ABMD Software
K213760 · HeartLung Corporation · KGI · Jul 29, 2022 · Radiology
Device Facts
| Record ID | K213760 |
| Device Name | ABMD Software |
| Applicant | HeartLung Corporation |
| Product Code | KGI · Radiology |
| Decision Date | Jul 29, 2022 |
| Decision | SESE |
| Submission Type | Traditional |
| Regulation | 21 CFR 892.1170 |
| Device Class | Class 2 |
| Attributes | AI/ML, Software as a Medical Device |
Intended Use
The Automated Bone Mineral Density (ABMD) Software is a post-processing AI-powered software intended to measure bone mineral density (BMD) from existing CT scans by averaging Hounsfield units in the trabecular region of vertebral bones. ABMD Software is not intended to replace DXA or any other tests dedicated to BMD measurement. It is solely designed for measuring BMD in existing CT scans or CT scans ordered for reasons other than BMD measurement. In summary, ABMD Software is an opportunistic AI-powered tool that enables: (1) retrospective assessment of bone density from CT scans acquired for other purposes, (2) assessment of bone density in conjunction with another medically appropriate procedure involving CT scans, and (3) assessment of bone density without a phantom as an independent measurement procedure.
Device Story
ABMD Software is a post-processing AI-powered tool for opportunistic bone mineral density (BMD) assessment. It takes DICOM CT scans as input, extracting patient metadata (age, gender) and scan parameters. An AI-trained model segments vertebral bones; the software calculates average Hounsfield Units (HU) within a cylindrical volume of trabecular tissue, excluding cortical bone. It computes BMD, Z-scores, and T-scores using scanner-specific calibration factors. Output includes snapshots of spinal bones, measured areas, and calculated scores for radiologist review. Used in clinical settings by healthcare providers, the software assists in bone density evaluation without requiring additional radiation exposure from dedicated scans. Users must accept or reject the automated segmentation; if rejected, manual measurement is required. The device provides a non-invasive method to assess bone health from existing imaging data.
Clinical Evidence
Bench testing only. Study 1: 993 QCT readings compared ABMD to manual QCT measurements; showed strong correlation (r=0.97, p<0.01). Study 2: 172 cases compared ABMD to DXA and manual QCT; ABMD showed strong correlation with manual QCT and significant correlation with DXA (r=0.72, p<0.01). Analysis methods included Pearson Correlation, Deming Regressions, and Bland-Altman Agreement.
Technological Characteristics
Software-only device (SaMD). Operates on Linux. Inputs: DICOM CT scans. Processing: AI-based segmentation of vertebral trabecular bone; HU averaging; Z-score/T-score calculation. Requires scanner-specific calibration factor input. Outputs: BMD metrics, segmented images, and scores for expert review.
Indications for Use
Indicated for post-processing analysis of bone mineral density in individuals who have undergone a CT scan that includes vertebral bone. Intended for use on existing CT scans or scans ordered for reasons other than BMD measurement.
Regulatory Classification
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.
Predicate Devices
- QCT Bone Mineral Density Analysis Software (K894854)
Reference Devices
- QCT Pro Asynchronous Calibration Module, CliniQCT (K140342)
Related Devices
- K242295 — BunkerHill BMD · BunkerHill Health · Apr 8, 2025
- K220402 — VirtuOst · O.N. Diagnostics · May 19, 2023
- K251078 — AutoDensity · Eos Imaging · Nov 14, 2025
- K082402 — OSDX HIP BMD SYSTEM · Imaging Therapeutics, Inc. · Oct 16, 2008
- K113725 — VIRTUOST · O.N. Diagnostics · Sep 13, 2012
Submission Summary (Full Text)
{0}------------------------------------------------
July 29, 2022
Image /page/0/Picture/1 description: The image contains two logos. The logo on the left is the Department of Health & Human Services logo. The logo on the right is the FDA logo, which is a blue square with the letters FDA in white, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue.
