Coronary Flow Reserve and their combination into the Coronary Flow Capacity (CFC) Map in patients with suspected or known coronary artery disease (CAD) in order to assist clinical interpretation of PET perfusion images by quantification of their severity.

HeartSee K171303 is intended for use by trained professionals, such as nuclear medicine or nuclear cardiology physicians, or cardiologists with appropriate training and certification. The clinician remains ultimately responsible for the final assessment and diagnosis based on standard practices, clinical judgment and interpretation of PET images or quantitative data.

Device Description

HeartSee K171303 is a software tool for cardiac positron emission tomography (PET) for determining regional and global absolute rest and stress myocardial perfusion in cc/min/q, Coronary Flow Reserve and their combination into the Coronary Flow Capacity (CFC) Map for facilitating the interpretation of PET perfusion images in patients with suspected ot known coronary artery disease. HeartSee K171303 is intended for use by trained professionals, such as nuclear technicians, nuclear medicine or nuclear cardiology physicians, or cardiologists with appropriate training and certification.

HeartSee contains two fundamental components. First, the software imports cardiac PET images in DICOM format from PET scanners with DICOM output. These images are reoriented to cardiac axes to produce standard tomographic and topographic displays of relative uptake. Second, the K171303 software quantifies absolute rest and stress myocardial perfusion per unit tissue (cc/min/g), Coronary Flow Reserve (CFR) as the stress/rest perfusion ratio and the Coronary Flow Capacity combining CFR and stress perfusion, all on a pixel basis for regional and global values. Archiving output data is supported for clinical diagnostics, quality control and research.

AI/ML Overview

Here's a breakdown of the requested information based on the provided document:

Acceptance Criteria and Device Performance Study

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by demonstrating that K171303 performs "identically" to the predicate device (K143664) for certain metrics and "better" for others.

Acceptance Criteria / Performance Metric	Predicate Device (K143664) Performance	Device (K171303) Performance	Result (K171303 vs. K143664)
Quantitative Measurements:
Rest Perfusion (cc/min/g)	N/A (implicit)	Values within two decimal places of K143664	Identical
Stress Perfusion (cc/min/g)	N/A (implicit)	Values within two decimal places of K143664	Identical
Coronary Flow Reserve (CFR)	N/A (implicit)	Values within two decimal places of K143664	Identical
Mean values and standard deviations for Rest Perfusion, Stress Perfusion, and CFR	N/A (implicit)	Identical to K143664	Identical
Correlation between K171303 and K143664 for Rest-Stress perfusion and CFR	N/A (implicit)	R = 1.0, P < 1 x 10^-16	Tightly correlated
Clinical Association (Risk Stratification):
Association with Major Adverse Coronary Events (MACE)	Significant (by Cox multivariate analysis)	Significant (by Cox multivariate analysis)	Equally well
Association with higher MACE than CFR or stress perfusion alone	Not significant (implicit)	Significant	Better (higher MACE association)
Association with reduced death and myocardial infarction after revascularization	Not significant	Significant	Better (significant association)

2. Sample size used for the test set and the data provenance

Sample Size: 4188 rest and 4188 stress PET perfusion scans.
Data Provenance: The document does not specify the country of origin of the data. It also does not explicitly state if the data was retrospective or prospective. However, given that the study is comparing performance of two software versions on an existing dataset, it's highly likely to be retrospective analysis of previously acquired patient scans.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document does not specify the number of experts used to establish the ground truth or their qualifications. The study primarily focuses on the algorithmic output against its predicate and clinical association, rather than expert-derived ground truth for individual scan features.

4. Adjudication method for the test set

The document does not describe an adjudication method for the test set. The comparison is between the outputs of two software versions (K171303 and K143664) and their statistical association with clinical outcomes, not against a consensus-based ground truth adjudicated by experts.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

A multi-reader multi-case (MRMC) comparative effectiveness study focused on human reader improvement with and without AI assistance was not done or reported in this summary. The study reported here is a direct comparison of two algorithmic software versions (K171303 vs. K143664) and their association with clinical outcomes.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, a standalone (algorithm-only) performance study was done. The entire summary describes the performance of the K171303 software in processing PET scans and generating quantitative values and maps, implicitly comparing it to the K143664 software, also in a standalone manner. The clinical associations are derived from these algorithmic outputs without explicitly evaluating human-in-the-loop performance.

7. The type of ground truth used

The ground truth used for performance evaluation appears to be:

Algorithmic equivalence: For the quantitative measurements (perfusion, CFR), the ground truth for K171303's accuracy is its identical output to the predicate K143664.
Outcomes data: For the clinical associations (MACE, reduced death and MI after revascularization), the ground truth is the actual patient outcomes.

8. The sample size for the training set

The document does not specify the sample size for the training set. It describes a "study" involving the analysis of 4188 rest and 4188 stress PET perfusion scans, which serves as the test set for comparison between K171303 and K143664. It is not clear if these scans were also part of a training set, or if an entirely separate training set was used for developing the software versions. Given the explanation of K171303 being "identical" in code to K143664 with the addition of the CFC map, it's plausible that the core algorithms were developed using separate data, and these 4188 scans validate the outputs and the new CFC map's utility.

9. How the ground truth for the training set was established

Since the document does not specify the training set sample size, it also does not detail how the ground truth for any training set was established.

