The ME-APDS (Magentig Eye's Automatic Polyp Detection System) is intended to be used by endoscopists as an adjunct to the common video colonoscopy procedure (screening and surveillance), aiming to assist in identifying lesions during colonoscopy procedure by highlighting regions with visual characteristics consistent with different types of mucosal abnormalities that appear in the colonoscopy video during the procedure. Highlighted regions can be independently assessed by the endoscopist and appropriate action taken according to standard clinical practice.

The ME-APDS is trained to process video images which may contain regions consistent with polyps.

The ME-APDS is limited for use with standard white-light endoscopy imaging only.

The ME-APDS is intended to be used as an adjunct to endoscopy procedures and is not intended to replace histopathological sampling as means of diagnosis.

Device Description

The ME-APDS (Magentig Eve's Automatic Polvo Detection System) is intended to be used as an adjunct to the common video colonoscopy procedure. The system application aims to assist the endoscopist in identifying lesions, such as polyps, during the colonoscopy procedures in real time. The device is not intended to be used for diagnosis or characterization of lesions, and does not replace clinical decision making.

The system acquires the digital video output signal from the local endoscopy camera and processes the video frames. It runs deep machine learning and additional supporting algorithms in real time on the video frames in order to detect and identify regions having characteristics consistent with different tvpes of mucosal abnormalities such as polyps. The output video with the detected lesions is presented on a separate touchscreen, supplied as part of the ME-APDS, highlighting the suspicious areas on the original video. The output of the system can also be presented on additional monitors in the procedure room using the 1x4 HDMI Splitter supplied with the system. The user can also take snapshots of the videos, with and without the highlighting of the suspicious areas, record videos and view in full screen mode.

AI/ML Overview

Acceptance Criteria and Study Details for ME-APDS™

1. Table of Acceptance Criteria and Reported Device Performance:

Metric	Acceptance Criteria (Stated or Implied)	Reported Device Performance (ME-APDS™)
Standalone Performance:
Polyp-wise Recall (Polyps with Histology)	Not explicitly stated, but high recall across consecutive frames is implied for adequate aid.	PRecall1: 100.0%PRecall3: 99.6%PRecall5: 99.6%PRecall7: 99.6%
Polyp-wise Recall (Entire Testing Dataset)	Not explicitly stated, but high recall across consecutive frames is implied for adequate aid.	PRecall1: 98.2%PRecall3: 94.2%PRecall5: 91.5%PRecall7: 90.0%
False Positives Per Full Video (FPPF)	FPPF threshold of 0.0328 (normalized to 15 minutes)	Met the FPPF threshold of 0.0328
Marker Annotation Latency	Not explicitly stated, but real-time performance is a key feature.	Median: 0.166 sec (5 frames)Average: 0.85 sec
Robustness (IoU threshold variation)	Robust performance with varying IoU thresholds up to 0.2.	Changing IoU from 0.01 to 0.1 and 0.2 "slightly influenced only the framewise recall, and did not influence the other results supporting the robustness of the testing."
Clinical Performance (Comparative Effectiveness):
Adenomas Per Colonoscopy (APC)	MEAC APC expected to be >1.05 compared to CC APC (lower limit of 95% CI of MEAC/CC ratio).	MEAC APC: 0.70CC APC: 0.51 (Implied ratio: 0.70/0.51 ≈ 1.37, which is > 1.05)
Adenomas Per Extraction (APE)	APE of MEAC expected to be non-inferior to APE of CC (lower limit of 95% CI of difference between APE of MEAC and CC expected to be above -0.20).	MEAC APE: 0.31CC APE: 0.27 (Difference: 0.04. The document states "APE proved non-inferior to that of CC," indicating the criterion was met. Actual CI not explicitly given in table for overall APE difference but for subgroups).

