ADAS 3D

K253969 · Adas3D Medical S.L. · QIH · Jun 29, 2026 · Radiology

Device Facts

• Record ID: K253969
• Device Name: ADAS 3D
• Applicant: Adas3D Medical S.L.
• Product Code: QIH · Radiology
• Decision Date: Jun 29, 2026
• 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
Left Chambers and Aorta Segmentation	—	Dice > 0.84 (LV, LA, AO); Dice > 0.76 (LAA); Dice > 0.66 (PAPS TRABEC, PVs); Dice > 0.67 (Esophagus); MSD < 2.23 mm	Dice: 0.94 (LV), 0.94 (LA), 0.94 (AO), 0.81 (LAA), 0.73 (PAPS TRABEC), 0.79 (PVs), 0.75 (Esophagus); MSD: 1.03 (LV), 1.03 (LA), 0.83 (AO), 1.69 (LAA), 1.79 (PAPS TRABEC), 1.74 (PVs), 1.53 (Esophagus)	226 DICOM images (Localizer, LV, LA, LAA, AO, PAPS TRABEC); 179 DICOM images (PVs); 139 DICOM images (Esophagus)	>1 (clinical teams)	100 cases	>1 (clinical experts)
Coronary Artery Segmentation	—	Dice > 0.78; 95% HD < 10.86 mm	Dice: 0.81 (LCA), 0.81 (RCA); 95% HD: 6.56 (LCA), 6.91 (RCA)	228 DICOM images	>1 (clinical teams)	100 cases	>1 (clinical experts)
Left Atrium Wall Segmentation	—	MSD < 0.32 mm (ENDO); MSD < 0.76 mm (EPI); CA > 43.90; CD1 < 49.00; CD2 < 12.10	MSD: 0.37 (ENDO), 0.55 (EPI); CA: 61.69; CD1: 35.22; CD2: 3.09	144 DICOM images	>1 (clinical teams)	100 cases	>1 (clinical experts)
Left Ventricle 2D MRI Slice Alignment	—	MDS < 6.23 mm	MDS: 2.77 mm	162 DICOM images	>1 (clinical teams)	30 cases	>1 (clinical experts)
Left Ventricle 2D MRI Segmentation	—	Dice > 0.85 (ENDO); APD < 2.12 mm (ENDO); HD < 13.25 mm (ENDO); Dice > 0.89 (EPI); APD < 1.93 mm (EPI); HD < 13.25 mm (EPI)	Dice: 0.92 (ENDO), 0.94 (EPI); APD: 1.91 (ENDO), 2.00 (EPI); HD: 8.57 (ENDO), 8.72 (EPI)	162 DICOM images	>1 (clinical teams)	100 cases	>1 (clinical experts)
Left Ventricle 3D MRI Segmentation	—	Dice > 0.79 (ENDO); HD < 27.32 mm (ENDO); Dice > 0.78 (EPI); HD < 27.32 mm (EPI)	Dice: 0.88 (ENDO), 0.90 (EPI); HD: 9.44 (ENDO), 9.89 (EPI)	100 DICOM images	>1 (clinical teams)	100 cases	>1 (clinical experts)
Left Atrium 3D MRI Segmentation	—	Dice > 0.86; MSD < 1.39 mm; HD < 16.50 mm	Dice: 0.89; MSD: 1.7 mm; HD: 12.33 mm	114 DICOM images	>1 (clinical teams)	100 cases	>1 (clinical experts)
Left Ventricle CTA Segmentation	—	Dice > 0.87 (ENDO); MSD < 0.97 mm (ENDO); Dice > 0.84 (EPI); MSD < 1.22 mm (EPI)	Dice: 0.95 (ENDO), 0.96 (EPI); MSD: 0.73 (ENDO), 0.90 (EPI)	187 DICOM images	>1 (clinical teams)	100 cases	>1 (clinical experts)

Indications for Use

ADAS 3D is indicated for use in clinical settings to support the visualization and analysis of MR and CT images of the heart on individual patients with cardiovascular disease. ADAS 3D is indicated for patients with myocardial scar produced by ischemic or non-ischemic heart disease. ADAS 3D processes MR and CT images. The quality and the resolution of the medical images determines the accuracy of the data produced by ADAS 3D. ADAS 3D is indicated to be used only by qualified medical professionals (cardiologists, electrophysiologists, radiologists or trained technicians) for the calculation, quantification and visualization of cardiac images and intended to be used for pre-planning and during electrophysiology procedures. The data produced by ADAS 3D must not be used as an irrefutable basis or a source of medical advice for clinical diagnosis or patient treatment. The data produced by ADAS 3D is intended to be used to support qualified medical professionals for clinical decision making. The clinical significance of using ADAS 3D to identify arrhythmia substrates for the treatment of cardiac arrhythmias (e.g., ventricular tachycardia) or risk stratification has not been established. ADAS 3D is not intended for radiotherapy treatment planning, dose calculation, or treatment delivery. The DICOM RT Structure Set (RTSTRUCT) export functionality is provided solely for interoperability and standardized exchange of anatomical contour information.

