PeekMed web is a system designed to help healthcare professionals carry out pre-operative planning for several surgical procedures, based on their imported patients' imaging studies. Experience in usage and a clinical assessment is necessary for the proper use of the system in the revision and approval of the output of the planning.

The multi-platform system works with a database of digital representations related to surgical materials supplied by their manufacturers.

This medical device consists of a decision support tool for qualified healthcare professionals to quickly and efficiently perform the pre-operative planning for several surgical procedures, using medical imaging with the additional capability of planning the 2D or 3D environment. The system is designed for the medical specialties within surgery and no specific use environment is mandatory, whereas the typical use environment is a room with a computer. The patient target group is adult patients who have an injury or disability diagnosed previously. There are no other considerations for the intended patient population.

Device Description

The multi-platform system works with a database of digital representations related to surgical materials supplied by their manufacturers.

As PeekMed web is capable of representing medical images in a 2D or 3D environment, performing relevant measurements on those images, and also capable of adding templates, it then can perform a total overview of the surgery. Being software it does not interact with any part of the body of the user and/or patient.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document provides the acceptance criteria but does not directly state the reported device performance metrics from the external validation. It only states that the efficacy results "met the acceptance criteria."

ML Model	Acceptance Criteria	Reported Device Performance (Not explicitly stated in document, only that criteria were met)
Segmentation	DICE is no less than 90%HD-95 is no more than 8STD DICE is between +/- 10%Precision is more than 85%Recall is more than 90%	Met acceptance criteria
Landmarking	MRE is no more than 7mmSTD MRE is between +/- 5mm	Met acceptance criteria
Classification	Accuracy is no less than 90%.Precision is no less than 85%Recall is no less than 90%F1 score is no less than 90%	Met acceptance criteria
Detection	MAP is no less than 90%.Precision is no less than 85%Recall is no less than 90%	Met acceptance criteria

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

Test Set (External Validation Dataset) Sample Sizes:
- Segmentation ML model: 375
- Landmarking ML model: 345
- Classification ML model: 347
- Detection ML model: 198
Data Provenance: The document states "multiple sites." It does not specify the country of origin. The external validation dataset was collected "independently of the development data to prevent bias" and was a "fully independent dataset." It is not explicitly stated whether the data was retrospective or prospective, but the phrasing "collected independently" for external validation often implies existing, retrospectively collected data used for this specific purpose.

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

The document states that the external validation dataset was "labeled by a separate team" to establish ground truth. It does not provide the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience").

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1). It only states that the ground truth was "labeled by a separate team."

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

No MRMC comparative effectiveness study involving human readers with and without AI assistance is described in the provided text. The study focuses solely on the standalone performance of the ML models against a predefined ground truth. The device is a "decision support tool" requiring "clinical assessment" and "revision and approval of the output of the planning" by healthcare professionals, implying a human-in-the-loop workflow, but no human performance study is detailed.

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

Yes, a standalone performance evaluation of the ML models was done. The acceptance criteria and the evaluation against a "predefined ground truth" for Segmentation, Landmarking, Classification, and Detection ML models indicate standalone algorithm performance. The document states that the "efficacy results... met the acceptance criteria for ML model performance."

7. The Type of Ground Truth Used

The ground truth was "predefined ground truth" established by a "separate team" for the external validation dataset. While not explicitly stated as "expert consensus," this typically implies human expert review and labeling given the context of medical imaging and planning. It is not stated as pathology or outcomes data.

8. The Sample Size for the Training Set

The ML models were developed with datasets totaling 2852 CR datasets and 1903 CT scans.

Training Set: 80% of these datasets were used for training.
- 0.80 * (2852 + 1903) = 0.80 * 4755 = 3804 datasets

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

The document states that the ML models were "developed with datasets from multiple sites." While it mentions that "External validation datasets were collected independently of the development data... labeled by a separate team," it does not explicitly describe the methodology for establishing ground truth for the training dataset. However, it's generally inferred in such contexts that training data also requires labeled ground truth, likely established by human annotators or experts, but the specifics are not provided in this document.

Summary

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

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left, there is a symbol representing the Department of Health & Human Services. To the right, there is the FDA logo in blue, followed by the words "U.S. FOOD & DRUG" in a larger font and "ADMINISTRATION" in a smaller font below it, also in blue. The logo is clean and professional, reflecting the organization's role in regulating food and drugs.

