IB Lab LAMA
Device Facts
| Record ID | K223646 |
|---|---|
| Device Name | IB Lab LAMA |
| Applicant | Ib Lab GmbH |
| Product Code | QIH · Radiology |
| Decision Date | Jun 16, 2023 |
| Decision | SESE |
| Submission Type | Traditional |
| Regulation | 21 CFR 892.2050 |
| Device Class | Class 2 |
| Attributes | AI/ML, Software as a Medical Device |
AI Performance
| Output | Algorithm | Acceptance | Observed | Dev DS | Dev Readers | Test DS | Test Readers |
|---|---|---|---|---|---|---|---|
| Mechanical axis deviation | Convolutional neural networks | — | Mean Diff: -1.37 mm, Std. Dev: 2.54 mm | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Femur length | Convolutional neural networks | — | Mean Diff: 0.09 cm, Std. Dev: 0.16 cm | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Tibia length | Convolutional neural networks | — | Mean Diff: 0.01 cm, Std. Dev: 0.13 cm | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Leg length | Convolutional neural networks | — | Mean Diff: 0.05 cm, Std. Dev: 0.12 cm | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Leg length discrepancy | Convolutional neural networks | — | Mean Diff: 0.13 mm, Std. Dev: 1.4 mm | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Hip knee ankle angle | Convolutional neural networks | — | Mean Diff: -0.19 °, Std. Dev: 0.73 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Anatomical tibiofemoral angle | Convolutional neural networks | — | Mean Diff: -0.51 °, Std. Dev: 1.18 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Anatomical mechanical angle | Convolutional neural networks | — | Mean Diff: 0.06 °, Std. Dev: 0.89 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Joint-line convergence angle | Convolutional neural networks | — | Mean Diff: 0.22 °, Std. Dev: 1.35 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Mechanical lateral proximal femoral angle | Convolutional neural networks | — | Mean Diff: 2.48 °, Std. Dev: 2.45 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Mechanical lateral distal femoral angle | Convolutional neural networks | — | Mean Diff: -0.37 °, Std. Dev: 0.96 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Mechanical medial proximal tibia angle | Convolutional neural networks | — | Mean Diff: -0.01 °, Std. Dev: 1.28 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Mechanical lateral distal tibia angle | Convolutional neural networks | — | Mean Diff: -0.62 °, Std. Dev: 2.05 ° | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
| Arthroplasty detection | Convolutional neural networks | — | Sensitivity: 95.05%, Specificity: 99.80% | — | — | Standalone performance study: 189 radiographs of bilateral AP lower extremity radiographs resulting in 325 legs | 2 (US Board certified musculoskeletal radiologists) |
Indications for Use
IB Lab LAMA is a fully-automated radiological image processing software device intended to aid users in the measurement of limb-length discrepancy and quantitative knee alignment parameters on uni- and bilateral AP full leg radiographs of individuals at least 22 years of age. It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The software device is intended to be used by healthcare professionals trained in radiology.
Device Story
IB Lab LAMA is a fully-automated radiological image processing software; inputs are uni- or bilateral AP full leg radiographs (CR, DX, SC formats). Device uses deep learning (CNNs) for landmark detection, segmentation, and classification; classical methods compute auxiliary points, lengths, and angles. Outputs are human/machine-readable DICOM reports containing measurements (e.g., mechanical axis deviation, leg length discrepancy, HKA angle). Used in clinical settings by radiologists/healthcare professionals; integrated via PACS/third-party viewers. User reviews and accepts/rejects findings. Device aids in assessing lower extremity deformities; does not replace clinical evaluation or diagnosis.
Clinical Evidence
Standalone performance study (SPT) using 189 radiographs (325 legs) from US clinical sites. Ground truth established by two board-certified musculoskeletal radiologists. Primary endpoints: agreement between LAMA and ground truth (Bland-Altman, ICC). Results showed high agreement across all metrics (e.g., HKA mean diff -0.19°, LLD mean diff 0.13mm). Secondary objective: Arthroplasty detection sensitivity 95.05% (90.29-98.96% CI), specificity 99.80% (99.39-100.00% CI). Failure rate 2.8%. Repeatability testing showed no differences in repeated runs.