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

Standalone Performance Testing:
- Sample Size: 172 unique full colonoscopy videos, containing 449 polyps (16 videos contained no polyps).
- Data Provenance: Not explicitly stated for each video, but the videos covered various demographic factors (subject sex, age, race). Given that the clinical study data was collected from "10 medical centers in Europe, the United States and Israel," it is highly probable that the standalone testing data also originates from a similar diverse geographical pool. The context suggests it is likely retrospective video data collected from past procedures.
Clinical Testing (Comparative Effectiveness Study):
- Sample Size: 950 patients enrolled (916 patients for baseline demographics). The treatment arms were:
  - CC (Conventional Colonoscopy): 398 patients
  - CC-MEAC (CC followed by MEAC): 69 patients
  - MEAC (ME-APDS-assisted Colonoscopy): 385 patients
  - MEAC-CC (MEAC followed by CC): 64 patients
- Data Provenance: A randomized, two-arm, multi-center, controlled study conducted at 10 medical centers in Europe, the United States, and Israel. This is a prospective study.

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

Standalone Performance Testing: The document does not explicitly state the number of experts or their qualifications for establishing the ground truth specifically for the standalone test set videos. It mentions "Polyps evaluated varied by subject sex... 263 polyps had histology findings..." which implies that histology was used for ground truth. The polyps being "reported in the procedure report" suggests the involvement of clinical experts (endoscopists) at the time of procedure.
Clinical Testing (Comparative Effectiveness Study): The ground truth for polyps (number of adenomas, extractions) was established by the endoscopists performing the colonoscopies within each arm of the study. These would be qualified medical professionals (endoscopists) at the participating clinical centers. The document does not specify their exact years of experience or the number of individual experts beyond the "10 medical centers." The use of "histology" for confirmation of adenomas is also mentioned implicitly in the APE definition, meaning pathology experts contribute to the final ground truth.

4. Adjudication Method for the Test Set:

Standalone Performance Testing: Not explicitly stated. The mention of "polyps verified by histology" implies that a pathologist's report served as the ultimate ground truth. It does not describe an adjudication process between multiple readers of the videos for annotation or ground truth establishment.
Clinical Testing (Comparative Effectiveness Study): No specific adjudication method across multiple independent experts is described for determining the ultimate ground truth in the clinical study. The number of adenomas and extractions were recorded during the colonoscopy procedures, with histology confirming the nature of extracted polyps. The "tandem" design (CC followed by MEAC or MEAC followed by CC) in a subset of patients implicitly allows for a comparison of findings within the same patient, acting as an internal check.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and effect size of human readers improvement with AI vs without AI assistance:

Yes, a comparative effectiveness study was done.
Study Design: A randomized, two-arm, multi-center, controlled study comparing conventional colonoscopy (CC) with ME-APDS-assisted colonoscopy (MEAC). This is a clinical trial, not a typical MRMC study where multiple readers interpret cases for diagnostic accuracy. However, it still assesses the effectiveness of human readers with AI assistance versus without.
Effect Size:
- Adenomas Per Colonoscopy (APC): MEAC APC was 37% higher (relative increase) than CC APC.
  - MEAC APC: 0.70
  - CC APC: 0.51
  - Absolute difference: 0.70 - 0.51 = 0.19 adenomas per colonoscopy.
- The study found "a mean 0.20 increment between arms for each analyzed subgroup" for APC.
- MEAC was "more effective than CC in detecting ≤5mm polyps and in detecting >6-9 mm polyps, sessile and flat polyps and adenomas in the proximal colon."
- "more sessile serrated adenomas (SSAs) were identified in MEACs as compared to CCs, which resulted in also a higher sessile serrated detection rate (SDR)."

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

Yes, a standalone performance testing was done. This is detailed under "Standalone Performance Testing" on page 5.

7. The type of ground truth used:

Standalone Performance Testing: The ground truth was primarily based on histology findings for 263 polyps and implicitly based on the endoscopist's procedure report for the remaining polyps identified in the videos.
Clinical Testing (Comparative Effectiveness Study): The ground truth was established by recorded adenoma detections and extractions by endoscopists during the procedures, with the definitive diagnosis of adenomas confirmed by histopathology results.

8. The sample size for the training set:

The document does not explicitly state the sample size (number of videos or polyps) used for the ME-APDS training set. It only mentions that the system "runs deep machine learning and additional supporting algorithms" and "is trained to process video images."

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

The document does not explicitly describe how the ground truth for the training set was established. However, given the nature of the device and the testing methodologies, it is highly probable that the training data would have been meticulously annotated by clinical experts (e.g., experienced gastroenterologists or endoscopists) to label polyps, potentially with subsequent pathological confirmation for cases where tissue was removed. This common practice ensures high-quality ground truth for training medical AI models.

