TruSPECT is intended for acceptance, display, storage, and processing of images for detection of radioisotope tracer uptakes in the patient's body. The device using various processing modes supported by the various clinical applications and various features designed to enhance image quality. The emission computerized tomography data can be coupled with registered and/or fused CT/MR scans and with physiological signals in order to depict, localize, and/or quantify the distribution of radionuclide tracers and anatomical structures in scanned body tissue for clinical diagnostic purposes. The acquired tomographic image may undergo emission-based attenuation correction.

Visualization tools include segmentation, colour coding, and polar maps. Analysis tools include Quantitative Perfusion SPECT (QPS), Quantitative Gated SPECT (QGS) and Quantitative Blood Pool Gated SPECT (QBS) measurements, Multi Gated Acquisition (MUGA) and Heart-to-Mediastinum activity ratio (H/M).

The system also includes reporting tools for formatting findings and user selected areas of interest. It is capable of processing and displaying the acquired in traditional formats, as well as in three-dimensional renderings, and in various forms of animated sequences, showing kinetic attributes of the imaged organs.

TruSPECT is based on Windows operating system. Due to special customer requirements and the clinical focus the TruSPECT can be configured with different combinations of Windows OS based software options and clinical applications which are intended to assist the physician in diagnosis and/or treatment planning. This includes commercially available post-processing software packages.

TruSPECT is a processing workstation primarily intended for, but not limited to cardiac application can be integrated with the D-SPECT cardiac scanner system or used as a standalone post-processing station.

Device Description

The TruSPECT is a Nuclear Medicine Software system designed for nuclear medicine images' post processing and further review procedures for detection of the radioisotope tracer uptake in the patient's body. Thus, using a variety of post processing features oriented to specific clinical applications.

SUMO Workflow enables visual evaluation and assessment of the sympathetic innervation system of the heart by quantification of uptake ratios between regions of interest, identifying discreet uptake areas of AdreViewtm (lobenguane 123 Injection) or similar agents within the heart. The results generated by the SUMO workflow can be displayed on the D-SPECT processing station and additionally, can be exported to EP systems. It can also be used by the physician to aid in ablation treatment planning by electrophysiologists.

D-SPECT Dynamic CFR is a workflow for visualization, and quantification of specific areas of attention. It is capable of processing and displaying the acquired information in traditional formats, as well as in three-dimensional renderings, and in various forms of animated sequences, showing kinetic attributes of the imaged organs providing quantitative blood flow measurements of SPECT images. The application provides visualization and measurement tools for both qualitative and quantitative visualization and input data evaluation. It provides automated and manual tools for orientation and segmentation of the myocardium. The software calculates myocardial blood flow measurements and provides tools, such as a database comparison workflow, to the clinician to evaluate these outcomes.

TruSPECT CT based Attenuation Correction (CTAC) is an application that removes soft tissue artifacts from SPECT images. The goal is to minimize the impact of attenuation to provide more consistent and reliable reading images. The CT Attenuation Correction (CTAC) uses a second form of imaging (CT) to develop a density map of each patient and correct the SPECT image accordingly.

TruCorr enhances the user's ability to visualize the acquired information (by way of a single clear image) - thus optimizing what would otherwise be a disjointed visual comparison. It is an Emission Based attenuation correction application using the deep learning model which was trained to directly estimate attenuation corrected SPECT images from non-attenuation corrected ones without the use of any anatomical images.

AI/ML Overview

This document describes the TruSPECT Radiological Image Processing Station (K212230), which is a modification to the D-SPECT® Processing and Reviewing Workstation (K160120). The key modification is the TruCorr application, an image attenuation correction method that integrates pre-trained neural networks in the iteration reconstruction process.

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

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in a tabular format. However, it mentions that the "performance testing for the AI-based algorithm for iteration reconstruction process to control image attenuation have been evaluated and demonstrates algorithm's performance and uses test datasets of representative clinical exams." The evaluation method involved a 5-point Likert scale by experts.

Acceptance Criteria (Implied)	Reported Device Performance
Qualitative Assessment of Image Attenuation Correction: The AI-based algorithm (TruCorr) should produce attenuation-corrected SPECT images that are deemed acceptable by expert reviewers.	"The NM Physicists and Physicians... reviewed the results and scored them using a 5-point Likert scale." The "scientific methods used to evaluate the effectiveness of proposed application are acceptable and support the determination of substantial equivalence."
Clinical Efficacy (Implied): Improve the user's ability to visualize acquired information by optimizing the visual comparison of images.	"TruCorr enhances the user's ability to visualize the acquired information (by way of a single clear image) - thus optimizing what would otherwise be a disjointed visual comparison."

