The Emory Cardiac Toolbox™ (CEqual®, EGS™) 2.6 software program should be used for the quantification of myocardial perfusion (CEqual®), for the display of wall motion for the quantification of left-ventricular function parameters from gated Tc99m gPECT & and quantification of lell-venthcaller fanonen for the 3D alignment of coronary artery PET myocarulal perfusion studies (LES - ); and ter the left ventricular 3D epicardial surface.

Device Description

The Emory Cardiac Toolbox™ 2.6 is used to display gated wall motion and for quantifying The Emory Strends Tronular perfusion and function from gated SPECT & PET myocardial paramours of ices. These parameters are: perfusion, ejection fraction, end-diastolic volume, end-systolic volume, myocardial mass and transient ischemic dilatation (TID). In addition, the program offers the capability of providing the following diagnostic information: computer the program of or are riog, prognostic information, expert system image interpretation, and patient specific 3D coronary overlay. The program can also be used for the 3D alignment of coronary artery models from CT coronary angiography onto the left ventricular 3D of coronaly aftery models from of corenary any in the IDL operating systems which epicalular sunace. "This program was avversions on any nuclear medicine computer systems to The supports IDL and the Aladdin (General Electric) software development environment. The Supports IDL and the Riadain (Gonoral Elookie) Sownload of output is required and manual processing capability is provided.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study information for the Emory Cardiac Toolbox™ 2.6, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state pre-defined acceptance criteria with numerical targets. Instead, it describes a series of validation studies with their corresponding patient numbers. The "device performance" in this context refers to the successful evaluation and validation of various algorithms, implying they met the implicit criteria for functionality and accuracy.

Feature/Parameter Tested	Number of Patients/Cases	Study Type/Purpose	Reported Performance (Implicit Acceptance)
Left ventricular functional parameter calculations	217 (initial program, in-house) & 80 (multicenter)	Phantom & Multicenter Trial Validation (Accuracy)	Successfully evaluated and validated.
Computer assisted visual scoring	20 (patients)	Validation	Successfully evaluated.
Prognosis program	504 (patients)	Validation	Successfully evaluated.
Expert system	461 (patients)	Validation	Successfully evaluated.
Coronary fusion algorithms	9 (patients)	Validation	Successfully evaluated.
Normal limits (Emory Cardiac Toolbox™ 2.1)	176 (patients)	Validation	Successfully completed.
PET tools for assessment of perfusion – metabolism match-mismatch	90 (patients)	Validation	Successfully completed.
N-13-ammonia normal limits	144 (patients)	Validation	Successfully completed.
Alignment of 3D models of coronary arteries onto the left ventricular 3D epicardial surface	Not explicitly given specific patient count for this specific validation, but "successfully completed"	Validation	Successfully completed.

2. Sample Sizes and Data Provenance

Test Set Sample Sizes:
- Left ventricular functional parameter calculations: 217 (in-house) and 80 (multicenter).
- Computer assisted visual scoring: 20 patients.
- Prognosis program: 504 patients.
- Expert system: 461 patients.
- Coronary fusion algorithms: 9 patients.
- Normal limits (Emory Cardiac Toolbox™ 2.1): 176 patients.
- PET tools for perfusion-metabolism: 90 patients.
- N-13-ammonia normal limits: 144 patients.
- Alignment of 3D models of coronary arteries: Not explicitly stated as a separate patient cohort, but implied to be validated with existing data or a subset.
Data Provenance: The document mentions "in-house" validation and a "multicenter trial validation," indicating that data was gathered from more than one institution. Specific countries of origin are not detailed, nor is it explicitly stated whether the data was retrospective or prospective, though multicenter trials are often prospective or a mix.

3. Number of Experts and Qualifications for Ground Truth

The document does not specify the number of experts used to establish ground truth or their qualifications. It mentions "computer assisted visual scoring," implying human visual interpretation, but the details of the ground truth establishment for the various functional parameter calculations and algorithms are not provided.

4. Adjudication Method

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for establishing ground truth on the test sets.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

A MRMC comparative effectiveness study that quantitatively assesses how much human readers improve with AI vs. without AI assistance is not described in the provided text. The document refers to the program as "merely a display and alignment and processing program to aid in the standard visual analysis" and states it is "not meant to replace or eliminate the recall of the patients' clinical and diagnostic information." This suggests the device is considered an aid rather than a replacement, but specific efficacy over human-only reading is not quantified.

6. Standalone (Algorithm Only) Performance Study

Yes, standalone (algorithm only) performance was done. The description of the validation studies for "left ventricular functional parameter calculations," "computer assisted visual scoring," "prognosis program," "expert system," "coronary fusion algorithms," "normal limits," "PET tools," and "N-13-ammonia normal limits" indicates that the algorithms within the Toolbox were evaluated for their accuracy and functionality. The general wording of "successfully evaluated" for these specific functions implies their standalone performance was assessed.