Summary

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

Image /page/0/Picture/0 description: The image contains the logos of the Department of Health and Human Services and the Food and Drug Administration (FDA). The Department of Health and Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.

July 25, 2023

Magentiq Eye LTD % John Smith Partner Hogan Lovells US LLP Columbia Square, 555 Thirteenth Street, NW Washington, District of Columbia 20004

Re: K223473

Trade/Device Name: ME-APDS™; MAGENTIQ-COLO™ Regulation Number: 21 CFR 876.1520 Regulation Name: Gastrointestinal Lesion Software Detection System Regulatory Class: Class II Product Code: ONP Dated: June 22, 2023 Received: June 22, 2023

Dear John Smith:

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

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

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 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 medical devices and radiation-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,

Shanil P. Haugen -S

Shanil P. Haugen, Ph.D. Assistant Director DHT3A: Division of Renal, Gastrointestinal, Obesity and Transplant Devices OHT3: Office of GastroRenal, ObGyn, General Hospital and Urology Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

510(k) Number (if known) K223473

Device Name

ME-APDS™: MAGENTIQ-COLOTM

Indications for Use (Describe)

The ME-APDS is trained to process video images which may contain regions consistent with polyps.

The ME-APDS is limited for use with standard white-light endoscopy imaging only.

The ME-APDS is intended to be used as an adjunct to endoscopy procedures and is not intended to replace histopathological sampling as means of diagnosis.

Type of Use (Select one or both, as applicable)

区 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.qov

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

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

510(k) SUMMARY Magentig Eye's ME-APDS

Submitter:

Magentiq Eye Ltd. 6 Ben-Gurion Blvd., Haifa. 3541416. lsrael

Phone: +972 (77) 2018838

Contact Person: Dr. Dror Zur

Date Prepared: July 23, 2023

Name of Device: Magentiq Eye's Automatic Polyp Detection System (ME-APDS™)

Common or Usual Name: Computer aided detection software for colorectal polyps

Classification Name: Gastrointestinal Lesion Software Detection System

Regulatory Class: II

Product Code: QNP

Predicate Device: Cosmo Artificial Intelligence - AI, LTD's GI Genius (K211951)

Device Description:

Intended Use / Indications for Use:

The ME-APDS (Magentiq Eye's Automatic Polyp Detection System) is intended to be used by endoscopists as an adjunct to the common video colonoscopy procedure (screening and surveillance). aiming to assist the endoscopist in identifying lesions during colonoscopy procedure by highlighting regions with visual characteristics consistent with different types of mucosal abnormalities that appear

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

in the colonoscopy video during the procedure. Highlighted regions can be independently assessed by the endoscopist and appropriate action taken according to standard clinical practice.

The ME-APDS is trained to process video images which may contain regions consistent with polyps.

The ME-APDS is limited for use with standard white-light endoscopy imaging only.

The ME-APDS is intended to be used as an adjunct to endoscopy procedures and is not intended to replace histopathological sampling as means of diagnosis.

Summary of Technological Characteristics:

Computer-Aided Polyp Detection (CADe) engine is the technological principle for both the subject and predicate devices. The maior roles of CADe engine during colonoscopy is to process a video frame and to indicate the presence and location of detected lesions (such as polyps) in real time during colonoscopy procedure in order to improve mucosal lesion rates, thus improving the performance of the endoscopist.

At a high level, the subject and predicate devices are based on the following same technological elements:

Both systems have similar intended use, intended user and patient population. ●
Both systems' computing devices retrieve the video stream from the Endoscope and ● run a deep machine learning algorithms from the type of Deep Neural Networks (DNN) technology in real time. It then feeds a video output with the detected lesions (such as polyps) in an overlay highlighting the suspicious areas on the original video.
Both systems do not make any elaboration or alteration of the colonoscopy video ● streaming.
o Both systems are suitable for use in white-light endoscopic mode of operations.

The following technological differences exist between the subject and predicate device:

o The ME-APDS is comprises a cart, monitor, a computing device, transformer and 1x4 HDMI Splitter. The ME-APDS shall be positioned adjacent to the colonoscopy cart, connected to the electricity and to the video output of coloscopy device. The GI Genius is comprised from a computing module only that is positioned on the coloscopy cart and connected to the video output of coloscopy device and to the coloscopy device display monitor.
The ME-APDS uses dual monitor display setup and is supplied together with a 1x4 HDMI Splitter to allow connecting the system's output to additional monitors in the procedure room. The predicate device uses a single monitor display setup and is connected directly to the coloscopy device display monitor.
The ME-APDS user interface is a touchscreen monitor allowing touch control of the ● system. The GI Genius uses the existing colonoscopy system display monitor and control.