Summary

{0}------------------------------------------------

DEPARTMENT OF HEALTH & HUMAN SERVICES

Public Health Service

Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002

September 22, 2017

University of Texas Medical School at Houston, Texas % K. Lance Gould, M.D. Professor of Cardiovascular Medicine 6431 Fannin St. Room 4.256 MSB HOUSTON TX 77030

Re: K171303

Trade/Device Name: Optional Screen Displays for HeartSee Cardiac P.E.T Processing Software Regulation Number: 21 CFR 892.1200 Regulation Name: Emission Computed Tomography System Regulatory Class: Class II Product Code: KPS Dated: September 19, 2017 Received: September 20, 2017

Dear K. Gould:

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. 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

{1}------------------------------------------------

Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical devicerelated adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Industry and Consumer Education (DICE) at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. 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

http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Industry and Consumer Education (DICE) at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.

Sincerely.

For

Robert A. Ochs. Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known)

K171303

Device Name

Optional Screen Displays For HeartSee Cardiac P.E.T. Processing Software 9/22/2017

Indications for Use (Describe)

Type of Use (Select one or both, as applicable) X Prescription Use (Part 21 CFR 801 Subpart D) D Over-The-Counter Use (21 CFR 801 Subpart C)

PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON A SEPARATE PAGE IF NEEDED.

FOR FDA USE ONLY

Concurrence of Center for Devices and Radiological Health (CDRH) (Signature)

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."

FORM FDA 3881 (1114)

Page 1 of 2

PSC Publishing Services (301) 443-6740

{3}------------------------------------------------

5. 510(k) Summary K171303

revision of 9/22/2017

Owner/Contact:

K. Lance Gould, M.D. Professor of Cardiovascular Medicine University of Texas Medical School at Houston 6431 Fannin St., Room MSB 4.256 Houston, TX 77030 Phone 713-500-6611 Fax 713-500-6615 Email K.Lance.Gould@uth.tmc.edu

Date of preparation: September 19, 2017

Device trade name: Optional Screen Displays For HeartSee Cardiac P.E.T. Processing Software

Common name: Cardiac Positron Emission Tomography (PET) Analysis Software

Classification names: Requlation name: Emission computed tomography system. Regulation number: 21 CFR 892.1200. Regulatory code: Class II. Product Code: KPS.

Devices claimed for equivalence: K143664

Device description:

Indications for use:

HeartSee K171303 Software for cardiac positron emission tomography (PET) is indicated for determining reqional and global absolute rest and stress myocardial perfusion in cc/min/g, Coronary Flow Reserve and their combination into the Coronary Flow Capacity (CFC) Map in patients with suspected or known coronary artery disease (CAD) in order to assist clinical interpretation of PET perfusion images by quantification of their severity. HeartSee K171303 is intended for use by trained professionals, such as nuclear technicians, nuclear medicine or nuclear cardiology physicians, or cardiologists with appropriate training

{4}------------------------------------------------

and certification. The clinician remains ultimately responsible for the final assessment and diagnosis based on standard practices, clinical judgment and interpretation of PET images or quantitative data.

Summary of technological characteristics of your device compared to predicate

device: K171303 and K143664 are software tools using identical standard, industrial computing hardware and applications The code in the software package K171303 is identical to K143664 including determination of quantitative myocardial perfusion in cc/min/g and Coronary Flow Reserve (CFR) and their displays except for the addition of the Coronary Flow Capacity (CFC) map to K171303.

In K171303, Coronary Flow Capacity combines CFR and stress perfusion by plotting their values for each pixel on a clinically defined, objective, color coded plot of combined ranges of values that assigns a color to that pixel for the corresponding range of combined values of CFR and stress perfusion. That color-coded pixel is then back projected into its original coordinate position in the topographic map. All pixels of the LV image are correspondingly color coded for ranges of combined CFR and stress perfusion for each pixel thereby producing a single four quadrant left ventricular map of the combined CFR-stress perfusion ranges. By incorporating all the stress perfusion and CFR data into objectively coded ranges on a pixel basis, the CFC map accounts for global and regional heterogeneity, objectively simplifies complex data for optimal clinical interpretation and associates with major adverse coronary events (MACE) and decreased death and myocardial infarction after revascularization better than CFR or stress flow alone in K143664.

Summary of performance data:

In 4188 rest and 4188 stress PET perfusion scans were analyzed by K143664 and separately by K171303. Rest and stress perfusion values in cc/min/g and CFR using K171303 were identical within two decimal places to the values using K143664, as were the mean values and their standard deviations. Rest-stress perfusion and CFR using K171303 and 143664 were tightly correlated with R = 1.0 and P < 1 x 10 -16

By Cox multivariate analysis, CFR and separately stress perfusion associate significantly with maior adverse coronary events (MACE) equally well for K171303 and K143664. However, the CFC map of K171303 associates significantly with higher MACE than either CFR or stress perfusion alone and also associates significantly with reduced death and myocardial infarction after revascularization. In contrast, CFR and stress perfusion alone in K143663 does not have a significant association with reduced death and myocardial infarction after revascularization.

Conclusions drawn from the performance data that demonstrate that the device is as safe, as effective, and performs as well as or better than the predicate device: K171303 performs identically to K143664 for determining rest and stress perfusion in cc/min/q, CFR and for significant associations with MACE. However, the CFC map of K171303 performs better for risk stratification than K143664 by its association with higher MACE than CFR or stress perfusion alone in K143664. As an additional superiority for risk stratification, K171303 associates with reduced death and myocardial infarction after revascularization that is not seen for CFR or stress perfusion alone in K143664. Therefore, K171303 has the same functionality as K143664 but performs better than K143664 for risk stratification of patients with suspected or known CAD.

{5}------------------------------------------------

Regulation Number and Section

§ 892.1200 Emission computed tomography system.

(a)
Identification. An emission computed tomography system is a device intended to detect the location and distribution of gamma ray- and positron-emitting radionuclides in the body and produce cross-sectional images through computer reconstruction of the data. This generic type of device may include signal analysis and display equipment, patient and equipment supports, radionuclide anatomical markers, component parts, and accessories.(b)
Classification. Class II.