Device Story

ADAS 3D is a stand-alone software for post-processing cardiovascular MR and CTA images. It ingests DICOM images to perform non-invasive quantification and 3D visualization of cardiac structures, including myocardial fibrosis, wall thickness, and epicardial adipose tissue. The device utilizes machine-learning-based features for automated initialization of cardiac chambers, coronary arteries, and other anatomical structures. It is operated by qualified medical professionals in clinical settings to support diagnostic decision-making and electrophysiology procedure planning. Output includes 3D models and quantitative data, which can be exported in industry-standard formats (including DICOM RTSTRUCT) for integration with catheter navigation systems and third-party visualization software. The device provides an advanced visualization module compatible with stereoscopic displays. It does not provide clinical diagnosis or treatment advice; it serves as a decision-support tool.

Clinical Evidence

No clinical trials were conducted. Analytical validation was performed using a diverse dataset of DICOM images from multiple international clinical sites. Performance of machine-learning features was evaluated against ground truth annotations generated by clinical experts. Metrics included Dice Metric (DC), Mean Surface Distance (MSD), and Hausdorff Distance (HD). Results demonstrated performance consistent with state-of-the-art benchmarks and the predicate device.

Technological Characteristics

Stand-alone software for DICOM image processing. Features machine-learning-based algorithms for automated anatomical initialization. Supports Linux RHEL 8 and Windows 11. Integrates with third-party systems (Siemens syngo.via, Circle cvi42, Abbott EnSite X, Philips AVW). Exports data via DICOM RTSTRUCT and other industry-standard formats. Includes advanced visualization module for stereoscopic displays.

Indications for Use

Indicated for patients with myocardial scar from ischemic or non-ischemic heart disease. Used by cardiologists, electrophysiologists, radiologists, or trained technicians for cardiac image calculation, quantification, and visualization to support pre-planning and electrophysiology procedures.

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

• ADAS 3D (K240791)

Submission Summary (Full Text)

{0}

**FDA** **U.S. FOOD & DRUG**
ADMINISTRATION

June 29, 2026

Adas3D Medical S.L.
Antoni Riu
General Manager
Rambla Catalunya 53, 4-H
Barcelona, 08007
Spain

Re: K253969

Trade/Device Name: ADAS 3D

Regulation Number: 21 CFR 892.2050

Regulation Name: Medical Image Management And Processing System

Regulatory Class: Class II

Product Code: QIH, LLZ

Dated: June 2, 2026

Received: June 2, 2026

Dear Antoni Riu:

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'

U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov

{1}

K253969 - Antoni Riu

Page 2

(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 Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (Preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3).

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 (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-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (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-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-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-devices/medical-device-safety/medical-device-reporting-mdr-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/medical-devices/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-devices/device-advice-comprehensive-regulatory-

{2}

K253969 - Antoni Riu

Page 3

assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email ([e-mail]) or phone [phone] or 301-796-7100).

Sincerely,

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}

DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration

Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.

# Indications for Use

510(k) Number (if known)
K253969

Device Name
ADAS 3D

Indications for Use (Describe)

ADAS 3D is indicated for use in clinical settings to support the visualization and analysis of MR and CT images of the heart on individual patients with cardiovascular disease.

ADAS 3D is indicated for patients with myocardial scar produced by ischemic or non-ischemic heart disease. ADAS 3D processes MR and CT images. The quality and the resolution of the medical images determines the accuracy of the data produced by ADAS 3D.

ADAS 3D is indicated to be used only by qualified medical professionals (cardiologists, electrophysiologists, radiologists or trained technicians) for the calculation, quantification and visualization of cardiac images and intended to be used for pre-planning and during electrophysiology procedures. The data produced by ADAS 3D must not be used as an irrefutable basis or a source of medical advice for clinical diagnosis or patient treatment. The data produced by ADAS 3D is intended to be used to support qualified medical professionals for clinical decision making.

The clinical significance of using ADAS 3D to identify arrhythmia substrates for the treatment of cardiac arrhythmias (e.g., ventricular tachycardia) or risk stratification has not been established.

ADAS 3D is not intended for radiotherapy treatment planning, dose calculation, or treatment delivery. The DICOM RT Structure Set (RTSTRUCT) export functionality is provided solely for interoperability and standardized exchange of anatomical contour information.

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
[e-mail]

"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 FDA 3881 (8/23)

Page 1 of 1

PSC Publishing Services [phone] EF

{4}

Adas3D Medical

K253969
510(k) Summary

## 1 General Information

This 510(k) Summary is being submitted in accordance with the requirements detailed in 21 CFR 807.92.

