The Med-Imaps TBS iNsight is a software provided for use as a complement to a DEXA analysis. It computes the antero-posterior spine DEXA examination file and calculates a score (Trabecular Bone Score - TBS) that is compared to those of the age-matched controls. The TBS is derived from the texture of the DEXA image and has been shown to be related to bone microarchitecture and fracture risk. This data provides information independent of BMD value; it is used as a complement to the data obtained from the DEXA analysis and the clinical examination (questioning by the clinician about patient history, bioassay of bone resorption markers ... ).

The TBS score can assist the health care professional in assessment of fracture risk and in monitoring the effect of treatments on patients across time.

Overall fracture risk will depend on many additional factors that should be considered before making diagnostic or therapeutic recommendations. The software does not diagnose disease, or recommend treatment regimens. Only the health care professional can make these judgments.

Device Description

TBS iNsight is a software package that provides an estimate of the trabecular bone quality based on analysis of data derived from DEXA examination. The program utilizes a quantitative bone structural algorithm that analyzes the texture of AP spine projection scans from which the Trabecular Bone Score (TBS) is mathematically derived.

The results (TBS) can be used for comparison to a reference database of age-matched controls.

AI/ML Overview

Here's an analysis of the acceptance criteria and study findings for the Medimaps Group TBS iNsight software, based on the provided 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not explicitly present a table of quantitative acceptance criteria for each validation study. Instead, it describes general objectives and qualitative outcomes for each performance bench test and clinical study. However, the conclusion states that the device "met all acceptance criteria." Based on the descriptions, we can infer the objectives that served as de-facto acceptance criteria.

Acceptance Criteria (Inferred from Study Objectives)	Reported Device Performance
Bench Tests:
Correlation between Microarchitecture (3D µCT) and TBS (Simulated 2D Projections):	Significant correlations were observed between TBS and 3D microarchitecture parameters, regardless of projection resolution.
Correlation between Microarchitecture (3D µCT) and TBS (Actual DEXA Scans):	Significant correlations were detected between TBS and 3D parameters of bone microarchitecture. The study indicated that TBS adds value and differentiation between samples with similar BMDs but different bone microarchitectures, strengthening the assumption that bone microarchitecture can be estimated from DEXA using TBS.
Ex-vivo Reproducibility of TBS:	The TBS ex-vivo precision error was lower than 0.02, the CV% was lower than 1.5%, and the least significant change was lower than 4.2%. These results demonstrate TBS is reproducible and can be used to monitor microarchitecture changes over time.
Clinical Tests:
Diagnostic Value (Differentiation of Fractured vs. Non-Fractured Patients):	In five cross-sectional studies, TBS was significantly lower in women with fractures versus without, both independently and in conjunction with BMD.
Prognostic Value (Prediction of Future Fractures):	In three longitudinal studies, spine TBS and BMD predicted fractures equally well and independently.
Monitoring Changes Across Time (In-vivo Reproducibility):	In two in-vivo reproducibility studies, the mean TBS reproducibility value (CV%) at L1-L4 achieved 1.8%, demonstrating TBS is reproducible, comparable to BMD, and adherent to ISCD rules.
Treatment Follow-up (Responsiveness to Treatment):	Results were consistent with published literature across six studies (various treatments vs. placebo/comparators), suggesting TBS is valuable for monitoring changes over time, especially for treated patients.
Age-related US Reference Data (Establish Normative Data):	Age-related normative data for non-Hispanic white US women aged 30 to 90 years was obtained. Lumbar vertebral combinations (L1, L2, L3, L4) showed significant decreases in TBS with age, reflecting age-related microarchitecture changes.

2. Sample Sizes and Data Provenance

Bench Test - µCT and Simulated Projections:
- Sample Size: Thirty human cadaveric vertebrae.
- Data Provenance: Ex-vivo (cadaveric tissue). Country of origin not specified, but the company is Swiss.
Bench Test - µCT and DEXA Scans:
- Sample Size: Thirty human cadaveric vertebrae.
- Data Provenance: Ex-vivo (cadaveric tissue). Country of origin not specified.
Bench Test - Ex-vivo Reproducibility:
- Sample Size: Not explicitly stated, but likely the same thirty human cadaveric vertebrae from the other bench tests, as it builds on them.
- Data Provenance: Ex-vivo (cadaveric tissue). Country of origin not specified.
Clinical Studies - Diagnostic Value:
- Sample Size: Evaluated through "five cross-sectional studies." Specific sample sizes for each study are not provided.
- Data Provenance: Clinical (patient data). Retrospective/Prospective not specified for each study, but typical for cross-sectional analysis in published literature. Country of origin not specified.
Clinical Studies - Prognostic Value:
- Sample Size: Evaluated through "three longitudinal studies." Specific sample sizes for each study are not provided.
- Data Provenance: Clinical (patient data). Longitudinal indicates prospective follow-up. Country of origin not specified.
Clinical Studies - In-vivo Reproducibility:
- Sample Size: "Two in-vivo reproducibility studies." Specific sample sizes not provided.
- Data Provenance: Clinical (patient data). In-vivo implies prospective. Country of origin not specified.
Clinical Studies - Treatment Follow-up:
- Sample Size: "All six studies" mentioned. Specific sample sizes not provided.
- Data Provenance: Clinical (patient data). Longitudinal and prospective (clinical trials). Country of origin not specified but likely international across multiple trials.
Clinical Studies - Age-related US Reference Data:
- Sample Size: Non-Hispanic white US women aged 30 to 90 years. Specific number of women is not provided.
- Data Provenance: Clinical (patient data). Likely retrospective collection from a US cohort.

