(70 days)
Not Found
Yes
The document explicitly mentions the development, training, testing, and validation of "ML models" and provides details on the datasets used and performance metrics for these models (Segmentation ML model, Landmarking ML model, Classification ML model, and Detection ML model).
No
The device is a decision support tool for pre-operative planning and does not directly provide therapy.
No
This device is designed for pre-operative planning and decision support for surgical procedures, not for diagnosing conditions.
Yes
The device description explicitly states "Being software it does not interact with any part of the body of the user and/or patient." and the intended use describes a system for pre-operative planning based on imported imaging studies, which is a software-based function. While it relies on a computer for use, the device itself is the software system.
Based on the provided information, this device is not an In Vitro Diagnostic (IVD).
Here's why:
- IVDs are used to examine specimens derived from the human body. The intended use and device description clearly state that PeekMed web is used for pre-operative planning based on patients' imaging studies (X-ray and CT scans). These are medical images, not biological specimens like blood, urine, or tissue.
- The purpose of an IVD is to provide information for diagnosis, monitoring, or screening. PeekMed web is described as a decision support tool for pre-operative planning. While it aids in clinical decision-making, its primary function is not to diagnose a condition or monitor a patient's health status through the analysis of biological samples.
The device falls under the category of medical imaging software used for surgical planning, which is a different regulatory classification than IVDs.
No
The input states "Control Plan Authorized (PCCP) and relevant text: Not Found", which indicates the letter does not contain the required explicit approval language for a PCCP.
Intended Use / Indications for Use
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.
Product codes
QIH, LLZ
Device Description
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.
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.
Mentions image processing
Yes
Mentions AI, DNN, or ML
Yes
Input Imaging Modality
X-ray and CT scan
Anatomical Site
- Hip
- Knee
- Upper limb
- Foot
Indicated Patient Age Range
Adults
Intended User / Care Setting
Healthcare Professionals / a room with a computer
Description of the training set, sample size, data source, and annotation protocol
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%.
Description of the test set, sample size, data source, and annotation protocol
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.
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.
Summary of Performance Studies
Nonclinical performance testing was performed:
- 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 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.
- 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.
Key results: Comparison of the efficacy results of the Segmentation ML model, Landmarking ML model, Classification ML model, and 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.
Key Metrics
Segmentation ML model:
- DICE is no less than 90%
- HD-95 is no more than 8
- STD DICE is between +/- 10%
- Precision is more than 85°%
- Recall is more than 90°%
Landmarking ML model:
- MRE is no more than 7mm
- STD MRE is between +/- 5mm
Classification ML model:
- 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 ML model:
- MAP is no less than 90%.
- Precision is no less than 85%
- Recall is no less than 90%
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 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).
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)
Device Name
PeekMed web
Indications for Use (Describe)
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.
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 Silva
Chief 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
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.
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.
5. Intended Use/Indications for Use
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.
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 web
Predicate device K240926 | PeekMed web
Subject device | Substantially
Equivalent? | Justification and rationale |
|------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Product Code | QIH, LLZ | LLZ, QIH | Yes | --- |
| Regulation
Number | 21 CFR 892.2050 | 21 CFR 892.2050 | Yes | --- |
| Regulation Name | Medical Image Management And
Processing System | Medical Image Management And
Processing System | Yes | --- |
| Intended
use/Indications for
use | 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 | 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 | Yes | --- |
| Characteristic | PeekMed web
Predicate device K240926 | PeekMed web
Subject device | Substantially
Equivalent? | Justification and rationale |
| | 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. | 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. | | |
| Contraindications | No contraindications specific to this
device. | No contraindications specific to this device | Yes | --- |
| Clinical purpose | PeekMed web allows the surgeon to
perform orthopedic pre-surgical planning
efficiently in the musculoskeletal system
(e.g., Hip procedures, Knee procedures) | PeekMed web allows the surgeon to
perform orthopedic pre-surgical planning
efficiently in the musculoskeletal system
(e.g., Hip procedures, Knee procedures) | Yes | --- |
| Anatomical regions | PeekMed web allows the surgeon to
perform the pre-surgical planning
efficiently in the following anatomical
regions:
- Hip
- Knee
- Upper limb
- Foot | PeekMed web allows the surgeon to
perform the pre-surgical planning efficiently
in the following anatomical regions: - Hip
- Knee
- Upper limb
- Foot | Yes | --- |
| Patient Population | Adults | Adults | Yes | --- |
| Characteristic | PeekMed web
Predicate device K240926 | PeekMed web
Subject device | Substantially
Equivalent? | Justification and rationale |
| End users | Healthcare Professionals | Healthcare Professionals | Yes | --- |
| Device availability | Software is cloud-based (not installable)
and can be displayed on any personal
device or workstation that can run on a
web browser | Software is cloud-based (not installable)
and can be displayed on any personal
device or workstation that can run on a
web browser | Yes | --- |
| Software
Architecture | Distributed system (cloud-based). This
distributed system is a combination of
software modules placed on servers that
are able to communicate with each other. | Distributed system (cloud-based). This
distributed system is a combination of
software modules placed on servers that
are able to communicate with each other. | Yes | --- |
| Workflow | The workflow is as follows: Import case
images, configure images, identify the
case, pre-surgical planning, and export
the case. | The workflow is as follows: Import case
images, configure images, identify the
case, pre-surgical planning, and export the
case. | Yes | --- |
| Internet connection | Required | Required | Yes | --- |
| Images source | Receives medical images from various
sources | Receives medical images from various
sources | Yes | --- |
| Data processing | The software processes data to provide
an overlap and dimensioning of digital
representations of the prosthetic material | The software processes data to provide an
overlap and dimensioning of digital
representations of the prosthetic material | Yes | --- |
| Digital overlap of
templates | Allows the overlap of models and the
intersection of the models | Allows the overlap of models and the
intersection of the models | Yes | --- |
| Interactive model
positioning | Yes | Yes | Yes | --- |
| Interactive model | Yes | Yes | Yes | --- |
| Characteristic | PeekMed web
Predicate device K240926 | PeekMed web
Subject device | Substantially
Equivalent? | Justification and rationale |
| dimensioning | | | | |
| Model rotation | Yes | Yes | Yes | --- |
| Support for digital
prosthetic
materials provided
by the
manufacturers | Yes | Yes | Yes | --- |
| Pre-surgical
planning | Yes | Yes | Yes | --- |
| Type of
pre-surgical
planning | Automatic or Manual | Automatic or Manual | Yes | --- |
| Contact with the
patient | No | No | Yes | --- |
| Control of life
supporting devices | No | No | Yes | --- |
| Human
intervention for
image
interpretation | Yes | Yes | Yes | --- |
| Ability to add
additional modules
when available | Yes | Yes | Yes | --- |
| Automatic bone | Yes | Yes | Yes | The subject device includes new ML |
| Characteristic | PeekMed web
Predicate device K240926 | PeekMed web
Subject device | Substantially
Equivalent? | 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 for
foot region with CT scans but the
subject device also allows with X-ray
images.
This does not constitute an intended
purpose update nor does it raise
questions of safety and performance,
since the development, verification,
validation, and deployment processes
are the same for both devices. |
| Type of
landmarking | 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 ML
model variants for landmarking.
Both devices allow the planning for
foot region with CT scans but the
subject device also allows with X-ray
images.
This does not constitute an intended
purpose update nor does it raise
questions of safety and performance,
since the development, verification,
validation, and deployment processes
are 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 8 | |
| STD DICE is between +/- 10% | |
| Precision is more than 85% | |
| Recall is more than 90% | |
| Landmarking | MRE is no more than 7mm |
| STD 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.