7. Type of Ground Truth Used

The type of ground truth used is not explicitly detailed for each study. However, given the context of myocardial perfusion, ejection fraction, ventricular volumes, and coronary artery models, it's highly probable that a combination of:

Expert Consensus: For visual scoring, qualitative interpretation, and possibly for establishing "normal limits."
Reference Standards/Clinical Data: For validating quantitative measurements (e.g., ejection fraction, volumes) against established methods or clinical outcomes, although this is not explicitly stated as "outcomes data."
Pathology: Not directly mentioned, but could be a component for certain diagnoses.

The statement that the program itself is "not perfect, and will be accompanied with some false positive and false negative results" suggests that there was a ground truth against which these "false positives and negatives" were defined.

8. Sample Size for the Training Set

The document does not explicitly state the sample size used for the training set of the algorithms. The numbers provided (217, 80, 20, 504, 461, 9, 176, 90, 144 patients) relate to validation studies. For a device cleared in 2004, common practice at the time often involved using the same data sets (or subsets thereof) for both development/training and validation, or it might not have been standard to strictly delineate "training" and "test" sets in the same way as modern machine learning development.

9. How Ground Truth for the Training Set Was Established

Since an explicit training set size isn't provided, the method for establishing its ground truth is also not detailed. However, it's reasonable to infer that if a training set were used, its ground truth would have been established through methodologies similar to those used for validation sets (e.g., expert consensus, reference standards, and clinical data), but these details are not present in the provided text.

Summary

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

Kotori4

JAN : 0 2004

ITEM G

510(k) SUMMARY

Safety and Effectiveness

1. Medical Device Establishment:

Syntermed, Inc. Registration No. 1066019 Owner Operator I.D. 9041128 Device Requlation Number: 892.1200 Product Code: KPS Classification Panel: Radiology Voice: (714) 281-1256, FAX: (714) 281-1290 Contact person: Kenneth F. Van Train Syntermed, Inc. Address: Tower Place Center 3340 Peachtree Road, NE Suite 1800 Atlanta, GA 30326 Date Summary Prepared: December 30, 2003

2. Medical Device:

Emory Cardiac Toolbox™ 2.6 - Display and Processing program for gated SPECT & PET myocardial perfusion studies executing on nuclear medicine computer systems.

Classification Name - System, Tomography, Computed, Emission

Medical Device Equivalence:

Emory Cardiac Toolbox™ (CEqual®, EGS™) Version 2.1, Ref. 510(k) #: K014033.

4. Device Description:

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

of coronary artery models from CT coronary angiography onto the left ventricular 3D of coronaly aftery models from of corenary any in the IDL operating systems which epicalular sunace. "This program was avversions on any nuclear medicine computer systems to The supports IDL and the Aladdin (General Electric) software development environment. The Supports IDL and the Riadain (Gonoral Elookie) Sownload of output is required and manual processing capability is provided.

5. Intended Use and Potential Adverse Effect on Health:

The intended use of this program was to provide the physician with a program which would The intended use of this program was analysis of the myocardial perfusion, display wall allow inin to uctermine quantitutio of ejection fraction and ventricular volumes from his motion and delemine measuromonto or ojostion frasion study, obtain visual interpretation patterns gated of LOT & F & F nryott system interpretation, and coronary overlay and scores, program images. This program serves merely as a display and alignment onlo "SD" pendolor" interpretation of a patients' study. It was not processing program to alla in the standard visual analysis of the gated SPECT & PET meant to Teplace of Climmato the teall of the patients' clinical and diagnostic information, study. The priysician should integrate and of the pullity control images, visual interpretation of including his find the gated tomographic images, and quantitative results, prior to making his final the gated toniographio integory and one interpretation: - This compronential with some false positive and false negative results. IS not perfect, and will be account.or rogram can be found in the multicenter trial results The Uxpotod Gouraby of Cardiac Toolbox™ (CEqual®, EGS™) Version Ilsted in the article by Vansant of all Enery Cardide 510(k) #: K014033). The accuracy for modifications in version 2.6 for the Ammonia normal limit and alignment of 3D models of modifications in Vorbion 2.0 for coronary angiography onto the left ventricular 3D coronary vessels obtained from OF corenary anglesal and of this 510(i) submission.
epicardial surface can be found in Item F (Testing & Validation) of this 510 (in the epicalular sufface cur be loand in kom - (1 common The physician should be aware of this program has no direct adverse effect on health since This marinterpretation. Horolers, at the information which the physician will utilize for his the results represent only a part of the many of the study lies with the physician.

6. Marketing History:

There have been several medical device gated SPECT programs marketed in the There nave been several moundal as those performed by the Emory Cardiac Tool past which periom omiliar fancions to to all used for the purpose of displaying wall box 2.0 and deriving functional parameters for the diagnostic interpretation by a motion and 'dening Tundional' param' (1) 26 provides a program which executes in priyalian. The Emory ourailers of we believe is substantially equivalent to the iDE operainly of the Emory Cardiac Tool Box™ 2.1 (CEqual®, EGS™), our previous vorsion of the there have been no safety problems with the Emory No 1400. To our 11, 20 or 2.1 (CEqual®, EGS™) program which has been in the marketplace since July 20, 1999.