HeartLung Corporation % Lauren Lee Regulatory Consultant 1124 W Carson St TORRANCE CA 90502
#### Re: K213760
Trade/Device Name: ABMD Software Regulation Number: 21 CFR 892.1170 Regulation Name: Bone Densitometer Regulatory Class: Class II Product Code: KGI Dated: June 22, 2022 Received: June 29, 2022
Dear Lauren Lee:
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); medical device reporting of medical device-related adverse events) (21 CFR 803) for
{1}------------------------------------------------
devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Laurel Burk Assistant Director DHT8B: Division of 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) K213760
Device Name ABMD Software
#### Indications for Use (Describe)
The Automated Bone Mineral Density Software Module (ABMD) is a post-processing AI-powered software intended to measure bone mineral density (BMD) from existing CT scans by averaging Hounsfield units in the trabecular region of vertebral bones. ABMD is not intended to replace DXA or any other tests dedicated to BMD measurement. It is solely designed for measuring BMD in existing CT scans ordered for reasons other than BMD measurement. In summary, ABMD is an opportunistic AI-powered tool that enables: (1) retrospective assessment of bone density from CT scans acquired for other purposes, (2) assessment of bone density in conjunction with another medically appropriate procedure involving CT scans, and (3) assessment of bone density without a phantom as an independent measurement procedure.
X 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."
{3}------------------------------------------------
Image /page/3/Picture/0 description: The image is a logo for a company called HeartLung. The logo features a stylized human figure with a heart in the chest area and lungs represented by horizontal lines. The word "HeartLung" is written in red below the figure. The logo has a modern and clean design.
### 510(K) Summary
This summary of 510(k) safety and effectiveness information is submitted in accordance with the requirements of 21 CFR 807.92:
## 1. Submitter
HeartLung Corporation 1124 W Carson St. The Lundquist Institute, MRL Building, Floor 3 Torrance, CA 90502 Tel: (650) 448-8089 Contact: Dr. Morteza Naghavi Date Prepared: November 24, 2021
# 2. Device
Subject Device: Automated Bone Mineral Density Software Trade Name: ABMD Software Common Name: ABMD Software Classification: Class II, 21 CFR 892.1170 Product Code: KGI
# 3. Predicate Device
Manufacturer: Mindways Trade Name: QCT Bone Mineral Density Analysis Software Predicate 510(k): K894854 Classification: Class II, 21 CFR 892.1170 Product Code: KGI
# 4. Reference Device
Manufacturer: Mindways Trade Name: QCT Pro Asynchronous Calibration Module, CliniQCT Predicate 510(k): K140342 Classification: Class II, 21 CFR 892.1170 Product Code: KGI
# 5. Device Description
#### General Description
The Automated Bone Mineral Density (ABMD) Software is a software module that estimates bone mineral density in the vertebral bones by averaging Hounsfield Units (HU) in the trabecular
| | | Pg. 1 of 7 |
|--|--|------------|
|--|--|------------|
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image is a logo for a company called HeartLung. The logo features a stylized human torso with a heart in place of the lungs. The heart is pink, and the rest of the torso is blue. The logo is set against a white background.
area. ABMD Software is a post-processing software that works on existing CT scans. ABMD Software measurements are to be reviewed by radiologists and should be used by healthcare providers in conjunction with clinical evaluation.
# Intended Patient Population
ABMD Software is for post-processing analysis of bone mineral density in people who underwent a CT scan that includes vertebral bone.
# Principles of Ops
ABMD Software reads a CT scan (in DICOM format) and extracts patient-specific metadata such as age, gender, and scan specific information like acquisition time, pixel size and scanner type. The ABMD Software uses an AI trained model to segment out vertebral bones in the field of view and subsequently measures the average of the Hounsfield unit, HU, in a cylinder volume within the trabecular tissue of each vertebral bone without including the cortical bone. The bone mineral density (BMD) is calculated by the mean of those averages for vertebral bones found in the field of view. Subsequently, the Z-score and T-scores are calculated based on the age and gender of the person and the calibration factor for the CT scan. The snapshots of the spinal bones and measured area along with the average HU and the scores are exported for review and confirmation by a human expert.
Software will output the segmentation of trabecular bone used in calculation of BMD as determined by the sample volume being a minimum of 1 pixel away from the cortical bone.
Software passes if the sample volume is at least 1 pixel away from the cortical border.
Software fails if the sample volume crosses or intersects with the cortical border.
The end user cannot change or edit the segmentation or results of the device. The end user must accept or reject the region where the BMD measurement is done. If rejected, the end user must conduct an alternate method such as manual measurement using the same methods described in QCT-based manual measurement of BMD.
This device is not intended to replace DXA scanners. It is only intended to be used on the existing CT scans or CT scans ordered for reasons other than measuring BMD so that it will prevent extra radiation dose being introduced to the patients.