As validated in the clinical study, none of the identified technological differences introduce new aspects of safety or effectiveness. Both systems clinical efficacy and safety performances are very similar.

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

Performance Data:

Non-Clinical Testing:

The non-clinical performance studies of the subject device included:

o Pixel-level comparison of degradation of image quality
o Software validation
. EMC testing in accordance with the requirements of IEC 60601-1-2:2014
o Electrical safety testing in accordance with IEC 60601-1:2005.

In all instances, the ME-APDS functioned as intended and all tests' results observed were as expected.

Assessment of marker annotation delay

Marker annotation delay was assessed for all polyps all in the standalone performance testing. The marker annotation latency's median, calculated over all the polyps, is 0.166 sec (5 frames) and its average is 0.85 sec.

Standalone Performance Testing:

The algorithm was tested offline on 172 unique full colonoscopy videos, containing 449 polyps, 16 videos contained no polyps. Of the 449 polyps, 330 were small (s≤5mm), 76 have medium size (5mm<s<10mm), and 43 were large (s≥10mm). 263 polyps had histology findings where 210 were found to be adenoma polyps. Polyps evaluated varied by subject sex (270 Male, 170 Female, 6 Unknown), age (27 under 50 years, 67 50-60 years, 169 older than 60 years), race (343 Caucasian, 6 African American, 100 Unknown).

ME-APDS recall and false positive performance was evaluated. Recall was measured both framewise and polyp-wise and classified according to polyp size and type. In addition, the number of False Positives Per Full Video (procedure) rate was assessed. A verification of the robustness scoring of the Polyp-Wise and Frame-Wise calculations was performed by varying the Intersection over Union (IoU) threshold from 0.01 to 0.1 and 0.2.

Polyp-wise Recall was defined as the number of polyps detected, each for a set number consecutive frames, out of the total number of polyps in the testing dataset, Polyp-wise Recall was evaluated a 1, 3, 5 and 7 consecutive frames as Precall1, Precall3, and Precall7, respectively.

The system detects 100% to 99.6% (PRecall1 to PRecall7) of polyps verified by histology and 98.2% to 90% (PRecall1 to PRecall7) of the polyps when polyps without histology verification were included, showing the ability of the system to adequately aid in the detection of polyps when working with the ME-APDS. The median of the coverage of polyps with histology was high (82.0%). And the False Positives Per Video, when all the videos are normalized to a time length of 15 minutes is met the False Positives Per Frame (FPPF) threshold of 0.0328.

Results on polyps that were reported in the procedure report, classified according to polyps with histology and without

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

	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
WithHistology	75.7%	[72.5%;78.8%]	82.0%	100.0%	[100.0%;100.0%]	99.6%	[98.8%;100.0%]	99.6%	[98.8%;100.0%]	99.6%	[98.8%;100.0%]
WithoutHistology	81.54%	[71.1%;89.9%]	84.5%	100.0%	[100.0%;100.0%]	100.0%	[100.0%;100.0%]	100.0%	[100.0%;100.0%]	100.0%	[100.0%;100.0%]

Results on the Entire Testing Dataset

FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
73.1%	[69.6%;76.4%]	72.9%	98.2%	[96.1%;100.0%]	94.2%	[92.0%;96.1%]	91.5%	[88.7%;94.0%]	90.0%	[87.0%;92.7%]

Results on Polyps with Histology Classified by Polyp Size

-	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
Small(s≤5)	71.7%	[67.6%;75.7%]	80.3%	100.0%	[100.0%;100.0%]	99.5%	[98.5%;100.0%]	99.5%	[98.5%;100.0%]	99.5%	[98.5%;100.0%]
Medium(5 82.9% [77.6%;87.8%] 85.2% 100.0% [100.0%;100.0%] 100.0% [100.0%;100.0%] 100.0% [100.0%;100.0%] 100.0% [100.0%;100.0%]