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

7. Conclusions:

The safety of this program has been determined through the various stages of
the safety of this program in the intellished sign, acquinq dobugging testing software development which included the initial design, coding, debugging, testing, software development which included the initial program, Emory Cardias Toolbox™
and validation. The effectiveness of the initial program, Emory Cardias in-bouse and validation. The enectivelless of the interess of the increase in-house 2.0, has been established in phantom of left vehicular functional parameter
trial validations which included an evaluation of left vehicler consisting of 80 that validations which included an overadion of the validation consisting of 80
calculations in 217 patients, and in a multicenter trial validation of 80 calculations in 217 patients, and in a manisantoning, progrosis, expert system,
patients. In addition, the computer assisted visual scoring, program, and and a patients. In addition, the computer assisted in 20, 504, 461, and 9
and coronary fusion algorithms were successfully evaluated in 20, 504, 401, 21 and coronary idsion algonthini wo croller of the Emory Cardiac Toolbox™
patients respectively. Additional validation of the Emore Limite (n=176) and valida 2.1 patients respectively. Additional validation -8 (normal limits (n=176) and validation program for development and validation of Research of Resolumn match-mismatch (n=90) were
of PET tools for assessment of perfusion – metabolism match-mismator (n of PET tools for assessment of pendsion - The Emory Cardiac Toolbox™ 2.6 program for successfully completed. Validation of the Emery of 144) and validation of
development and validation of N-13-ammonia normal virus is opicardial development and validation of N-13 uninning no the left venting in the left venting in the left venting & the alignment intentou for SD Of coronary and see listed in Item F, Testing & We contend that the method employed for the development and Validation. Validation validation of the N-13-anmonial and SD anghinone of this medical display softwares onto The Tell Venthedial JD Episaralar Satety and effectiveness. In program, Enory Cardiac Toolbox - - E.S, Rave Program Land Cardially equivalent to our our opinion the Emory Ourdra Toolbox™ 2.1 (CEqual®, EGS™) which has previous version of the Emory Cardiac Toolbox™ 2.6 is intended for the been cleared of marketing. The Elitory Gurdias for and of 3D CT coronary same purpose along with the additional parpose and raises no new issues of safety or effectiveness.

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

Image /page/3/Picture/1 description: The image contains the words "Public Health Service" in a simple, sans-serif font. The text is arranged on a single line, with each word clearly legible. The overall impression is clean and straightforward, suggesting an official or institutional context.

Food and Drug Administration 9200 Corporate Boulevard Rockville MD 20850

JAN 3 0 2004

Syntermed, Inc. % Ms. Elizabeth Drew Reviewer Medical Device Services Underwriters Laboratories, Inc. 1655 Scott Blvd. SANTA CLARA CA 95050

Re: K040141 Trade/Device Name: Emory Cardiac Toolbox™ 2.6 Regulation Number: 21 CFR 892.1200 Regulation Name: Emission computed tomography system Regulatory Class: II Product Code: 90 KPS Dated: January 20, 2004 Received: January 22, 2004

Dear Ms. Drew:

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.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to such 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 801); 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.

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

Page 2

This letter will allow you to begin marketing your device as described in your Section 510(k) I ms letter will and with you to begin manies of your device of your device to a legally premarket notinoution: "The eleman a classification for your device and thus, permits your device to proceed to the market.

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please If you dosn't specific at me of the following numbers, based on the regulation number at the top of the letter:

8xx. 1xxx	(301) 594-4591
876.2xxx, 3xxx, 4xxx, 5xxx	(301) 594-4616
884.2xxx, 3xxx, 4xxx, 5xxx, 6xxx	(301) 594-4616
892.2xxx, 3xxx, 4xxx, 5xxx	(301) 594-4654
Other	(301) 594-4692

Additionally, for questions on the promotion and advertising of your device, please contact the Additional Compliance at (301) 594-4639. Also, please note the regulation entitled, "Misbranding Other of other premarket notification" (21CFR Part 807.97) you may obtain. Other general of received to premation on your the Act may be obtained from the Division of Small manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 443-6597 or at its Internet address http://www.fda.gov/cdrh/dsma/dsmamain.html.

Sincerely yours,

Nancy C. Brogdon

Nancy C. Brogdon Director, Division of Reproductive, Abdominal and Radiological Devices Office of Device Evaluation Center for Devices and Radiological Health

Enclosure

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

Page / of _

510(k) Number (if known): K04014

Emory Cardiac Toolbox 2.6 Executing on Nuclear Medicine Computers Device Name:

Indications For Use:

(PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON ANOTHER PAGE IF NEEDED)

Concurrence of CDRH, Office of Device Evaluation (ODE)

Prescription Use
(Per 21 CFR 801.109)

Over-The-Counter Use

(Optional Forms 1-2-96)

David R. Legum

(Division Sign-Off) (Division Sign Only)
Division of Reproductive, Abdominal, and Radiological Devices 510(k) Number -

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.