**DATE:** June 29, 2026

**SUBMITTER:** Adas3D Medical S.L.
Rambla Catalunya 53, 4-H
08007
Barcelona
Spain

**CONTACT:** Antoni Riu
[phone]
[e-mail]

**DEVICE TRADE NAME:** ADAS 3D

**COMMON NAME:** Radiological Image Processing System

**CLASSIFICATION NAME:** Radiological Image Processing System (21 CFR 892.2050)

**PRODUCT CODE:** Primary product code: QIH
Secondary product code: LLZ

**REGULATION DESCRIPTION:** Medical image management and processing system

**PREDICATE DEVICE:** ADAS 3D (K240791)

29-06-2026 V.1.4

{5}

Adas3D Medical

510(k) Summary

## 2 Device Description

ADAS 3D is a stand-alone software tool designed for post-processing cardiovascular enhanced Magnetic Resonance (MR) images and Computed Tomography Angiography (CTA) images that are formatted in the Digital Imaging and Communication in Medicine (DICOM) standard. ADAS 3D software aids in the non-invasive calculation, quantification and visualization of cardiac imaging data to support a comprehensive diagnostic decision-making process for understanding cardiovascular disease.

ADAS 3D exports information to multiple industry standard file formats suitable for documentation and interoperability purposes. The 3D data is exported into industry standard file formats supported by catheter navigation systems and by other third-party software applications that implement the Digital Imaging and Communications in Medicine Radiation Therapy (DICOM RT) Structure Set (RTSTRUCT) standard for standardized exchange of anatomical contour information.

ADAS 3D analyses the enhancement of myocardial fibrosis from DICOM MR images to support:

- Visualization of the distribution of the enhancement in a three-dimensional (3D) chamber of the heart.
- Quantification of the total volume of the enhancement within the Left Ventricle (LV) and the visualization of the enhancement area in multiple layers through the cardiac structure.
- Calculation, quantification and visualization of corridors of intermediate signal intensity enhancement in the LV.
- Quantification and visualization of the total area and distribution of the enhancement within the left Atrium (LA).
- Calculation, and visualization of LV and LA regionalization.

Additionally, ADAS 3D imports DICOM CTA images to support:

- Quantification and visualization of LV and LA wall thickness.
- Quantification and visualization of LV and LA hypoenhancement.
- Quantification and visualization of LV and LA Epicardial Adipose Tissue.
- Identification and Visualization of other 3D anatomical structures.
- Quantification and visualization of distances from the LV and LA epicardium to other 3D anatomical structures.
- Calculation, and visualization of corridors of wall thickness in the LV.
- Calculation, and visualization of LV and LA regionalization.

Additionally, ADAS 3D imports DICOM Magnetic Resonance Angiography (MRA) images to support:

- Identification and Visualization of other 3D anatomical structures.

Additionally, ADAS 3D uses the following machine-learning-based features:

- Standard Initialization of the LV, LA, LAA, PVs, Aorta, Esophagus, Trabeculae and Papillary Muscles from CTA
- Standard Initialization of the Coronary Arteries from CTA
- Standard Initialization of the LV from CTA
- Standard Initialization of the LA from CTA
- Standard Initialization of the LV from 2D LGE-MRI and Automatic Slice Alignment
- Standard Initialization of the LV from 3D LGE-MRI
- Standard Initialization of the LA from 3D LGE-MRI

29-06-2026 V.1.4

{6}

Adas3D^{}[] Medical

**510(k) Summary**

Additionally, ADAS 3D imports EP STUDIES from catheter navigation systems for post-treatment analysis after the electrophysiology procedure.

Additionally, ADAS 3D includes an advanced visualization module for DICOM images and models that can be used in combination with stereoscopic displays and 3D interaction devices.

It is designed to be used by qualified medical professionals (cardiologists, radiologists or trained technicians) experienced in examining and evaluating cardiovascular MR and CTA images as part of the comprehensive diagnostic decision-making process.

29-06-2026 V.1.4

{7}

Adas3D^{}[] Medical

**510(k) Summary**

### 3 Indications for Use

ADAS 3D is indicated for use in clinical settings to support the visualization and analysis of MR and CT images of the heart for use on individual patients with cardiovascular disease.

ADAS 3D is indicated for patients with myocardial scar produced by ischemic or non-ischemic heart disease. ADAS 3D processes MR and CT images. The quality and the resolution of the medical images determines the accuracy of the data produced by ADAS 3D.

ADAS 3D is indicated to be used only by qualified medical professionals (cardiologists, electrophysiologists, radiologists or trained technicians) for the calculation, quantification and visualization of cardiac images and intended to be used for pre-planning and during electrophysiology procedures. The data produced by ADAS 3D must not be used as an irrefutable basis or a source of medical advice for clinical diagnosis or patient treatment. The data produced by ADAS 3D is intended to be used to support qualified medical professionals for clinical decision making.