Peek Health, S.A. Sara Silva Chief Quality Officer (CQO) Centro de Negócios Ideia Atlântico, Rua Padres Carmelitas Braga, 4719-005 Portugal

March 19, 2025

Re: K250042

Trade/Device Name: PeekMed web Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH, LLZ Dated: January 8, 2025 Received: January 8, 2025

Dear Sara Silva:

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 (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

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

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device"

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

(https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system.

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

For comprehensive regulatory information about 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-regulatory

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

assistance/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,

Jessica Lamb

Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

Submission Number (if known)

K250042

Device Name

PeekMed web

Indications for Use (Describe)

The multi-platform system works with a database of digital representations related to surgical materials supplied by their manufacturers.

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

Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

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

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

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

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

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

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

Image /page/4/Picture/1 description: The image shows the logo for PeekMed. The logo features a stylized, three-dimensional cube shape in a teal color. Within the cube, there is a white eye shape, suggesting a focus on vision or medical imaging. Below the cube, the text "PeekMed" is written in a simple, sans-serif font, also in teal.

510(k) summary

This 510(k) summary of safety and effectiveness is being submitted in accordance with the requirements of 21 CFR 807.92.

1. Submitter

Peek Health, S.A. Centro de Negócios Ideia Atlântico Rua Padres Carmelitas 4719-005 Braga Portugal

Contact Person:	Sara SilvaChief Quality Officer (CQO)

Email:	sara.silva@peekmed.com
Office number:	+ 351 253 128 941

Date Summary Prepared: March 17, 2025

2. Device

2.1 PeekMed web

Trade Name:	PeekMed web
Common or Usual Name:	Medical image management and processing system
Classification Name:	System, Image Processing, Radiological(21 C.F.R. § 892.2050)
Regulatory Class:	Class II
Product Code:	QIH, LLZ

3. Legally Marketed Predicate Device

3.1 PeekMed web

510(k)	Product Name	Clearance Date
K240926	PeekMed web	December 6, 2024

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

Image /page/5/Picture/1 description: The image shows the logo for PeekMed. The logo features a stylized, geometric shape in blue, resembling a cube with a section cut out to reveal a white eye in the negative space. Below the geometric shape, the text "PeekMed" is written in a simple, sans-serif font, also in blue.

4. Device Description Summary

The multi-platform system works with a database of digital representations related to surgical materials supplied by their manufacturers.

5. Intended Use/Indications for Use

The multi-platform system works with a database of digital representations related to surgical materials supplied by their manufacturers.

5.1. Contraindications

No contraindications specific to this device.

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

Image /page/6/Picture/1 description: The image shows the logo for PeekMed. The logo is a stylized, geometric shape in blue, resembling a cube with a section cut out to form the shape of an eye. Below the geometric shape, the word "PeekMed" is written in a simple, sans-serif font, also in blue. The logo is clean and modern, suggesting a focus on vision or medical imaging.

5.2 Indications for Use Comparison

There are NO differences between the indications for use of this device and its predicate.

6. Technological Comparison to Predicate

PeekMed web was compared to its respective predicate device in intended use, indications for use, design, function, and technology and it was demonstrated that they are substantially equivalent. Any technological differences within this 510(k), between the subject device and the predicate device, do not impact substantial equivalence, or safety and effectiveness.

The subject device and its predicate are both medical software that allows healthcare professionals to perform orthopedic pre-surgical planning efficiently in the musculoskeletal system of adults in a healthcare environment, therefore sharing the same intended user and intended patient population. To properly and fully use both devices, clinical judgment, and experience are mandatory.

Both devices have the same workflows, use requirements (e.g., internet connection, output validation), and planning features (e.g., model representation, digital overlap of prosthetic material, possible 2D and 3D environments). Both devices generate a final report of the planning which consists of the selected images with templates, measurements, and textual information describing the patient and/or the surgical procedure to be performed.

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

Image /page/7/Picture/1 description: The image shows the logo for PeekMed. The logo is a stylized blue square with a white eye in the center. Below the logo, the word "PeekMed" is written in blue font. The logo is simple and modern.