# Conditions of Use:
The ABMD Software is a post-processing software module that only works on existing CT scans that include spinal bones.
# 6. Intended Use
| | | Pg. 2 of 7 |
|--|--|------------|
| | | |
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image is a logo for an organization called HeartLung. The logo features a stylized human figure with a heart in the chest area and what appears to be lungs below the heart. The figure is outlined in blue, and the heart is pink. The text "HeartLung" is written in red below the figure.
K213760 HeartLung Corporation 1124 W Carson St The Lundquist Institute, MRL Building, Floor 3 Torrance, CA 90502
The Automated Bone Mineral Density (ABMD) Software is a post-processing AI-powered software intended to measure bone mineral density (BMD) from existing CT scans by averaging Hounsfield units in the trabecular region of vertebral bones. ABMD Software is not intended to replace DXA or any other tests dedicated to BMD measurement. It is solely designed for measuring BMD in existing CT scans or CT scans ordered for reasons other than BMD measurement. In summary, ABMD Software is an opportunistic AI-powered tool that enables: (1) retrospective assessment of bone density from CT scans acquired for other purposes, (2) assessment of bone density in conjunction with another medically appropriate procedure involving CT scans, and (3) assessment of bone density without a phantom as an independent measurement procedure.
7. Comparison of Technological Characteristics & Intended Use to Predicate Device The table below provides a summary of the technological characteristics of the ABMD Software in comparison to the predicate device. The indications for use for the predicate device are similar to the indications for the use of the ABMD Software. There are no major technological differences between the two systems that raise new issues of safety and/or effectiveness. Thus, the ABMD Software is substantially equivalent to the predicate device.
| Feature | Subject Device<br>ABMD Software | Predicate<br>Device<br>QCT Bone<br>Mineral Density<br>Analysis<br>Software<br>K894854 | Reference<br>Device<br>QCT Pro<br>Asynchronous<br>Calibration<br>Module,<br>CliniQCT<br>K140342 | Summary |
|-------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------|
| Indication for<br>Use/Intended<br>Use | Estimate bone<br>mineral density<br>within the spine. | Estimate bone<br>mineral density<br>within the spine. | Estimate bone<br>mineral density<br>within the spine. | Equivalent. |
| Modality | CT scan images<br>(DICOM) | CT scan images<br>(DICOM) | CT scan images<br>(DICOM) | Equivalent. |
| Device provides<br>estimates of | Yes | Yes | Yes | Equivalent. |
| bone mineral<br>density from the<br>spine. | | | | |
| Device provides<br>the bone mineral<br>density value. | Yes | Yes | Yes | Equivalent. |
| Device provides<br>Z-score. | Yes | Yes | Yes | Equivalent. |
| Device provides<br>T-score. | Yes | Yes | Yes | Equivalent. |
| User | Healthcare<br>Providers | Healthcare<br>Providers | Healthcare<br>Providers | Equivalent. |
| Operating<br>System | Linux | Windows | Windows | Equivalent,<br>software<br>function is<br>independent<br>from<br>operating<br>system. |
| Retrospective<br>measurements<br>from CT scans. | CT scan images<br>can be selected and<br>inputted to the<br>software. | CT scan images<br>can be selected<br>and inputted to<br>the software. | CT scan images<br>can be selected<br>and inputted to<br>the software. | Equivalent. |
| Automatic<br>Averaging<br>Hounsfield<br>Units | Software<br>automatically<br>measures and<br>averages<br>Hounsfield units in<br>the trabecular | Software<br>automatically<br>measures and<br>averages<br>Hounsfield units<br>in the trabecular | Software<br>automatically<br>measures and<br>averages<br>Hounsfield units<br>in the trabecular | Equivalent. |
| | region of spinal<br>bones. | region of spinal<br>bones. | region of spinal<br>bones. | |
| Calibration | Inputting CT<br>scanner-specific<br>calibration factor is<br>required. Software<br>outputs calibrated<br>BMD score. | Simultaneous<br>scanning of<br>calibration<br>phantom is<br>required.<br>Software outputs<br>calibrated BMD<br>score. | Asynchronous<br>scanning of<br>calibration<br>phantom is<br>required.<br>Software outputs<br>calibrated BMD<br>score. | Equivalent.<br>Software<br>provides<br>measurements<br>corrected for<br>calibration<br>data. |
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image is a logo for an organization called HeartLung. The logo features a stylized human figure with a heart in the chest area and lungs on either side. The heart is pink, while the lungs are blue. The text "HeartLung" is written in red below the figure.