3. Number of Experts and Qualifications for Ground Truth (Test Set)

The document does not provide details on the number of experts used to establish ground truth for the test set or their specific qualifications (e.g., radiologist with X years of experience). The ground truth for the bench tests relied on µCT measurements, which is an objective physical measurement rather than expert consensus on images. For the clinical studies, ground truth related to fracture diagnosis/prognosis and treatment effects would typically be established by clinical diagnoses, imaging reports (potentially read by radiologists, but not explicitly stated for this purpose), and follow-up data.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for establishing ground truth within the test sets. For the bench tests, the ground truth was objective µCT measurements, precluding the need for human adjudication of image interpretations. For clinical outcomes, fracture events, and treatment responses, these are typically clinical endpoints.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study is mentioned. The studies focus on the performance of TBS itself (correlations, reproducibility, diagnostic/prognostic value) rather than comparing human reader performance with and without AI assistance.

6. Standalone (Algorithm Only) Performance Study

Yes, the studies described are primarily standalone performance investigations of the TBS iNsight algorithm.

The bench tests directly assess the algorithm's ability to derive TBS values that correlate with 3D microarchitecture parameters or demonstrate ex-vivo reproducibility.
The clinical studies evaluate the direct diagnostic, prognostic, and monitoring capabilities of the calculated TBS values.
While the intended use is "as a complement to a DEXA analysis," the performance evaluation focuses on the algorithm's output (TBS) rather than its impact on a human reader's interpretation flow.

7. Type of Ground Truth Used

Bench Tests: The primary ground truth for comparing TBS to actual bone structure was 3D microarchitecture parameters derived from µCT (micro-computed tomography) datasets. This is an objective and highly detailed measure of bone structure, often considered the gold standard for microarchitectural assessment.
Clinical Studies (Diagnostic/Prognostic/Treatment/Reference Data): The ground truth for clinical studies implicitly relies on clinical outcomes data (e.g., confirmed fracture events, patient diagnoses of fracture status, observed response to treatment regimens). For the age-related reference data, the "ground truth" is the observed TBS values within that specific population.

8. Sample Size for the Training Set

The document does not specify the sample size for the training set used to develop the TBS iNsight algorithm. The provided information relates to validation studies, not algorithm development.

9. How Ground Truth for the Training Set Was Established

The document does not provide information on how the ground truth for the training set was established, as it focuses on the validation of the already developed device.

Summary

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

510K Summary Page 1 of 4 medimaps
group

This summary of the 510(k) Premarket Notification for the medimaps group TBS iNsight software is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 807.92.

The assigned 510(k) number is : _K121716

OCT 5 2012

Company:	medimaps groupChemin des aulx, 181294 Plan les OuatesSwitzerland
Telephone:	+ (41) 22 884 86 44
Fax:	+ (41) 22 884 83 00
Contact Person:	Christophe LelongChief Operations Officere-mail: clelong@med-imaps.com
Date Prepared:	June, 4, 2012
Device Names:
Trade/Proprietary Name:	TBS iNsight
Common or Usual Name:	Bone microarchitecture assessment from medical imaging
Device Class	Class II
Classification Name:	21 CFR 892.1170 - Bone Densitometer

DEVICE DESCRIPTION

Product Code:

The results (TBS) can be used for comparison to a reference database of age-matched controls.

INTENDED USE / INDICATIONS FOR USE

KGI

The TBS score can assist the health care professional in assessment of fracture risk and in monitoring the effect of treatments on patients across time.

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

PREDICATE DEVICE

: ' _

The TBS iNsight software is considered substantially equivalent to FDA cleared predicate The TDO INSIGN of the both indications for use and technological characteristics. de not with regare to to treviously acquired x-ray images to provide an estimate of the bone strength and a comparison to a normative data cohort for interpretation.

This predicate device is Imaging Therapeutics OsDx Hip BMD System, cleared under K082402.