The clinical significance of using ADAS 3D to identify arrhythmia substrates for the treatment of cardiac arrhythmias (e.g., ventricular tachycardia) or risk stratification has not been established.

ADAS 3D is not intended for radiotherapy treatment planning, dose calculation, or treatment delivery. The DICOM RT Structure Set (RTSTRUCT) export functionality is provided solely for interoperability and standardized exchange of anatomical contour information.

29-06-2026 V.1.4

{8}

| Adas3D Medical | 510(k) Summary |
| --- | --- |

## 4 Comparison with Predicate Device

Adas3D Medical SL is modifying its own device [ADAS 3D; K240791] under this traditional 510(k). The purpose of this submission is to make three (3) modifications to the device. The following two tables compare the Indications for Use, Device Description (including functional and technological characteristics) and the new modifications of the subject device to the predicate device.

| Elements of Comparison | Subject DeviceADAS 3D(Adas3D Medical S.L.) | Predicate DeviceADAS 3D(K240791) |
| --- | --- | --- |
| Regulatory data | | |
| Regulatory Class | Class II | Class II |
| Classification name | Radiological Image processing system | Radiological Image processing system |
| Regulation Number | 21 CFR 892.2050 | 21 CFR 892.2050 |
| Product Code | | QIH, LLZ |
| 510(k) Number | | K240791 |
| Use | | |
| Indications for Use | ADAS 3D is indicated for use in clinical settings to support the visualization and analysis of MR and CT images of the heart for use on individual patients with cardiovascular disease.ADAS 3D is indicated for patients with myocardial scar produced by ischemic or non-ischemic heart disease. ADAS 3D processes MR and CT images. The quality and the resolution of the medical images determines the accuracy of the data produced by ADAS 3D.ADAS 3D is indicated to be used only by qualified medical professionals (cardiologists, electrophysiologists, radiologists or trained technicians) for the calculation, quantification and visualization of cardiac images and intended to be used for pre-planning and during electrophysiology procedures. The data produced by ADAS 3D must not be used as an irrefutable basis or a source of medical advice for clinical diagnosis or patient treatment. The | ADAS 3D is indicated for use in clinical settings to support the visualization and analysis of MR and CT images of the heart for use on individual patients with cardiovascular disease.ADAS 3D is indicated for patients with myocardial scar produced by ischemic or non-ischemic heart disease. ADAS 3D processes MR and CT images. The quality and the resolution of the medical images determines the accuracy of the data produced by ADAS 3D.ADAS 3D is indicated to be used only by qualified medical professionals (cardiologists, electrophysiologists, radiologists or trained technicians) for the calculation, quantification and visualization of cardiac images and intended to be used for pre-planning and during electrophysiology procedures. The data produced by ADAS 3D must not be used as an irrefutable basis or a source of medical advice for clinical diagnosis or patient treatment. The |

29-06-2026 V.1.4

{9}

| Adas3D Medical | 510(k) Summary |
| --- | --- |

| Elements of Comparison | Subject DeviceADAS 3D(Adas3D Medical S.L.) | Predicate DeviceADAS 3D(K240791) |
| --- | --- | --- |
| | data produced by ADAS 3D is intended to be used to support qualified medical professionals for clinical decision making.The clinical significance of using ADAS 3D to identify arrhythmia substrates for the treatment of cardiac arrhythmias (e.g., ventricular tachycardia) or risk stratification has not been established.ADAS 3D is not intended for radiotherapy treatment planning, dose calculation, or treatment delivery. The DICOM RT Structure Set (RTSTRUCT) export functionality is provided solely for interoperability and standardized exchange of anatomical contour information. | data produced by ADAS 3D is intended to be used to support qualified medical professionals for clinical decision making.The clinical significance of using ADAS 3D to identify arrhythmia substrates for the treatment of cardiac arrhythmias (e.g., ventricular tachycardia) or risk stratification has not been established. |
| Device Description(Including Functional and Technological Characteristics) | ADAS 3D is a stand-alone software tool designed for post-processing cardiovascular enhanced Magnetic Resonance (MR) images and Computed Tomography Angiography (CTA) images that are formatted in the Digital Imaging and Communication in Medicine (DICOM) standard. ADAS 3D software aids in the non-invasive calculation, quantification and visualization of cardiac imaging data to support a comprehensive diagnostic decision-making process for understanding cardiovascular disease.ADAS 3D exports information to multiple industry standard file formats suitable for documentation and interoperability purposes. The 3D data is exported into industry standard file formats supported by catheter navigation systems and by other third-party software applications that implement the Digital Imaging and Communications in Medicine Radiation Therapy (DICOM RT) Structure Set (RTSTRUCT) standard for standardized exchange of anatomical contour information. | ADAS 3D is a stand-alone software tool designed for post-processing cardiovascular enhanced Magnetic Resonance (MR) images and Computed Tomography Angiography (CTA) images that are formatted in the Digital Imaging and Communication in Medicine (DICOM) standard. ADAS 3D software aids in the non-invasive calculation, quantification and visualization of cardiac imaging data to support a comprehensive diagnostic decision-making process for understanding cardiovascular disease.ADAS 3D exports information to multiple industry standard file formats suitable for documentation and information sharing purposes. The 3D data is exported into industry standard file formats supported by catheter navigation systems.ADAS 3D analyses the enhancement of myocardial fibrosis from DICOM MR images to support:- Visualization of the distribution of the |