2. Sample Size Used for the Test Set and Data Provenance

Sample Size: The document refers to "test datasets of representative clinical exams" but does not specify the exact number of cases or images.
Data Provenance: Not explicitly stated. It mentions "representative clinical exams," suggesting real-world patient data, but the country of origin or whether it was retrospective or prospective is not provided.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

Number of Experts: Not explicitly stated, but it mentions "experienced NM Physicists and Physicians." The plural form indicates more than one expert.
Qualifications of Experts: "experienced NM Physicists and Physicians." No specific years of experience are provided.

4. Adjudication Method for the Test Set

The document states that "experienced NM Physicists and Physicians... were used as ground truth. The NM Physicists and Physicians also performed the algorithm evaluation. They reviewed the results and scored them using a 5-point Likert scale." This implies an expert-driven evaluation, but a specific adjudication method like "2+1" or "3+1" is not mentioned. It could be that experts individually scored the images, or they reached a consensus for the ground truth and then individually evaluated the algorithm's output.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

There is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being done to quantify the improvement of human readers with AI assistance versus without AI assistance. The evaluation focused on the algorithm's standalone performance as assessed by experts.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, a standalone performance evaluation was done. The "performance testing for the AI-based algorithm... have been evaluated" and "NM Physicists and Physicians also performed the algorithm evaluation. They reviewed the results and scored them..." This indicates the algorithm's output was evaluated directly.

7. The Type of Ground Truth Used

Expert Consensus/Manual Assessment: The ground truth for the test set was established by "experienced NM Physicists and Physicians" who "manually accessed" the clinical exams.

8. The Sample Size for the Training Set

The document states that the TruCorr deep learning model "was trained to directly estimate attenuation corrected SPECT images from non-attenuation corrected ones without the use of any anatomical images." However, the sample size for the training set is not provided. It mentions the use of "nonadaptive machine learning algorithms trained with clinical and/or artificial data," suggesting a combination of real and synthetic data.

9. How the Ground Truth for the Training Set Was Established

The document implies that the "pre-trained neural networks" for TruCorr were trained to estimate "attenuation corrected SPECT images from non-attenuation corrected ones." While it doesn't explicitly state how the "ground truth" for the training set was established, for a deep learning model to generate "attenuation corrected SPECT images," the training data would typically consist of pairs of non-attenuated and corresponding accurately attenuated SPECT images. This typically involves either:
- Images that have undergone a known, reliable attenuation correction method (e.g., CTAC) used as the target for the AI.
- Simulated data where the true attenuation is known.
- Expert-defined "ideal" attenuation correction.

The text does not detail this process but refers to "clinical and/or artificial data" being used for training.

Summary

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

August 16, 2021

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Spectrum Dynamics Medical Ltd % Igor Naroditsky Vice President, Quality and Regulatory Affairs 22 Bareket St North Industrial Park Caesarea. 3079837 ISRAEL

Re: K212230

Trade/Device Name: TruSPECT Radiological Image Processing Station Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QIH, LLZ Dated: July 10, 2021 Received: July 16, 2021

Dear Igor Naroditsky:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part

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

801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4. Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

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) K212230

Device Name

TruSPECT Radiological Image Processing Station

Indications for Use (Describe)

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

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

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

Image /page/3/Picture/0 description: The image contains the logo for Spectrum Dynamics Medical. On the left side of the logo is a blue triangular shape. To the right of the shape is the company name, with the word "SPECTRUM" on top of the words "DYNAMICS MEDICAL."

510(k) SUMMARY

510(k) Number: K212203

Date of submission:	July 10, 2021
Submitter:	Spectrum Dynamics Medical Ltd.22 Bareket St. North Industrial ParkCaesarea, Israel 3079837.
Submitter Contact:	Mr. Igor Naroditsky, VP QA/RATel: + (972) 54-438-4386Fax: + (972) 73-737-4502Email: igorn@spectrum-dynamics.com
Device Trade Name:	TruSPECT
Common Name/Classification:	Automated Radiological Image Processing SoftwareMedical image management and processing system
Class:	II
Product Code:	QIH, LLZ
Classification Panel:	Radiology
Regulation No:	892.2050

Marketed Devices:

The Spectrum Dynamics TruSPECT is a modification to the D-SPECT® Processing and Reviewing Workstation (K160120). The modification is the TruCorr, an image attenuation correction method which integrates pre-trained neural networks in the iteration reconstruction process to control image attenuation. ThruCorr aids as an alternative to the current image attenuation correction algorithm based on CT image, which is still available on the proposed devices.