SUBSTANTIAL EQUIVALENCE

The following table provides a more detailed substantial equivalence discussion :

	Predicate Device	Subject Device
Product Name	OsDx Hip BMD System(K082402)	TBS iNsight
Classification	Class II	Identical
Product Code	KGI	Identical
ClassificationName	Bone Densitometer	Identical
Classification Rule	21 CFR 992.1170	Identical
Device Description	The OsDx Hip BMD System is asoftware package that providesan estimate of BMD based onanalysis of data derived fromscanned hip X-rays. The programutilizes a quantitative bonestructural algorithm thatmeasures a composite ofweighted cortical and trabecularparameters in proximal femurprojection radiographs from whichtotal hip bone mineral density(BMD) is mathematically derived.Image analysis can take placeremotely or at the point of care.The results, expressed asgm/cm², can be used forcomparison to a reference database of young normals (T-score)or age-matched controls (Z-Score).	TBS iNsight is a software packagethat provides an estimate of thetrabecular bone quality based onanalysis of data derived from DEXAexamination data (dual-energyimages, Regions of interest, patientsdata). The program utilizes aquantitative bone structural algorithmthat analyzes the texture of AP spineprojection scans from which theTrabecular Bone Score (TBS) ismathematically derived.The results (TBS) can be used forcomparison to a reference databaseof age-matched controls.
Data source	Importation of external datasource	Identical
Imaging technology	X-Ray absorption	Identical
Data analysis method	Data image processing Algorithm	Identical
	Quantitative bone structuralalgorithm that measures acomposite of weighted corticaland trabecular parameters inproximal femur projectionradiographs from which BMD ismathematically derived	Quantitative bone micro-structuralalgorithm that analyzes the porosityof the trabecular bone in DEXAprojection images, using theexperimental variogram approachfrom which the TBS ismathematically derived

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

	Predicate Device	Subject Device
Product Name ·	OsDx Hip BMD System(K082402)	TBS iNsight
Data Output	Estimate of Bone Mineral Density(BMD) on selected ROICombines measurements ofprojected trabecular bone pattern,with cortical bone and geometricdimensions to estimate the totalhip BMD	TBS calculated on selected ROIAnalyses projected trabecular bonepattern to estimate the trabecularbone score (TBS)

CONFORMITY TO RECOGNISED STANDARDS

TBS iNsight has been developed in accordance with the following product standards & FDA Guidance :

IEC 62304:2006, Medical Device Software: Software Life Cycle Processes 1.
150 14971:2007, Medical Devices: Application of Risk Management to Medical 11. Devices
General Principles of Software Validation; Final Guidance for Industry and FDA Staff 111. (2002)
Guidance for Off-the-Shelf Software Use in Medical Devices (1999) IV.
Guidance for Industry Cybersecurity for Networked Medical Devices Containing Off-V. the Shelf (OTS) Software (2005)

PERFORMANCE BENCH TESTING

| Bench Test Performance was demonstrated via the following :

Correlations between microarchitecture and TBS computed on simulated projections from µCT datasets
This study was to demonstate the level of correlation between the microarchitecture parameters of the 3-dimensional (3D) bone volume using a µCT (GE-Locus) and the TBS values computed on the 2D projected image of the bone volume, using thirty human cadaveric vertebrae.

Significant correlations were observed between TBS and 3D microarchitecture parameters, regardless of the projection resolution.

Correlations between microarchitecture and TBS on DEXA scans .
This study was to demonstrate the correlations between the 3D microarchitecture parameters of human anteroposterior vertebrae and the TBS values computed on DEXA (Dual X-ray Absorptiometry) acquisitions, using thirty human cadaveric vertebrae.

Significant correlations were detected between TBS and 3D parameters of bone microarchitecture.

The study indicates that TBS adds value and power of differentiation between samples with similar BMDs but different bone microarchitectures. It strengthens our assumption that it is possible to estimate bone microarchitecture status from DEXA imaging using TBS.

TBS reproducibility ex-vivo This study is to evaluate the ex-vivo reproducibility of TBS without repositioning.

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

The study shows that the TBS ex-vivo precision error is lower than 0.02, the The Stady Shower than 1.5 %, and the least significant change is lower than 4.2 96.

These results show that TBS is reproducible and, considering measurement rules rricss Toullie onow the be used to monitor microarchitecture changes across time.

CLINICAL TESTING

| The performance of TBS iNsight was evaluated via clinical studies covering the following :

Clinical Aspects diagnostic value .
- Olinical Aspecte alagro alagraminate a fractured patient from a control patient (nonfractured), independently and in conjunction with BMD, has been evaluated through five cross-sectional studies.

In all studies TBS was significantly lower in women with fractures versus without.