Technological Characteristics
Software-based image processing; operates on OTS hardware in Linux/Docker environment. Uses CNNs for classification, landmarking, and segmentation; classical methods for geometric calculations. DICOM-compliant input/output. Moderate level of concern software. No patient contact; no life-sustaining function.
Indications for Use
Indicated for adults (≥22 years) requiring measurement of limb-length discrepancy and quantitative knee alignment on AP full leg radiographs. Contraindicated for radiographs with Ankle Arthroplasties or Unicompartmental Knee Arthroplasties.
Regulatory Classification
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.
Special Controls
*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).
Predicate Devices
- KOALA (K192109)
Submission Summary (Full Text)
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
IB Lab GmbH % Richard Ljuhar Official Correspondent Zehetnergasse 6/2/2 Vienna, 1140 AUSTRIA
June 16, 2023
Re: K223646
Trade/Device Name: IB Lab LAMA Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QIH Dated: May 17, 2023 Received: May 17, 2023
Dear Richard Ljuhar:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801 and Part 809); medical device reporting of medical device-related adverse events) (21 CFR
{1}------------------------------------------------
803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely.
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
{2}------------------------------------------------
#### Indications for Use
510(k) Number (if known) K223646
Device Name IB Lab LAMA
IB Lab LAMA is a fully-automated radiological image processing software device intended to aid users in the measurement of limb-length discrepancy and quantitative knee alignment parameters on uni- and bilateral AP full leg radiographs of individuals at least 22 years of age. It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The software device is intended to be used by healthcare professionals trained in radiology.
IB Lab LAMA is not indicated for use on radiographs on which Ankle Arthroplasties and/or Unicompartmental Knee Arthroplasties are present.
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."
Form Approved: OMB No. 0910-0120 Expiration Date: 06/30/2023 See PRA Statement below.
{3}------------------------------------------------
Summary Premarket Notification 510(k) IB Lab LAMA
Image /page/3/Picture/2 description: The image shows the logo for Image Biopsy Lab. On the left is a red pixelated image that resembles a space invader. To the right of the pixelated image is the text "image biopsy lab" in red sans-serif font.
# 510(k) Summary
The following 510(k) summary has been prepared pursuant to requirements specified in 21CFR 807.92(a).
| Submitter Information 807.92(a)(1) | |
|------------------------------------|----------------------------------------------------------------------------------------|
| IB Lab GmbH | |
| Zehetnergasse | |
| 6/2/2 | |
| A-1140 Vienna | |
| Austria | |
| Phone: | +43 1 61 067 12 |
| Fax: | +43 1 90 512 09 |
| Contact Person: | Dr. Richard Ljuhar |
| Date: | 02. December 2022 |
| 807.92(a)(2) | |
| Trade Name: | IB Lab LAMA |
| Common Name: | Al supported Leg Geometry Measurement Assistant |
| Classification Name(s): | Medical image management and processing system<br>(per 21 CFR section 21 CFR 892.2050) |
| Product Code: | OIH |
#### Predicate Devices/ Reference Devices 807.92(a)(3)
| | predicate device |
|------------------------------------|------------------------------------------------------------|
| Manufacturer: | IB Lab GmbH<br>Zehetnergasse 6/2/2<br>1140 Wien<br>Austria |
| Trade Name | KOALA |
| 510(k) document control number | K192109 |
| Device Class | Class II |
| Granted marketing clearance by FDA | Yes |
| Product code | LLZ/892.2050,<br>JAK/892.1750 |
| Clearance Date | November 6, 2019 |
{4}------------------------------------------------
Image /page/4/Picture/1 description: The image shows the logo for Image Biopsy Lab. The logo consists of a pixelated red icon on the left and the words "image biopsy lab" in red on the right. The pixelated icon resembles a stylized face or creature made up of red squares.