29-06-2026 V.1.4

{10}

| Adas3D Medical | 510(k) Summary |
| --- | --- |[{"box_2d": [92, 118, 904, 940], "label": "table", "caption": "| Elements of Comparison | Subject DeviceADAS 3D(Adas3D Medical S.L.) | Predicate DeviceADAS 3D(K240791) |
| --- | --- | --- |
| | ADAS 3D analyses the enhancement of myocardial fibrosis from DICOM MR images to support:Visualization of the distribution of the enhancement in a three-dimensional (3D) chamber of the heart.Quantification of the total volume of the enhancement within the Left Ventricle (LV) and the visualization of the enhancement area in multiple layers through the cardiac structure.Calculation, quantification and visualization of corridors of intermediate signal intensity enhancement in the LV.Quantification and visualization of the total area and distribution of the enhancement within the left Atrium (LA).Calculation, and visualization of LV and LA regionalization.Additionally, ADAS 3D imports DICOM CTA images to support:Quantification and visualization of LV and LA wall thickness.Quantification and visualization of LV and LA hypoenhancement.Quantification and visualization of LV and LA Epicardial Adipose Tissue.Identification and Visualization of other 3D anatomical structures.Quantification and visualization of distances from the LV and LA epicardium to other 3D anatomical structures.Calculation, and visualization of corridors of wall thickness in the LV.Calculation, and visualization of LV and LA regionalization. | enhancement in a three-dimensional (3D) chamber of the heart.Quantification of the total volume of the enhancement within the Left Ventricle (LV) and the visualization of the enhancement area in multiple layers through the cardiac structure.Calculation, quantification and visualization of corridors of intermediate signal intensity enhancement in the LV.Quantification and visualization of the total area and distribution of the enhancement within the left Atrium (LA).Additionally, ADAS 3D imports DICOM CTA images to support:Quantification of LV wall thickness.Identification and Visualization of other 3D anatomical structures.Quantification and visualization of LA wall thickness.Quantification and visualization of distances from the LA epicardium to other 3D anatomical structures.Additionally, ADAS 3D imports DICOM Magnetic Resonance Angiography (MRA) images to support:Identification and Visualization of other 3D anatomical structures.Additionally, ADAS 3D uses the following machine-learning-based features:Standard Initialization of the LV, LA, and Aorta from CTAStandard Initialization of the Coronary Arteries from CTAStandard Initialization of the LA from CTAStandard Initialization of the LV from 2D LGE-MRI and Automatic Slice Alignment |"]}]

29-06-2026 V.1.4

{11}

| Adas3DMedical | 510(k) Summary |
| --- | --- |[{"box_2d": [92, 118, 904, 890], "label": "table", "caption": "| Elements of Comparison | Subject DeviceADAS 3D(Adas3D Medical S.L.) | Predicate DeviceADAS 3D(K240791) |
| --- | --- | --- |
| | Additionally, ADAS 3D imports DICOM Magnetic Resonance Angiography (MRA) images to support:- Identification and Visualization of other 3D anatomical structures.Additionally, ADAS 3D uses the following machine-learning-based features:- Standard Initialization of the LV, LA, LAA, PVs, Aorta, Esophagus, Trabeculae and Papillary Muscles from CTA- Standard Initialization of the Coronary Arteries from CTA- Standard Initialization of the LV from CTA- Standard Initialization of the LA from CTA- Standard Initialization of the LV from 2D LGE-MRI and Automatic Slice Alignment- Standard Initialization of the LV from 3D LGE-MRI- Standard Initialization of the LA from 3D LGE-MRIAdditionally, ADAS 3D imports EP STUDIES from catheter navigation systems for post-treatment analysis after the electrophysiology procedure.Additionally, ADAS 3D includes an advanced visualization module for DICOM images and models that can be used in combination with stereoscopic displays and 3D interaction devices.It is designed to be used by qualified medical professionals (cardiologists, radiologists or trained technicians) experienced in examining and evaluating cardiovascular MR and CTA images as part of the comprehensive diagnostic decision-making process. | - Standard Initialization of the LV from 3D LGE-MRI- Standard Initialization of the LA from 3D LGE-MRIIt is designed to be used by qualified medical professionals (cardiologists, radiologists or trained technicians) experienced in examining and evaluating cardiovascular MR and CTA images as part of the comprehensive diagnostic decision-making process. |"]}]