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

Large(10≤s)	82.6%	[78.0%;87.0%]	87.7%	100.0%	[100.0%;100.0%]	100.0%	[100.0%;100.0%]	100.0%	[100.0%;100.0%]	100.0%	[100.0%;100.0%]
-----------------	-------	-----------------------	-------	--------	-------------------------	--------	-------------------------	--------	-------------------------	--------	-------------------------

Changing the loU from 0.01 to 0.1 and 0.2, slightly influenced only the framewise recall, and did not influence the other results supporting the robustness of the testing demonstrates the system performs well on all polyps sizes (small, medium and large polyps), polyps with histology, and both adenomatous and non-adenomatous polyps.

Subgroup analysis by age group, device manufacturer, sex, race, BMI, US/OUS, and reason for colonoscopy demonstrated detection between 100% to 97.3% (PRecall 1 to PRecall7) in all subgroups of polyps verified by histology.

Performance (IoU 0.01 and FPPF 0.328), over all the polyps verified by histology in the testing dataset, according to device manufacturer

-	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
Olympus	75.8%	[72.0%;79.5%]	81.4%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]
Pentax	75.5%	[69.8%;80.8%]	82.1%	100%	[100.0%;100.0%]	98.7%	[97.2%;100.0%]	98.7%	[97.2%;100.0%]	98.7%	[97.2%;100.0%]

Performance (IoU 0.01 and FPPF 0.328), over all the polyps verified by histology in the testing dataset, according to age group

-	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
<50	83.6%	[75.2%;90.9%]	87.4%	100%	[100.0%;	100%	[100.0%;	100%	[100.0%;	100%	[100.0%;

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

					100.0%]	100.0%]	100.0%]	100.0%]
50 to <60	76.6%	[69.8%;82.6%]	84.2%	100%	[100.0%;100.0%]	[100.0%;100.0%]	[100.0%;100.0%]	[100.0%;100.0%]
60≤	74.2%	[70.2%;78.1%]	80.1%	100%	[100.0%;100.0%]	[98.2%;100.0%]	[98.2%;100.0%]	[98.2%;100.0%]

Performance (IoU 0.01 and FPPF 0.328), over all the polyps verified by histology in the testing dataset, according to patient sex group

-	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
Male	76.7%	[72.5%;80.7%]	82.5%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]
Female	74.5%	[69.7%;79.2%]	82.6%	100%	[100.0%;100.0%]	99.0%	[97.2%;100.0%]	99.0%	[97.2%;100.0%]	99.0%	[97.2%;100.0%]
Unknown	70.4%	[70.4%;70.4%]	63.7%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]

Performance (IoU 0.01 and FPPF 0.328), over all the polyps verified by histology in the testing dataset, according to reason for colonoscopy

{9}------------------------------------------------

-	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
Screening	76.2%	[70.2%;81.7%]	83.0%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]
Surveillance	73.1%	[67.6%;78.4%]	81.7%	100%	[100.0%;100.0%]	99.1%	[97.5%;100.0%]	99.1%	[97.5%;100.0%]	99.1%	[97.5%;100.0%]
Unknown	80.6%	[76.4%;84.5%]	82.2%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]

Performance (IoU 0.01 and FPPF 0.328), over all the polyps verified by histology in the testing dataset, according to race

	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
Caucasian	75.0%	[71.3%;78.6%]	81.5%	100%	[100.0%;100.0%]	99.5%	[98.6%;100.0%]	99.5%	[98.6%;100.0%]	99.5%	[98.6%;100.0%]
Afro-American	90.6%	[90.6%;90.6%]	88.3%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]
Unknown	79.4%	[74.8%;84.0%]	82.6%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]

{10}------------------------------------------------

Performance (IoU 0.01 and FPPF 0.328), over all the polyps verified by histology in the testing dataset, according to BMI group

-	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
<18.5	49.9%	[49.9%;49.9%]	47.6%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]
18.5 to <25	78.7%	[71.5%;85.4%]	83.3%	100%	[100.0%;100.0%]	97.3%	[90.2%;100.0%]	97.3%	[90.2%;100.0%]	97.3%	[90.2%;100.0%]
25 to <30	74.8%	[65.2%;83.6%]	83.1%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]
30≤	72.1%	[59.4%;81.5%]	78.2%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]
Unknown	76.6%	[72.6%;80.3%]	81.0%	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]	100%	[100.0%;100.0%]