#### Device Description 807.92(a)(4)
IB Lab LAMA uses deep learning technology to provide precise fully-automated geometric length and angle measurements of the lower limb on full leg X-ray images. The outputs aid healthcare professionals who are interested in the analysis of leg-length discrepancy and knee alignment in adult patients with suspected or present deformities of the lower extremities. IB Lab LAMA provides the following measurements:
- mechanical axis deviation .
- full leg length .
- femur length ●
- tibia length
- leg length discrepancy ●
- hip knee ankle angle
- anatomical tibiofemoral angle
- anatomical mechanical angle
- joint-line convergence angle
- mechanical lateral proximal femoral angle
- mechanical lateral distal femoral angle
- mechanical medial proximal tibia angle
- mechanical lateral distal tibia angle ●
The user does not interact directly with IB Lab LAMA except or reject the generated report findings via cleared third party medical viewers. The measurements are compared to fixed predetermined norm-ranges, based on standard state of the art clinical practices hard-coded into the software. Outputs are summarized in reports that can be viewed on any cleared medical DICOM viewer. IB Lab LAMA operates in a Linux environment and can be deployed on any operating system that supports the third-party software Docker. The integration environment has to support IB Lab LAMA data input and output requirements. The device does not interact with the patient directly, nor does it control any life-sustaining devices.
#### Intended Use / Indications for Use 807.92(a)(5)
IB Lab LAMA is a fully-automated radiological image processing software device intended to aid users in the measurement of limb-length discrepancy and quantitative knee alignment parameters on uni- and bilateral AP full leq radiographs of individuals at least 22 years of age. It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. The software device is intended to be used by healthcare professionals trained in radiology.
{5}------------------------------------------------
Image /page/5/Picture/1 description: The image shows the logo for Image Biopsy Lab. The logo consists of a pixelated red square on the left and the words "image biopsy lab" in red on the right. The pixelated square is made up of smaller red squares, arranged in a pattern that resembles a face. The words "image biopsy lab" are stacked on top of each other, with "image" on the top line, "biopsy" on the second line, and "lab" on the bottom line.
IB Lab LAMA is not indicated for use on radiographs on which Ankle Arthroplasties and/or Unicompartmental Knee Arthroplasties are present.
{6}------------------------------------------------
Image /page/6/Picture/1 description: The image contains the logo for "image biopsy lab". The logo consists of a pixelated red figure on the left and the text "image biopsy lab" on the right. The text is also in red and is stacked vertically.
## Comparison of the Technological Characteristics with the Predicate Devices 807.92(a)(6)
| Characteristic | KOALA | IB Lab LAMA | Discussion of Differences |
|---------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| | IB Lab GmbH | IB Lab GmbH | |
| | Predicate Device (K192109) | Subject Device | |
| Indications for use | IB Lab KOALA is a radiological<br>fully-automated image processing<br>software device of either computed<br>(CR) or directly digital (DX) images<br>intended to aid medical<br>professionals in the measurement of<br>minimum joint space width; the<br>assessment of the presence or<br>absence of sclerosis, joint space<br>narrowing, and osteophytes based<br>OARSI criteria for these parameters;<br>and, the presence or absence of<br>radiographic knee OA based on<br>Kellgren & Lawrence Grading of<br>standing, fixed-flexion radiographs<br>of the knee. It should not be used<br>in-lieu of full patient evaluation or<br>solely relied upon to make or<br>confirm a diagnosis. The system is to<br>be used by trained professionals<br>including, but not limited to,<br>radiologists, orthopedics, physicians<br>and medical technicians. | IB Lab LAMA is a fully-automated<br>radiological image processing software<br>device intended to aid users in the<br>measurement of limb-length discrepancy<br>and quantitative knee alignment<br>parameters on uni- and bilateral AP full leg<br>radiographs of individuals at least 22 years<br>of age. It should not be used in-lieu of full<br>patient evaluation or solely relied upon to<br>make or confirm a diagnosis. The software<br>device is intended to be used by healthcare<br>professionals trained in radiology.<br>IB Lab LAMA is not indicated for use on<br>radiographs on which Ankle Arthroplasties<br>and/or Unicompartmental Knee<br>Arthroplasties are present. | The subject device performs measurements of lengths<br>and angles on full leg images. The predicate device<br>performs length and grade measurements on knee<br>images. This difference in specific anatomic locations<br>does not raise new types of questions for safety or<br>effectiveness and therefore does not induce changes in<br>the intended use. For both devices, the key question is<br>whether the software is able to generate accurate and<br>reproducible anatomical measurements within the<br>target population. |
{7}------------------------------------------------
Image /page/7/Picture/1 description: The image contains a logo for "image biopsy lab". The logo consists of a pixelated graphic on the left and the text "image biopsy lab" on the right. The pixelated graphic is made up of red squares arranged in a somewhat abstract shape. The text is also in red and is stacked vertically.