29-06-2026 V.1.4

{12}

## 510(k) Summary

### 5 Changes from the predicate device

| Feature | Subject Device ADAS 3D (Adas3D Medical S.L.) | Predicate Device ADAS 3D (Adas3D Medical S.L.) (K240791) | Comparison |
| --- | --- | --- | --- |
| Supported Operating Systems | Linux RHEL 8 and Windows 11. | Linux RHEL 8, Windows 11 and Windows 10. | Removed support for Windows 10. |
| Integration | Siemens syngo.via OpenApps, Circle cvi42, Abbott EnSite X, Philips Advanced Visualization Workspace (AVW). | Siemens syngo.via OpenApps, Circle cvi42. | Added the integration with Abbott EnSite X and Philips Advanced Visualization Workspace (AVW). |
| Initial Identification of structures | Manual and semi-automatic using Machine Learning technique: - Left Chambers from CTA - Left Ventricle from 2D DE-MRI - Coronaries from CTA - Left Ventricle from 3D DE-MRI - Left Atrium from 3D DE-MRI - Left Atrium Wall Thickness from CTA - Left Ventricle Wall Thickness from CTA | Manual and semi-automatic using Machine Learning technique: - Left Chambers from CTA - Left Ventricle from 2D DE-MRI - Coronaries from CTA - Left Ventricle from 3D DE-MRI - Left Atrium from 3D DE-MRI - Left Atrium Wall Thickness from CTA | Added one new semi-automatic segmentations using Machine Learning technique. Improved the already existing semi-automatic segmentations. |
| Automation of Existing Analyses | - Automated identification of 3D Corridors (LV ENHANCEMENT from MRI) - Automated LV regionalization (MRI/CTA) - Automated identification of 3D Corridors (LVWT from CTA) - Automated LA regionalization (MRI/CTA) | - Automated identification of 3D Corridors (LV ENHANCEMENT from MRI) - Automated LV regionalization (MRI/CTA) | Added three automations to existing analyses. |
| Analyses | - LV and LA Enhancement, LV and LA Wall Thickness, LV Transmurality, LV and LA Isodistances. - LV and LA Epicardial Adipose | - LV and LA Enhancement, LV and LA Wall Thickness, LV Transmurality, LV and LA Isodistances. | Added two new analyses. |

29-06-2026 V.1.4

{13}

| Adas3D Medical | **510(k) Summary** |
| --- | --- |

| Feature | Subject Device ADAS 3D (Adas3D Medical S.L.) | Predicate Device ADAS 3D (Adas3D Medical S.L.) (K240791) | Comparison |
| --- | --- | --- | --- |
| | Tissue and LV and LA Hypoenhancement . | | |
| General Study Tools | - Heart Anatomy Extraction, Image Alignment, Compare 3D. - EP Review, Volume Definition Tool, and ADAS VR (standard volume rendering). | - Heart Anatomy Extraction, Image Alignment, and Compare 3D. | Added three new General Study Tools. |

The substantial equivalence between the Subject Device and the Predicate Devices was established based on the comparison outlined in Table above and the discussion on intended use, measurements, technological characteristics and features.

After evaluating the modifications, we conclude that the changes in the device description to the subject device do not impact its safety and effectiveness.

29-06-2026 V.1.4

{14}

**510(k) Summary**

## 6 Summary of Non-Clinical Testing

The subject device underwent software verification and validation activities, including source code verification, integration testing, system testing, regression testing, and cybersecurity testing, in accordance with FDA guidance on software validation and cybersecurity for device software functions. In addition, analytical validation was performed to evaluate the accuracy and performance of the device’s image processing and machine-learning-based functionalities. Interoperability and compatibility validation were also performed for supported third-party systems, file exports, and hardware configurations. These testing activities demonstrated that the device meets its design requirements and performs as intended.

### 6.1 Machine Learning features

The machine-learning features were trained and tested using DICOM data from several clinical sites from multiple countries. The DICOM data was acquired using a variety of CT/MRI scanners and scanner protocols from different manufacturers.

This DICOM data was anonymized by the hospitals before being sent to us, in compliance with the European General Data Protection Regulation (GDPR). This anonymization process prevented including personal patient information such as gender, age, or ethnicity.