Performance (IoU 0.01 and FPPF 0.328), over all the polyps verified by histology in the testing dataset, according to US vs. OUS

-	FRecall	CI	MPC	PRecall1	CI	PRecall3	CI	PRecall5	CI	PRecall7	CI
US	80.4%	[75.9%;	83.5%	100%	[100.0%;	100%	[100.0%;	100%	[100.0%;	100%	[100.0%;

{11}------------------------------------------------

		84.8%]			100.0%]		100.0%]		100.0%]		100.0%]
OUS	74.9%	[71.2%;78.5%]	81.5%	100%	[100.0%;100.0%]	99.5%	[98.4%;100.0%]	99.5%	[98.4%;100.0%]	99.5%	[98.4%;100.0%]

The testing results were observed to be as expected and support that the device has similar performance to the predicate device.

Clinical Testing:

A randomized, two-arm, multi-center, controlled study to evaluate the safety and efficacy of the use of Magentiq Eye's Automatic Polyp Detection System (ME-APDS) during colonoscopy was conducted at 10 medical centers in Europe, the United States and Israel with 950 patients enrolled.

Patients due to undergo screening or surveillance colonoscopy of ≥3 years since last colonoscopy procedure, were randomized to undergo conventional colonoscopy, CC, (Cohort A1), or ME-APDSassisted colonoscopy, MEAC, (Cohort B1). In each arm, a subset of patients was further randomized to undergo both colonoscopies in tandem (either CC followed by MEAC (Cohort A2) or MEAC followed by CC (Cohort B2). The final ratios between treatment arms were 6:6:1:1.An outline of the baseline demographics is provided below:

	Treatment Group				Total, n
Population	CC(N=398)	CC-MEAC(N=69)	MEAC(N=385)	MEAC-CC(N=64)	(%) (N=916)
Age (years)
Mean (SD)	60.4 (9.2)	60.1 (10.1)	60.4 (8.8)	59.3 (9.0)	60.3 (9.1)
Median	60.0	61.0	60.0	59.5	60.0
Minimum, Maximum	27, 86	32, 86	31, 84	35, 79	27, 86
Age Group, n (%)
< 50	33 (8.3)	6 (8.7)	27 (7.0)	7 (11.0)	73 (8.0)
50-60	160 (40.2)	25 (36.3)	155 (40.3)	25 (39.1)	365
> 60	205 (51.5)	38 (55.1)	203 (52.7)	32 (50.0)	478
Sex, n (%)
Male	219 (55.0)	38 (55.1)	202 (52.5)	34 (53.1)	493(53.8)
Female	179 (45.0)	31 (44.9)	183 (47.5)	30 (46.9)	423
BMI (kg/m²)
Mean (SD)	27.5 (5.1)	25.9 (4.8)	27.0 (4.8)	27.2 (4.8)	27.2 (4.9)
Median	26.7	26.1	26.2	25.8	26.2

{12}------------------------------------------------

Minimum, Maximum	15.8, 57.4	15.5, 39.3	17.1, 52.6	19.4, 39.0	15.5,
Race, n (%)*
Caucasian	374 (94.2)	67 (97.1)	370 (96.1)	63 (98.4)	874
African-American	18 (4.5)	2 (2.9)	12 (3.1)	1 (1.6)	33 (3.6)
Asian	1 (0.3)	-	1 (0.3)	-	2 (0.2)
Other	4 (1.0)	-	2 (0.5)	-	6 (0.7)
Reason for Colonoscopy, n
Screening	222 (55.8)	37 (53.6)	219 (56.9)	36 (56.3)	514
Surveillance	176 (44.2)	32 (46.4)	166 (43.1)	28 (43.8)	402

*For one patient in the CC treatment group the race information was not reported

Primary endpoints:

APC: total number of adenomas detected and removed per examination
APE: the percentage of adenomas detected and removed divided by the total number of ● extractions (polypectomies or biopsies) during index colonoscopies

Success criteria:

More adenomas will be detected with MEAC compared to CC. This will result in higher APC with MEAC compared to CC. APE of MEAC is expected to be non-inferior to APE of CC.