Table 1: Summary of Predicate and Subject Device Characteristics to Demonstrate Substantial Equivalence

Characteristic	PeekMed webPredicate device K240926	PeekMed webSubject device	SubstantiallyEquivalent?	Justification and rationale
Product Code	QIH, LLZ	LLZ, QIH	Yes	---
RegulationNumber	21 CFR 892.2050	21 CFR 892.2050	Yes	---
Regulation Name	Medical Image Management AndProcessing System	Medical Image Management AndProcessing System	Yes	---
Intendeduse/Indications foruse	PeekMed web is a system designed tohelp healthcare professionals carry outpre-operative planning for several surgicalprocedures, based on their importedpatients' imaging studies. Experience inusage and a clinical assessment isnecessary for the proper use of thesystem in the revision and approval of theoutput of the planning. The multi-platformsystem works with a database of digitalrepresentations related to surgicalmaterials supplied by their manufacturers.This medical device consists of a decisionsupport tool for qualified healthcareprofessionals to quickly and efficientlyperform the pre-operative planning forseveral surgical procedures, usingmedical imaging with the additional	PeekMed web is a system designed tohelp healthcare professionals carry outpre-operative planning for several surgicalprocedures, based on their importedpatients' imaging studies. Experience inusage and a clinical assessment isnecessary for the proper use of the systemin the revision and approval of the outputof the planning. The multi-platform systemworks with a database of digitalrepresentations related to surgicalmaterials supplied by their manufacturers.This medical device consists of a decisionsupport tool for qualified healthcareprofessionals to quickly and efficientlyperform the pre-operative planning forseveral surgical procedures, using medicalimaging with the additional capability of	Yes	---
Characteristic	PeekMed webPredicate device K240926	PeekMed webSubject device	SubstantiallyEquivalent?	Justification and rationale
	capability of planning the 2D or 3Denvironment. The system is designed forthe medical specialties within surgery andno specific use environment is mandatory,whereas the typical use environment is aroom with a computer. The patient targetgroup is adult patients who have an injuryor disability diagnosed previously. Thereare no other considerations for theintended patient population.	planning the 2D or 3D environment. Thesystem is designed for the medicalspecialties within surgery and no specificuse environment is mandatory, whereasthe typical use environment is a room witha computer. The patient target group isadult patients who have an injury ordisability diagnosed previously. There areno other considerations for the intendedpatient population.
Contraindications	No contraindications specific to thisdevice.	No contraindications specific to this device	Yes	---
Clinical purpose	PeekMed web allows the surgeon toperform orthopedic pre-surgical planningefficiently in the musculoskeletal system(e.g., Hip procedures, Knee procedures)	PeekMed web allows the surgeon toperform orthopedic pre-surgical planningefficiently in the musculoskeletal system(e.g., Hip procedures, Knee procedures)	Yes	---
Anatomical regions	PeekMed web allows the surgeon toperform the pre-surgical planningefficiently in the following anatomicalregions:- Hip- Knee- Upper limb- Foot	PeekMed web allows the surgeon toperform the pre-surgical planning efficientlyin the following anatomical regions:- Hip- Knee- Upper limb- Foot	Yes	---
Patient Population	Adults	Adults	Yes	---
Characteristic	PeekMed webPredicate device K240926	PeekMed webSubject device	SubstantiallyEquivalent?	Justification and rationale
End users	Healthcare Professionals	Healthcare Professionals	Yes	---
Device availability	Software is cloud-based (not installable)and can be displayed on any personaldevice or workstation that can run on aweb browser	Software is cloud-based (not installable)and can be displayed on any personaldevice or workstation that can run on aweb browser	Yes	---
SoftwareArchitecture	Distributed system (cloud-based). Thisdistributed system is a combination ofsoftware modules placed on servers thatare able to communicate with each other.	Distributed system (cloud-based). Thisdistributed system is a combination ofsoftware modules placed on servers thatare able to communicate with each other.	Yes	---
Workflow	The workflow is as follows: Import caseimages, configure images, identify thecase, pre-surgical planning, and exportthe case.	The workflow is as follows: Import caseimages, configure images, identify thecase, pre-surgical planning, and export thecase.	Yes	---
Internet connection	Required	Required	Yes	---
Images source	Receives medical images from varioussources	Receives medical images from varioussources	Yes	---
Data processing	The software processes data to providean overlap and dimensioning of digitalrepresentations of the prosthetic material	The software processes data to provide anoverlap and dimensioning of digitalrepresentations of the prosthetic material	Yes	---
Digital overlap oftemplates	Allows the overlap of models and theintersection of the models	Allows the overlap of models and theintersection of the models	Yes	---
Interactive modelpositioning	Yes	Yes	Yes	---
Interactive model	Yes	Yes	Yes	---
Characteristic	PeekMed webPredicate device K240926	PeekMed webSubject device	SubstantiallyEquivalent?	Justification and rationale
dimensioning
Model rotation	Yes	Yes	Yes	---
Support for digitalprostheticmaterials providedby themanufacturers	Yes	Yes	Yes	---
Pre-surgicalplanning	Yes	Yes	Yes	---
Type ofpre-surgicalplanning	Automatic or Manual	Automatic or Manual	Yes	---
Contact with thepatient	No	No	Yes	---
Control of lifesupporting devices	No	No	Yes	---
Humanintervention forimageinterpretation	Yes	Yes	Yes	---
Ability to addadditional moduleswhen available	Yes	Yes	Yes	---
Automatic bone	Yes	Yes	Yes	The subject device includes new ML
Characteristic	PeekMed webPredicate device K240926	PeekMed webSubject device	SubstantiallyEquivalent?	Justification and rationale
segmentation	- Hip (X-ray and CT scan)- Knee (X-ray and CT scan)- Upper limb (CT scan)- Foot (CT scan)	- Hip (X-ray and CT scan)- Knee (X-ray and CT scan)- Upper limb (CT scan)- Foot (X-ray and CT scan)		model variants for segmentation.Both devices allow the planning forfoot region with CT scans but thesubject device also allows with X-rayimages.This does not constitute an intendedpurpose update nor does it raisequestions of safety and performance,since the development, verification,validation, and deployment processesare the same for both devices.
Type oflandmarking	Automatic or Manual- Hip (X-ray and CT scan)- Knee (X-ray and CT scan)- Upper limb (CT scan)- Foot (CT scan)	Automatic or Manual- Hip (X-ray and CT scan)- Knee (X-ray and CT scan)- Upper limb (CT scan)- Foot (X-ray and CT scan)	Yes	The subject device includes new MLmodel variants for landmarking.Both devices allow the planning forfoot region with CT scans but thesubject device also allows with X-rayimages.This does not constitute an intendedpurpose update nor does it raisequestions of safety and performance,since the development, verification,validation, and deployment processesare the same for both devices.