This DICOM dataset includes a diverse range of atrial and ventricular conditions. The Left Ventricle (LV) includes ischemic and non-ischemic cardiomyopathies such as left ventricular hypertrophy and dilated cardiomyopathy, as well as other cardiac conditions like premature ventricular contractions. The Left Atrium (LA), includes a diverse range of conditions and presentations, from relatively healthy atrial tissue to various forms of atrial fibrillation (paroxysmal, persistent, long-standing persistent, and recurrent cases), other atrial pathologies such as atrial flutter and atrial tachycardia, and structural heart diseases impacting left atrial function.

#### 6.1.1 Training

For each machine learning feature, the training dataset has been obtained from the initial DICOM dataset, according to the image modality and the target structure. All DICOM images are from European hospitals. The details of the training dataset for each machine learning feature are summarized in the table below.

| Machine learning feature | Number of DICOM images | Scanner manufacturers |
| --- | --- | --- |
| Algorithm Description of the tool for the Initial Identification of the Left Chambers and Aorta from 3D CTA | 226 (Localizer, LV, LA, LAA, AO, PAPS TRABEC) | GE (44.72%), Toshiba (31.85%), Philips (1.76%) and Siemens (21.67%) |
| | 179 (PVs) | GE (54.78%), Toshiba (39.09%), Philips (1.67%) and Siemens (4.46%) |
| | 139 (Esophagus) | GE (62.58%), Toshiba (34.53%) and Philips (2.88%) |
| Algorithm Description of the tool for the Initial | 228 | Toshiba (47.37%), Siemens (10.96%), GE (39.91%) and Philips (1.75%). |

29-06-2026 V.1.4

{15}

## 510(k) Summary

| Machine learning feature | Number of DICOM images | Scanner manufacturers |
| --- | --- | --- |
| Identification of the Coronaries from 3D CTA | | |
| Initial Identification of the Left Atrium Wall from 3D CTA | 144 | GE (6.96%), Toshiba (90.28%) and Philips (2.77%) |
| Algorithm description of the Initial Identification of the Left Ventricle from 2D DE-MRI | 162 | Siemens (94.44%), GE (3.7%), Phillips (1.86%) |
| Algorithm Description of the Initial Identification of the Left Ventricle from 3D LGE-MRI | 100 | Siemens (99%), GE (1%) |
| Initial Identification of the Left Atrium from 3D DE-MRI | 114 | GE (38.34%), Siemens (63.16%) |
| Initial Identification of the Left Ventricle Wall from 3D CTA | 187 | GE (21.93%), Toshiba (29.41%), Philips (2.14%) and Siemens (46.52%) |

The DICOM dataset has been annotated identifying the target structures. The annotation of the data was generated initially by the hospitals' clinical teams and revised by Adas3D Medical's Clinical Team. The Adas3D Medical's Clinical Team consists of highly experienced individuals with knowledge of cardiac anatomy, interpretation of MRI and CT volumes, and the use of ADAS 3D.

### 6.1.2 Performance testing

The performance testing for each machine learning feature was performed using a subset of the initial DICOM dataset, that was selected according to the target structure, the image modality, the country, and the scan manufacturer. Each testing dataset has been selected from hospitals not used in any stage of algorithm development, including training. The details of each testing dataset are summarized in the table below.

| Machine learning feature | Number of cases | Data sources | Scanner manufacturers |
| --- | --- | --- | --- |
| Testing of the Initial identification of the Left Chambers, AO, Esophagus, Pulmonary Veins and Papillary Muscles & Trabeculae from 3D CTA | 100 | US (67%) and OUS (33%) | US: SIEMENS (64,2%), Toshiba (29,9%) and GE (6%) OUS: SIEMENS (18,2%), Toshiba (30,3%), Canon (15,2%), GE (33,3%) and Philips (3%) |
| Testing of the Initial | 100 | US (64%) and | US: SIEMENS (64,1%), Toshiba (26,6%), GE (7,8%) and |