Clinical Aspects prognostic value .
Gillical Aspecto - progressions that will fracture from those who will not, independently and in conjunction with BMD, has been evaluated through three longitudinal studies.

In all studies spine TBS and BMD predicted fractures equally well and independently.

Clinical Aspects .
- Monitoring changes across time | ୦

In the two in-vivo reproducibility studies that were conducted, the mean TBS reproducibility value (CV%) at L1-L4 achieved 1.8%, showing that TBS is reproducible as the BMD and considering rules edited by the ISCD.

Treatment follow-up | o
rreatment follow up BMD and TBS values in patients treated either with zoledronic acid (vs placebo), teriparatide (vs ibandronate) or bisphosphonates (vs placebo), Strontium Ranelate (vs Alendronate), Tamoxifen & Exemestane (vs placebo) and Denosumab (vs placebo). For all six studies, the results were consistent with published literature.

with published morations. monitor change across time, particularly for treated patients.

Clinical Aspects Age-related US reference data . Olinical Aspedo - Aige Iding Non-Hispanic white US women aged 30 to 90 years has A & Gainludi Cid y in Civilian obtained for all lumbar vertebral combinations (L1, L2, L3, L4) decreased significantly with age. These decreases seen in lumbar spine TBS reflect age-related microarchitecture changes at spine.

CONCLUSION

medimaps group has demonstrated through the performance testing that the safety and nfounleps group noo Neight is not compromised and that they met all acceptance criteria, demonstrating that it can be considered substantially equivalent to the predicate device.

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

Image /page/4/Picture/1 description: The image shows the seal of the Department of Health & Human Services (HHS) of the United States. The seal features the department's name encircling a symbol. The symbol is a stylized representation of a human figure embracing a bird, which is meant to represent the department's mission of protecting the health of all Americans and providing essential human services.

Food and Drug Administration 10903 New Hampshire Avenue Silver Spring, MD 20993

5 2012

OCT

MEDIMAPS Group SA C/O Christophe Lelong Chief Operations Officer 18 Chemin des Aulx PLAN LES OUATES 1228 SWITZERLAND

Re: K121716

Trade/Device Name: Med- Imaps TBS iNsight Regulation Number: 21 CFR 892.1170 Regulation Name: Bone Densitometer Regulatory Class: Class II Product Code: KGI Dated: August 24, 2012 Received: August 30, 2012

Dear Mr. Lelong:

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. 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.

If your device is classified (see above) into class II (Special Controls), it may be subject to such additional controls. Existing major regulations affecting your device can be found in Title 21, Code of Federal Regulations (CFR), Parts 800 to 895. 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 Parts 801 and 809); medical device reporting (reporting of

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

medical device-related adverse events) (21 CFR 803); and good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820). This letter will allow you to begin marketing your device as described in your Section 510(k) premarket notification. The FDA finding of substantial equivalence of your device to a legally marketed predicate device results in a classification for your device and thus, permits your device to proceed to the market.

If you desire specific advice for your device on our labeling regulation (21 CFR Parts 801 and 809), please contact the Office of In Vitro Diagnostic Device Evaluation and Safety at (301) 796-5450. 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

http://www.fda.gov/MedicalDevices/Safety/ReportalProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/cdrh/industry/support/index.html.

Sincerely yours,

Mahal D. Oken. for

Janine M. Morris Director Division of Radiological Devices Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

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

INDICATIONS FOR USE

The Med-Imaps TBS iNsight is a software provided for use as a complement to a DEXA analysis. It computes the antero-posterior spine DEXA examination file and calculates a andrylis. It oompated the anters ps) that is compared to those of the age-matched controls. Soore (Trasecure Bono one texture of the DEXA image and has been shown to be related to The TOO is defired from the frexture risk. This data provides information independent of BMD bone intoroundstare annolement to the data obtained from the DEXA analysis and the value, it is been not on the clinician about patient history, bioassay of bone resorption markers ... ).

resorption maners... }}
The TBS score can assist the health care professional in assessment of fracture risk and in monitoring the effect of treatments on patients across time. T

monitoring the oneot on many additional factors that should be considered before making diagnostic or therapeutic recommendations. The software does not diagnose making are recommend treatment regimens. Only the health care professional can make these judgments.

Prescription Use X (Part 21 CFR 801 Subpart D) AND/OR

Over-The-Counter Use (21 CFR 807 Subpart C)

(PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON ANOTHER PAGE IF NEEDED)

(Division Sign-Off)

Office of in Vitro

510K K121716

Page 1 / 1

Regulation Number and Section

§ 892.1170 Bone densitometer.

(a)
Identification. A bone densitometer is a device intended for medical purposes to measure bone density and mineral content by x-ray or gamma ray transmission measurements through the bone and adjacent tissues. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.