APC: Difference between the event rates of MEAC vs. CC were compared using a t test, with a . two-sided alpha of 5%. The two-sided lower limit of a 95% confidence interval (CI) of the MEAC/CC ratio of events was expected to be >1.05.
APE: A two-sided Wilcoxon test with a non-inferiority margin of 20% was performed with a two-. sided alpha of 5%. The two-sided lower limit of the 95% Cl of the difference between the APE of each colonoscopy technique was expected be above -0.20. In addition, 95% Cls of the APE proportions of MEAC and CC were calculated using normal approximation.

APC & APE Results

The primary analysis assessed APC and APE: the percentage of adenomas detected and removed divided by the total number of extractions (polypectomies or biopsies) during index colonoscopies

	Treatment
	CC(N=467)	MEAC(N=449)
Total Adenomas	238	314
Total Colonoscopies	467	449
Adenomas Per Colonoscopy(APC)	0.51 (1.03)	0.70 (1.30)
SE	0.05	0.06

Adenoma per Colonoscopy (APC) and Adenoma per Extraction (APE) (ITT Population)

{13}------------------------------------------------

95% Cl	0.42, 0.60	0.58, 0.82

Total Adenomas	238	314
Total Extractions	360	536
Adenomas Per Extraction (APE)
Mean (SD)	0.27 (0.43)	0.31 (0.43)
SE	0.02	0.20
95% Cl	0.23, 0.31	0.27, 0.35

Subgroup Performance

Adenoma per Colonoscopy (APC) and Adenoma per Extraction (APE) by Study Region (ITT Population)

	Treatment
	CC(N=467)					MEAC(N=449)
	TotalAdenomas	TotalColonoscopies	APC	TotalExtractions	APE	TotalAdenomas	TotalColonoscopies	APC	TotalExtractions	APE
USA	102	84	1.21	142	0.72	105	77	1.36	171	0.61
OUS	136	383	0.36	218	0.62	209	372	0.56	365	0.57

Adenoma per Colonoscopy (APC) and Adenoma per Extraction (APE) by Subgroup (ITT Population)

	Treatment
	CC(N=467)			MEAC(N=449)
Subgroup	TotalAdenomas	TotalColonoscopies	APC	TotalExtractions	APE	TotalAdenomas	TotalColonoscopies	APC	TotalExtractions	APE
Reason for colonoscopy
Screening	106	259	0.41	171	0.62	149	255	0.58	239	0.62
Surveillance	132	208	0.63	189	0.70	165	194	0.85	297	0.56
Sex
Female	91	210	0.43	138	0.66	136	213	0.64	246	0.55
Male	147	257	0.57	222	0.66	178	236	0.75	290	0.61
Age Group
<50 yrs	8	39	0.21	15	0.53	7	34	0.21	23	0.30
50-60 yrs	72	185	0.39	122	0.59	121	180	0.67	186	0.65
>60 yrs	158	243	0.65	223	0.71	186	235	0.79	327	0.57

The table below provides the two sided 95% Cl's for APC and APE by subgroup. Calculations were made on patient level results assuming normal distribution.

Confidence Intervals for APC and APE by Subgroup

{14}------------------------------------------------

K223473
Page 12 of 13

Endpoint	Subgroup	Treatment	Mean	Lower95%	Upper95%
APC	US	CC	1.214	0.872	1.556
		MEAC	1.364	0.976	1.751
	OUS	CC	0.355	0.277	0.434
		MEAC	0.562	0.444	0.679
	Screening	CC	0.409	0.305	0.514
		MEAC	0.584	0.455	0.714
	Surveillance	CC	0.635	0.471	0.798
		MEAC	0.851	0.630	1.071
	Female	CC	0.433	0.304	0.563
		MEAC	0.638	0.453	0.824
	Male	CC	0.572	0.439	0.705
		MEAC	0.754	0.596	0.912
	< 50	CC	0.205	0.020	0.390
		MEAC	0.206	0.039	0.373
	50- 60	CC	0.389	0.267	0.511
		MEAC	0.672	0.494	0.850
	> 60	CC	0.650	0.501	0.799
		MEAC	0.791	0.608	0.975
APE	US	CC	0.484	0.384	0.584
		MEAC	0.443	0.351	0.536
	OUS	CC	0.222	0.181	0.262
		MEAC	0.278	0.234	0.321
	Screening	CC	0.247	0.196	0.299
		MEAC	0.300	0.247	0.354
	Surveillance	CC	0.295	0.236	0.355
		MEAC	0.314	0.255	0.373
	Female	CC	0.240	0.183	0.297
		MEAC	0.269	0.214	0.325
	Male	CC	0.292	0.239	0.346
		MEAC	0.340	0.283	0.396
	< 50	CC	0.147	0.033	0.262
		MEAC	0.152	0.027	0.277
	50- 60	CC	0.205	0.149	0.261
		MEAC	0.312	0.249	0.376
	> 60	CC	0.337	0.279	0.395
		MEAC	0.324	0.269	0.379