All other features in the system are the same as in the D-SPECT Processing and Reviewing Workstation (K160120) and have the same functionality, safety, and performance.

Predicate device:

D-SPECT® Processing and Reviewing Workstation (K160120)

Spectrum Dynamics Medical Ltd. POB 3033, 22 Bareket Street Caesarea Industrial Zone, 3079837 Israel Phone #: +972-73-7374500 Fax #: +972-73-7374501 spectrum-dynamics.com

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

Image /page/4/Picture/0 description: The image shows the logo for Spectrum Dynamics Medical. The logo consists of a blue triangular prism on the left and the words "SPECTRUM" and "DYNAMICS MEDICAL" in blue on the right. The word "SPECTRUM" is in a larger font than "DYNAMICS MEDICAL."

Device Description:

Spectrum Dynamics Medical Ltd. POB 3033, 22 Bareket Street Caesarea Industrial Zone, 3079837 Israel Phone #: +972-73-7374500 Fax #: +972-73-7374501 spectrum-dynamics.com

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

Image /page/5/Picture/0 description: The image shows the logo for Spectrum Dynamics Medical. The logo consists of a blue triangular shape on the left and the text "SPECTRUM DYNAMICS MEDICAL" on the right. The word "SPECTRUM" is in a larger font than "DYNAMICS MEDICAL".

Intended Use:

TruSPECT is intended for acceptance, transfer, display, storage, and processing of images for detection of radioisotope tracer uptakes in the patient's body. The device using various processing modes supported by the various clinical applications and various features designed to enhance image quality. The emission computerized tomography data can be coupled with registered and/or fused CT/MR scans and with physiological signals in order to depict, localize, and/or quantify the distribution of radionuclide tracers and anatomical structures in scanned body tissue for clinical diagnostic purposes. The acquired tomographic image may undergo emission-based attenuation correction.

The system also includes reporting tools for formatting findings and user selected areas of interest. It is capable of processing and displaying the acquired information in traditional formats, as well as in three-dimensional renderings, and in various forms of animated sequences, showing kinetic attributes of the imaged organs.

TruSPECT is a processing workstation primarily intended for, but not limited to cardiac applications. The workstation can be integrated with the D-SPECT cardiac scanner system or used as a standalone post-processing station.

Technoloqical characteristic:

TruSPECT 's basic functionality for processing and reviewing nuclear medicine and associated CT images has not changed from its predicate. This capability includes manual and automatic segmentation to present, localize and/or quantify the distribution of radionuclide tracers and anatomical structures in patients for diagnostic purposes. Most of these features are designed to simplify users' workflows.

TruSPECT introduces a new application that focused on specific imaging attenuation technique, using this basic functionality proposed TruSPECT also enhances existing applications to improve

Spectrum Dynamics Medical Ltd. POB 3033, 22 Bareket Street Caesarea Industrial Zone, 3079837 Israel Phone #: +972-73-7374500 Fax #: +972-73-7374501 spectrum-dynamics.com

{6}------------------------------------------------

Image /page/6/Picture/0 description: The image shows the logo for Spectrum Dynamics Medical. The logo consists of a blue geometric shape on the left and the text "SPECTRUM" in blue on the right. Below "SPECTRUM" is the text "DYNAMICS MEDICAL" in a smaller font size, also in blue. The geometric shape appears to be a stylized representation of a three-dimensional object, possibly a cube or a pyramid.

their workflow efficiency using both pre-trained neural networks in the iteration reconstruction process and traditional algorithms.

Characteristic	Predicate device	Proposed device
Workflow	Uses both, manual andautomated processes.	Continues use both, manual andautomated processes. Also includes anew, pre-trained neural networks in theiteration reconstruction process andtraditional algorithms
Al utilization	Does not contain any Alprocesses/algorithms	Use artificial intelligence includingnonadaptive machine learningalgorithms trained with clinical and/orartificial data
Hardware Needed toSupport proposedstation	Offered as preinstalled onSpectrum Dynamicsworkstation.	Offered as preinstalled on SpectrumDynamics workstation or as softwarethat can be loaded onto the customer'sworkstation that meets specification

The Proposed TruSPECT has identical or equivalent technological characteristics as its predicate devices. The changes and the different technological characteristics do not raise new or different questions of safety and effectiveness. The software was developed, verified, and validated under Spectrum Dynamics Medical's QMS including software development lifecycle.