| Characteristic | KOALA | IB Lab LAMA | Discussion of Differences |
|------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| | IB Lab GmbH | IB Lab GmbH | |
| | Predicate Device (K192109) | Subject Device | |
| | | | |
| Product code | LLZ/892.2050, JAK/892.1750 | QIH/892.2050 | Similar. The product code QIH was not yet available<br>when the predicate was cleared. |
| Human Intervention<br>for interpretation | Required | Required | Same. |
| | | | |
| | | | |
| Image Requirements | DICOM compliant images collected | DICOM compliant plain radiographs | Similar. This difference does not raise new questions |
| | in other devices in either digitally | collected in other devices in the CR, DX, SC | about safety since the additional format SC is |
| | computed (CR) or directly digital | formats. | standardly used for processed DICOM images. For |
| | (DX) formats | | long-leg radiographs post-processing is the standard |
| | | | since the images are generally assembled by cleared<br>medical software. |
| Anatomical area | knee | full leg | Similar. The anatomical region does not raise new |
| | | | questions regarding safety or effectiveness with |
| | | | respect to the technological characteristics. The |
| | | | techniques used for capturing full leg images and knee |
| | | | images are both standard procedures. |
| Workflow / Principles<br>of Operation | 1. User or PACS sends image<br>to device | 1. User or PACS sends image to<br>device | Same. |
| | 2. Device performs analysis | 2. Device performs analysis | |
| | 3. Image is sent back to PACS | 3. Image is sent back to PACS | |
| | 4. User reviews and | 4. User reviews and accepts/rejects | |
| | accepts/rejects report | report | |
| Characteristic | KOALA<br>IB Lab GmbH<br>Predicate Device (K192109) | IB Lab LAMA<br>IB Lab GmbH<br>Subject Device | Discussion of Differences |
| Processing<br>Architecture | 1. Pre-process the input image<br>2. Classify uni or bilateral image<br>3. Compute regions of interest for each side.<br>4. Detect landmarks and segmentations<br>5. Compute distances<br>6. Compute OA parameters<br>7. Generate reports | 1. Pre-process the input image<br>2. Classify uni or bilateral image<br>3. Compute regions of interest for each side.<br>4. Detect landmarks and segmentations<br>5. Compute lines and distances<br>6. Compute angles<br>7. Generate reports | 1. Same.<br>2. Same.<br>3. Same.<br>4. Same.<br>5. Similar. The subject also visualizes lines of which distances are measured and thus raises no new questions regarding safety and effectiveness. Standalone performance testing is performed to show that the subject device performs as intended. See Section 20: Performance Testing - Clinical.<br>6. The predicate measures OA parameters (grades), while the subject computes angles. Standalone performance testing is performed to show that the subject device performs as intended. See Section 20: Performance Testing - Clinical.<br>7. Same |
| Technology | ● Convolutional neural<br>networks for<br>○ classification<br>○ landmarking<br>○ segmentation<br>○ grading | ● Convolutional neural networks for<br>○ classification<br>○ landmarking<br>○ segmentation<br>● Classical methods for computing:<br>○ auxiliary points<br>○ lengths | ● Similar. The technology of the subject device is contained in the predicate and thus raises no new questions regarding safety and effectiveness. Standalone performance testing is performed to show that the subject device performs as intended. See Section 20: Performance Testing - Clinical |
| Characteristic | KOALA<br>IB Lab GmbH<br>Predicate Device (K192109) | IB Lab LAMA<br>IB Lab GmbH<br>Subject Device | Discussion of Differences |
| | Classical methods for computing: auxiliary points lengths | angles | Similar. Angles are computed using standard classical methods from lines and thus raises no new questions regarding safety and effectiveness. Standalone performance testing is performed to show that the subject device performs as intended. See Section 20: Performance Testing - Clinical. |