Pg. 4 of 7
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image is a logo for an organization called "HeartLung". The logo features a stylized human figure with a heart in the chest area and what appears to be a representation of the lungs. The figure is enclosed in a rounded square shape. The word "HeartLung" is written in red below the figure.
# 8. Performance Data
The following performance data were provided in support of the substantial equivalence determination.
#### Sterilization & Shelf-Life Testing
Not applicable for this software as a medical device.
#### Biocompatibility Testing
Not applicable for this software as a medical device.
## Electrical Safety and Electromagnetic Compatibility (EMC)
Not applicable for this software as a medical device.
#### Software Verification and Validation Testing
Software Verification and Validation testing was completed to demonstrate the safety and effectiveness of the device. Testing demonstrates the ABMD Software meets all its functional requirements and performance specifications.
| | | Pg. 5 of 7 |
|--|--|------------|
| | | |
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image is a logo for an organization called "HeartLung". The logo features a stylized human figure with a heart in the chest area and lungs surrounding the heart. The heart is colored pink, while the lungs and the rest of the figure are blue. The text "HeartLung" is written in red and blue below the figure.
The ABMD Software strongly correlated with manual QCT-based BMD measurement. The scatter plot and regression lines show the range of bias to be limited and display a very strong correlation between BMD measured by manual method versus ABMD Software (t = 0.97, p<0.01). The ABMD Software also correlated with DXA BMD measurement (r = 0. 72, p<0.01). A summary of two studies performed is listed below.
| | Study 1 | Study 2 |
|----------------------|----------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Reference<br>Dataset | 993 quantitative CT (QCT) readings of a<br>cohort of asymptomatic cases who<br>underwent CT scans. | 172 asymptomatic cases who underwent<br>whole-body DXA scans as well as CT<br>scans. |
| Truthing Process | QCT BMD, T-score, and Z-score values<br>derived from manual measurement by<br>trained operators. | DXA scans derived T-score, and Z-score<br>values plus QCT BMD, T-score, and Z-<br>score values derived from manual<br>measurement by trained operators. |
| Analysis methods | Pearson Correlation, Deming<br>Regressions, and Bland Altman<br>Agreement | Pearson Correlation, Deming<br>Regressions, and Bland Altman<br>Agreement |
| Results | Strong correlations and agreements were<br>found between manual QCT and ABMD<br>Software | Strong correlations and agreements were<br>found between manual QCT and ABMD<br>Software. Modest but significant<br>correlations and agreement were found<br>between DXA, and ABMD Software. |
#### ABMD Software Performance Studies
Significant correlations between BMD measurements by DXA and ABMD Software were found (r = 0.72 , p<0.01) which closely matched the correlations reported in literature between DXA and manual QCT (r=0.5 to r=0.75) measurements. While DXA BMD measurements at Ward Triangle correlate well with QCT BMD measurement in vertebral bones, the QCT measurement is exclusively focused on the trabecular bone tissue, as compared to DXA's combined measurement of cortical and trabecular bone tissues. Therefore, QCT based BMD measurement using ABMD Software is more specific to trabecular bone tissues and does not impose any additional safety or effectiveness concerns when compared to the predicate device.
#### Mechanical and Acoustic Testing
Not applicable for this software as a medical device.
# Animal Study
{9}------------------------------------------------
Image /page/9/Picture/0 description: The image is a logo for "HeartLung". The logo features a stylized human figure with a heart in the chest area and lungs on either side. The heart is pink, while the rest of the figure is blue. The text "HeartLung" is written in red below the figure.
Animal performance testing was not required to demonstrate safety and effectiveness of the device.
## Clinical Studies
Clinical testing was not required to demonstrate the safety and effectiveness of the device. Instead, substantial equivalence is based upon software verification and validation testing, or benchtop performance testing of the software as a medical device.
## 9. Conclusions
The body of testing summarized above indicates that the ABMD Software performs as intended and is substantially equivalent to the predicate device. The testing above demonstrates that the ABMD Software is as safe and effective as the predicate device. No new safety or effectiveness issues are raised by the ABMD Software.
| | | Pg. 7 of 7 |
|--|--|------------|
|--|--|------------|