Preclinical Validation:

Proposed TruSPECT and its clinical applications successfully completed all design control testing per Spectrum Dynamics Medical's quality system and verified compliance with the relevant standards (i.e. NEMA PS3.1 - 3.20, IEC62304). The testing did not raise any new safety questions or identify any new risks. TruSPECT is designed and will be manufactured under the Quality System Regulations of 21CFR 820 and ISO 13485. The following quality assurance measures were applied to the development of the system:

। Risk Analysis
| Requirements Reviews
| Design Reviews
-SW Development Lifecycle
-Testing on Unit Level (Module Verification)
-Integration Testing (System Verification)
| Performance Testing (Verification)
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------Safety testing (Verification)

Spectrum Dynamics Medical Ltd.

POB 3033, 22 Bareket Street Caesarea Industrial Zone, 3079837 Israel Phone #: +972-73-7374500 Fax #: +972-73-7374501 spectrum-dynamics.com

{7}------------------------------------------------

Image /page/7/Picture/0 description: The image contains the logo for Spectrum Dynamics Medical. The logo consists of a blue triangular prism on the left and the text "SPECTRUM" in blue, bold letters on the right. Below "SPECTRUM" is the text "DYNAMICS MEDICAL" in a smaller, non-bold font, also in blue.

Simulated Use Testing (Validation) |
The testing and their results do not raise different questions of safety and effectiveness than the predicate device. Spectrum Dynamics Medical believes TruSPECT is of comparable type and substantially equivalent to the predicate device, and hence is safe and effective for its intended use. The substantial equivalence also based on software documentation for a "Moderate" level of concern device.

Clinical Evaluation

TruSPECT did not require clinical studies to support the determination of equivalence. However, the performance testing for the Al-based algorithm for iteration reconstruction process to control image attenuation have been evaluated and demonstrates algorithm's performance and uses test datasets of representative clinical exams.

The test datasets were comprised of representative clinical exams that were manually accessed by experienced NM Physicists and Physicians and were used as ground truth. The NM Physicists and Physicians also performed the algorithm evaluation. They reviewed the results and scored them using a 5-point Likert scale. The scientific methods used to evaluate the effectiveness of proposed application are acceptable and support the determination of substantial equivalence.

Substantial Equivalence

The Substantial Equivalence of the proposed device has been demonstrated by:

। Review of the proposed Indications for Use shows that they are substantially equivalent to the predicate device. Proposed Indications for Use do not create a new Intended Use.
| The device description and the comparison of device characteristics show that the proposed device has identical or equivalent technological characteristics as its predicate.
-The testing (engineering and clinical) demonstrates the efficiency of proposed device for its intended purpose.

The changes and the different technological characteristics do not raise new or different questions of safety and effectiveness. The proposed device is as safe and effective as the legally marketed predicate device as demonstrated by the:

| Software verification and validation for a Moderate level of concern, without unexpected results.
Spectrum Dynamics Medical Ltd.

POB 3033, 22 Bareket Street Caesarea Industrial Zone, 3079837 Israel Phone #: +972-73-7374500 Fax #: +972-73-7374501 spectrum-dynamics.com

{8}------------------------------------------------

Image /page/8/Picture/0 description: The image contains the logo for Spectrum Dynamics Medical. The logo consists of a blue geometric shape resembling a three-dimensional triangle on the left. To the right of the shape, the words "SPECTRUM" and "DYNAMICS MEDICAL" are written in blue, with "SPECTRUM" in a larger font size.

Development under quality management system, design control activities including risk management.
। Device labeling.
-Engineering and clinical testing without unexpected results.

Conclusion:

Based on the conformance to standards, development under Spectrum Dynamics quality system, the successful verification testing, additional engineering testing, and the clinical evaluation, Spectrum Dynamics Medical believes that the TruSPECT is substantially equivalent to the predicate device, D-SPECT® Processing and Reviewing Workstation (K160120) and hence is safe and effective for its intended use.

Spectrum Dynamics Medical Ltd.

POB 3033, 22 Bareket Street Caesarea Industrial Zone, 3079837 Israel Phone #: +972-73-7374500 Fax #: +972-73-7374501 spectrum-dynamics.com

Regulation Number and Section

§ 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).