| Output | Human and machine readable reports in the DICOM format | Human and machine readable reports in the DICOM format | Same. |
| Physical<br>Characteristics | Software application operated on OTS hardware. | Software application operated on OTS hardware. | Same. |
| Safety | displayed warnings | displayed warnings | Same. |
| | intended user: qualified and trained healthcare professionals | intended user: qualified and trained healthcare professionals | Same. |
| | Automated input checks: Dicom tags check | Automated input checks: Dicom tags check | Same. |
{8}------------------------------------------------
Image /page/8/Picture/1 description: The image shows the logo for Image Biopsy Lab. The logo consists of a pixelated red graphic on the left and the words "image biopsy lab" in red on the right. The pixelated graphic is made up of red squares arranged in a pattern. The text is stacked vertically, with "image" on top, "biopsy" in the middle, and "lab" on the bottom.
{9}------------------------------------------------
Image /page/9/Picture/1 description: The image contains a logo for "image biopsy lab". On the left side of the logo is a pixelated image that is red and white. The text "image biopsy lab" is in red and is to the right of the pixelated image. The text is stacked on top of each other.
{10}------------------------------------------------
Image /page/10/Picture/1 description: The image contains a logo for "image biopsy lab". The logo consists of a pixelated red square design on the left and the text "image biopsy lab" on the right. The text is also in red and uses a simple, sans-serif font.
#### 807.92(b)(1)
Product verification and validation testing was completed for the subject device.
The non-clinical tests included unit, integration testing as well as system level tests. The performance of the individual deep-neural networks was tested on hold-out sets. The performance of the software outputs was not tested in this non-clinical setting. Product validation was performed via questionnaires.
The software functioned as intended and all results observed were as expected. The device documentation was created in accordance with the FDA Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices (2005) for a Moderate Level of Concern software. All software requirements and risk analysis have been successfully verified and traced.
### 807.92(b)(2)
To validate the outputs of IB Lab LAMA, a clinical data-based standalone performance study was conducted in the U.S. The Standalone performance testing (SPT) was performed on an image dataset composed of 189 radiographs of bilateral AP lower extremity radiographs of adults, with and without hip or knee implants, obtained from US clinical sites affiliated with the University of Texas Southwestern Medical Center (UTSW) resulting in 325 legs.
The ground truths for the measurements were independently established by two US Board certified musculoskeletal radiologists with at least 5 years post-fellowship expertise in the assessment of lower limb length and alignment on AP lower extremity radiographs, without using IB Lab LAMA outputs. The truthers were further blinded to the assessments from the clinical report as well as the readings from the other truther measurements were averaged to form the ground truth. If any pair of assessments differs by more than the threshold defined in the Test-Plan, the respective leg was consensus read by the two truthers in order to establish a reliable ground truth.
The SPT compares IB Lab LAMA's angle and length measurements to the ground truth using Bland-Altman plots, and by computing the interchangeability and intra-class correlation coefficient (ICC) for each measurement.
| IB Lab LAMA vs. GT - Primary Objective: Agreement | | | | | | |
|---------------------------------------------------|------|------|------------|-----------|--------------|--------------|
| Variable | Unit | No.1 | Mean Diff. | Std. Dev. | Lower<br>LOA | Upper<br>LOA |
<sup>4</sup> For the LLD measurement the No. column corresponds to the number of images. For all other measurements it corresponds to the number of legs.