The study results showed that the MEAC adenoma per colonoscopy (APC) was 37% higher (relative increase) than CC APC and was consistently higher across all patient subgroups. Inter-arm comparisons found consistently higher APC rates for MEAC as compared to CC procedures, regardless of colonoscopy indication, patient sex, or patient age, with a mean 0.20 increment between arms for each analyzed subgroup. In particular. MEAC proved more effective than CC in detecting ≤5mm polyps and in detecting >6-9 mm polyps, sessile and flat polyps and adenomas in the proximal colon. In addition, more sessile serrated adenomas (SSAs) were identified in MEACs as compared to CCs, which resulted in also a higher sessile serrated detection rate (SDR). Despite the increased detection rate, the MEAC adenomas per extraction (APE) proved non-inferior to that of CC, and did not involve clinically relevant longer withdrawal times or delayed bleeding. In line with these findings, AMR was significantly lower and ADR was significantly higher in the MEAC vs. CC arm. As expected, given the above findings, time to next scheduled colonoscopy was 4 months earlier in the MEAC as compared to the CC cohort.

{15}------------------------------------------------

These observations suggest a critical contribution of MEAC in minimizing the effects of confounding clinical and operator-related factors on colonoscopy outcomes. No intervention-related adverse events were reported during this study in either arm.

Based on the clinical performance as documented in the pivotal clinical study, the ME-APDS performs as intended under anticipated conditions of use and has a safety and effectiveness profile that is similar to the predicate device.

Conclusions:

The ME-APDS is as safe and effective as Cosmo Artificial Intelligence - Al. LTD's GI Genius. The ME-APDS has the same intended uses and similar indications, technological characteristics, and principles of operation as its predicate device. The minor differences in indications do not alter the intended use. In addition, the minor technological differences between the ME-APDS and its predicate devices raise no new issues of safety or effectiveness. Performance data demonstrate that the ME-APDS is as safe and effective as the GI Genius. Thus, the ME-APDS is substantially equivalent.

Regulation Number and Section

§ 876.1520 Gastrointestinal lesion software detection system.

(a)
Identification. A gastrointestinal lesion software detection system is a computer-assisted detection device used in conjunction with endoscopy for the detection of abnormal lesions in the gastrointestinal tract. This device with advanced software algorithms brings attention to images to aid in the detection of lesions. The device may contain hardware to support interfacing with an endoscope.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use, including detection of gastrointestinal lesions and evaluation of all adverse events.
(2) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use. Testing must include:
(i) Standalone algorithm performance testing;
(ii) Pixel-level comparison of degradation of image quality due to the device;
(iii) Assessment of video delay due to marker annotation; and
(iv) Assessment of real-time endoscopic video delay due to the device.
(3) Usability assessment must demonstrate that the intended user(s) can safely and correctly use the device.
(4) Performance data must demonstrate electromagnetic compatibility and electrical safety, mechanical safety, and thermal safety testing for any hardware components of the device.
(5) Software verification, validation, and hazard analysis must be provided. Software description must include a detailed, technical description including the impact of any software and hardware on the device's functions, the associated capabilities and limitations of each part, the associated inputs and outputs, mapping of the software architecture, and a description of the video signal pipeline.
(6) Labeling must include:
(i) Instructions for use, including a detailed description of the device and compatibility information;
(ii) Warnings to avoid overreliance on the device, that the device is not intended to be used for diagnosis or characterization of lesions, and that the device does not replace clinical decision making;
(iii) A summary of the clinical performance testing conducted with the device, including detailed definitions of the study endpoints and statistical confidence intervals; and
(iv) A summary of the standalone performance testing and associated statistical analysis.