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

Image /page/8/Picture/1 description: The image shows the logo for PeekMed. The logo is a blue, stylized eye inside of a geometric shape that resembles a cube with a section cut out. Below the symbol is the text "PeekMed" in a simple, sans-serif font, also in blue.

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

Image /page/9/Picture/1 description: The image shows the logo for PeekMed. The logo is a blue, stylized cube with a white eye in the center. The text "PeekMed" is written in blue below the cube. The logo is simple and modern.

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

Image /page/10/Picture/1 description: The image contains the logo for PeekMed. The logo features a stylized, geometric shape in blue, resembling a cube or a multifaceted object. Within the shape, there is a white eye symbol, suggesting a focus on vision or medical imaging. Below the geometric shape, the text "PeekMed" is written in a simple, sans-serif font, also in blue.

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

Image /page/11/Picture/1 description: The image shows the logo for PeekMed. The logo is a blue, three-dimensional shape that resembles a stylized eye. The word "PeekMed" is written in blue below the shape. The logo is simple and modern.

PeekMed web shares the same intended use, indications for use, end has patient population, and overall technical and functional capabilities, and therefore is substant to the predicate device. The subject device has the same design and

510(k) Summary - PeekMed web

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

Image /page/12/Picture/1 description: The image contains the logo for PeekMed. The logo features a stylized, geometric shape in blue, resembling a cube with a cutout in the center. Within the cutout, there is an eye symbol. Below the geometric shape, the text "PeekMed" is written in a simple, sans-serif font, also in blue.

function as the predicate device for the modes of operation and use. The subject device includes newimproved ML models and variants.

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

Image /page/13/Picture/1 description: The image shows the logo for PeekMed. The logo is a stylized, geometric shape in blue, resembling a cube or a three-dimensional square. Within the shape, there is a white space that forms the outline of an eye. Below the geometric shape, the word "PeekMed" is written in a simple, sans-serif font, also in blue.

7. Performance Data

Nonclinical performance testing performed on the subject device, PeekMed web, supports substantial equivalence to the predicate device. The following testing was performed on the subject device:

A. Verification activities to ensure that features were implemented following the requirements and covering the acceptance criteria.
B. ML models incorporated into the PeekMed web were also developed, trained, tested, and externally validated for their performance according to the internal procedures.
- A dedicated validation dataset containing different data from the ML development o dataset was used. Specifically, the validation dataset was not a sampling of the development dataset, has never been used for the algorithm training or for tunning the algorithm, and leakage between development and validation data sets did not occur.