IB Lab GmbH, Zehetnergasse 6/2/2, A-1140 Vienna, Austria Tel +43 1 90 512 06, Fax +43 1 90 512 09, mail@imagebiopsy.com, www.imagebiopsylab.com
{11}------------------------------------------------
Summary Premarket Notification 510(k) IB Lab LAMA
Image /page/11/Picture/1 description: The image shows the logo for Image Biopsy Lab. The logo consists of a red pixelated image on the left and the words "image biopsy lab" in red on the right. The pixelated image is a square shape with some of the pixels missing, creating a unique design.
| | | | | | (lower CI) | (upper CI) |
|--------------|------|-----|-------|------|------------|------------|
| MAD | [mm] | 244 | -1.37 | 2.54 | -6.89 | 4.15 |
| Femur Length | [cm] | 208 | 0.09 | 0.16 | -0.26 | 0.45 |
| Tibia Length | [cm] | 244 | 0.01 | 0.13 | -0.27 | 0.28 |
| Leg Length | [cm] | 208 | 0.05 | 0.12 | -0.23 | 0.32 |
| LLD | [mm] | 77 | 0.13 | 1.4 | -3.16 | 3.43 |
| HKA | [°] | 244 | -0.19 | 0.73 | -1.79 | 1.4 |
| aTFA | [°] | 244 | -0.51 | 1.18 | -3.08 | 2.05 |
| AMA | [°] | 244 | 0.06 | 0.89 | -1.88 | 1.99 |
| JLCA | [°] | 244 | 0.22 | 1.35 | -2.72 | 3.15 |
| mLPFA | [°] | 208 | 2.48 | 2.45 | -2.89 | 7.85 |
| mLDFA | [°] | 244 | -0.37 | 0.96 | -2.46 | 1.72 |
| mMPTA | [°] | 244 | -0.01 | 1.28 | -2.79 | 2.77 |
| mLDTA | [°] | 244 | -0.62 | 2.05 | -5.08 | 3.85 |
| IB Lab LAMA - Secondary Objective | |
|--------------------------------------|-------------------|
| Arthroplasty Detection (TKA and THA) | |
| Sensitivity | Specificity |
| 95.05% | 99.80% |
| (90.29%, 98.96%) | (99.39%, 100.00%) |
| Failure Rate | |
IB Lab GmbH, Zehetnergasse 6/2/2, A-1140 Vienna, Austria Tel +43 1 90 512 06, Fax +43 1 90 512 09, mail@imagebiopsy.com, www.imagebiopsylab.com
{12}------------------------------------------------
Summary Premarket Notification 510(k) IB Lab LAMA
Image /page/12/Picture/1 description: The image contains the logo for Image Biopsy Lab. The logo consists of a pixelated red icon resembling a retro video game character or abstract design. To the right of the icon, the text "image biopsy lab" is arranged vertically, with each word on a separate line, also in red. The overall design is simple and modern, with a focus on the company's name and a visual element that suggests technology or data analysis.
n = 9 of 324 legs failed; failure rate ~ 2.8 % (5%)
Repeatability Testing
No differences between repeated runs.
In summary, the standalone performance testing results demonstrate that IB Lab LAMA provides clinically relevant measurements of angles and lengths on long leg radiographs. The standalone performance testing results establish that IB Lab LAMA is an effective image processing device that provides reliable measurements of angles and lengths. Thus, the device performs as intended and is substantially equivalent to the predicate device.
#### Conclusion 807.92(b)(3)
IB Lab LAMA is as safe and effective as the predicate device. The subject device has the same intended use and principles of operation; furthermore, it has similar indications and technological characteristics as its predicate device. The minor differences between subject and predicate device in indications do not alter the intended use of the subject device and do not raise new or different questions regarding its safety and effectiveness when used as labeled. Performance data demonstrate that the device performs as intended.
Verification and validation testing, including the standalone software performance test, supports the safety of the device and demonstrates that IB Lab LAMA performs as intended. Therefore, IB Lab LAMA is substantially equivalent.