Training, development, testing and external validation data information

ML models were developed with datasets from multiple sites in a total of 2852 CR datasets, and 1903 CT scans. We trained the ML models with 80% of the datasets, developed with 10%, and tested with the remaining 10%. External validation is performed by sample size with a total unique dataset, for segmentation ML model: 375; Landmarking ML model: 345; Classification ML model: 347; and Detection ML model: 198. This comprehensive dataset was designed to cover the intended use population while ensuring a variety of data maintaining diverse patient characteristics.

Subgroup definition (generalizability)

Datasets were divided according to the subgroups listed below:

. Demographics
- · Patient Sex
- o Patient Age
Equipment and Protocols for Image Collection ●
- Institution Name O
- O Manufacturer
- O Manufacturer Model Name

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

Image /page/14/Picture/1 description: The image shows the logo for PeekMed. The logo is a stylized, teal-colored cube with a white eye shape in the center. Below the cube is the text "PeekMed" in a simple, sans-serif font, also in teal. The logo is clean and modern, suggesting a focus on vision or medical imaging.

Acceptance criteria

The acceptance criteria for each ML model are shown in the following table:

ML model	Acceptance Criteria
Segmentation	DICE is no less than 90%HD-95 is no more than 8STD DICE is between +/- 10%Precision is more than 85%Recall is more than 90%
Landmarking	MRE is no more than 7mmSTD MRE is between +/- 5mm
Classification	Accuracy is no less than 90%.Precision is no less than 85%Recall is no less than 90%F1 score is no less than 90%
Detection	MAP is no less than 90%.Precision is no less than 85%Recall is no less than 90%

Reference Standard ("Truthing" Process)

Comparison of the efficacy results of the Segmentation ML model using the testing and external validation datasets against the predefined ground truth met the acceptance criteria for ML model performance, demonstrating the substantial equivalence of the subject device to its predicate.

Comparison of the efficacy results of the Landmarking ML model using the testing and external validation datasets against the predefined ground truth met the acceptance criteria for ML model performance, demonstrating the substantial equivalence of the subject device to its predicate.

Comparison of the efficacy results of the Classification ML model using the testing and external validation datasets against the predefined ground truth met

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

Image /page/15/Picture/1 description: The image shows the logo for PeekMed. The logo is a stylized eye inside of a blue geometric shape that resembles a cube with a section cut out. Below the geometric shape, the text "PeekMed" is written in a simple, sans-serif font, also in blue.

the acceptance criteria for ML model performance, demonstrating the substantial equivalence of the subject device to its predicate.

Comparison of the efficacy results of the Detection ML model using the testing and external validation datasets against the predefined ground truth met the acceptance criteria for ML model performance, demonstrating the substantial equivalence of the subject device to its predicate.

Independence of Training and External Validation Data

External validation datasets were collected independently of the development data to prevent bias, ensuring the reliability of the results. For the external validation, a fully independent dataset, labeled by a separate team, was employed to provide an accurate assessment of the model's performance, over the whole population and for each sub-group mentioned before to prove that it generalizes well to unseen, real-world data. All the testing and external validation performed indicate acceptable performances of the ML models for its intended population.

C. Validation tests were performed internally before the release to the market by qualified personnel, in an environment simulating the real end-user environment. This validation follows a pre-defined test script document, according to the tests defined in the TestRail.
Nonclinical performance testing allowed us to understand that there are no related problems in the subject device. Furthermore, these tests will be repeated and updated when appropriate to ensure that the software is always properly validated, making it possible to understand in which version the problems arise and in which they are solved. Consequently, any problem that may appear in a given PeekMed web version will be identified and can be solved in subsequent versions, as all steps are traceable. All anatomical areas were tested, as well as other main areas of the software, such as the planning final report, and saved planning, ML models, among others.

After these successful validation tests, it is possible to deem the subject device, PeekMed web, as substantially equivalent to its predicate device.

{16}------------------------------------------------

Image /page/16/Picture/1 description: The image is a logo for PeekMed. The logo features a stylized eye inside of a geometric shape. The text "PeekMed" is written below the shape in a simple sans-serif font. The color of the logo is a light blue.

9. Conclusion

Based on the information provided in this 510(k) submission, it was determined that the subject device, PeekMed web, is substantially equivalent to the legally marketed predicate device concerning indications for use, intended use, design, technology, and performance.

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).