29-06-2026 V.1.4

{16}

Adas3D^{}[] Medical

## 510(k) Summary

| Machine learning feature | Number of cases | Data sources | Scanner manufacturers |
| --- | --- | --- | --- |
| Identification of the Coronaries from 3D CTA | | OUS (36%) | Phillips (1,6%) OUS: SIEMENS (25,0%), Toshiba (27,8%), Canon (13,9%), GE (30,6%) and Philips (2,8%) |
| Testing of the Initial Identification of the Left Atrium from CTA | 100 | US (71%) and OUS (29%) | US: SIEMENS (60,6%), Toshiba (31%) and GE (8,4%) OUS: SIEMENS (24,1%), Toshiba (34,5%), Canon (13,8%), GE (24,1%) and Philips (3,4%) |
| Testing of the Automatic Alignment of Slices of the Left Ventricle from 2D DE-MRI | 30 | US (66,6%) and OUS (33,3%) | US: SIEMENS (70%), Philips (20%) and GE (10%) OUS: Philips (20%), SIEMENS (20%) and GE (60%) |
| | 70 | US (45,7%) and OUS (54,3%) | US: SIEMENS (71,9%), Philips (25%) and GE (3,1%) OUS: Philips (57,9%), SIEMENS (18,4%) and GE (23,7%) |
| Testing of the Initial Identification of the Left Ventricle from 2D DE-MRI | 100 | US (52%) and OUS (48%) | US: SIEMENS (56%), Philips (40%) and GE (4%) OUS: Philips (50%), SIEMENS (18,8%) and GE (31,2%) |
| Testing of the Initial Identification of the Left Ventricle from 3D DE-MRI | 100 | US (69%) and OUS (31%) | US: SIEMENS (62,3%), Philips (31,9%) and GE (5,8%) OUS: SIEMENS (48,4%), Toshiba (3,2%), Philips (45,2%) and GE (3,2%) |
| Testing of the Initial Identification of the Left Atrium from 3D DE-MRI | 100 | US (61%) and OUS (39%) | US: Philips (50,8%), SIEMENS (44,3%) and GE (4,9%) OUS: SIEMENS (71,8%), Philips (25,6%) and GE (2,6%) |
| Testing of the Initial Identification of the Left Ventricle from CTA | 100 | US (65%) and OUS (35%) | US: Toshiba (31,3%), SIEMENS (64,1%) and GE (4,7%) OUS: SIEMENS (23,5%), Philips (2,9%), GE (29,4%), Toshiba (29,4%) and Canon (14,7%) |

Ground truth annotations were generated using the manual tools of the FDA-cleared ADAS 3D software by two clinical experts independent of the clinical experts who established the ground truth of the training dataset.

The performance metrics and the acceptance criteria for each target structure are based on a review of state-of-the-art algorithms. Performance testing follows a non-inferiority approach, with a predefined non-inferiority margin. The primary goal of ADAS 3D is to provide a preliminary initialization of the target structure, which would then be subject to further refinement by the user. This non-inferiority approach confirms that the performance aligns with the average performance benchmarks reported in the field.

The following metrics have been used to define the acceptance criteria:

- MSD: Mean Surface Distance.

29-06-2026 V.1.4

{17}

Adas3D Medical

## 510(k) Summary

- MDS: Mean Difference in Shifts computes the slice alignment error between two 2D MRI images. It is computed as the mean of the shifts in x and y dimensions for all slices.
- APD: The Average Perpendicular Distance measures the average distance (in mm) of all corresponding contour points between two contours. A low APD value means that the two contours match closely.
- DC: Dice Metric.
- Color agreement (CA), Color disagreement by one color (CD1), and Color disagreement by two colors or more (CD2): These three metrics are defined in the paper: Valles-Colomer, A., Rubio Forcada, B., Soto-Iglesias, D. et al. Reproducibility analysis of the computerized tomography angiography–derived left atrial wall thickness maps. J Interv Card Electrophysiol 66, 1045–1055 (2023). https://doi.org/10.1007/s10840-023-01472-5

The table below summarizes the performance results. The metric values used for evaluating the performance are highlighted in bold.

| Machine Learning feature | Target structure | Metric | Mean | Lower CI95 | Higher CI95 | Threshold | Meets acceptance criteria |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Standard Initialization of the Left Chambers and Aorta from CTA | LV | DC | 0.94 | **0.93** | 0.94 | **0.84** | yes |
| | LV | MSD | 1.03 | 0.96 | **1.09** | **2.23** | yes |
| | LA | DC | 0.94 | **0.94** | 0.95 | **0.84** | yes |
| | LA | MSD | 1.03 | 0.97 | **1.09** | **2.23** | yes |
| | AO | DC | 0.94 | **0.94** | 0.95 | **0.84** | yes |
| | AO | MSD | 0.83 | 0.73 | **0.93** | **2.23** | yes |
| | LAA | DC | 0.81 | **0.80** | 0.83 | **0.76** | yes |
| | LAA | MSD | 1.69 | 1.49 | **1.89** | **2.23** | yes |
| | PAPS TRABEC | DC | 0.73 | **0.72** | 0.75 | **0.66** | yes |
| | PAPS TRABEC | MSD | 1.79 | 1.62 | **1.96** | **2.23** | yes |
| | PVs | DC | 0.79 | **0.78** | 0.80 | **0.66** | yes |
| | PVs | MSD | 1.74 | 1.55 | **1.93** | **2.23** | yes |
| | Esophagus | DC | 0.75 | **0.74** | 0.77 | **0.67** | yes |
| | Esophagus | MSD | 1.53 | 1.36 | **1.69** | **2.23** | yes |
| Standard Initialization of the Coronary Arteries from CTA | LCA | DC | 0.81 | **0.80** | 0.82 | **0.78** | yes |
| | LCA | 95% HD | 6.56 | 4.97 | **8.15** | **10.86** | yes |
| | RCA | DC | 0.81 | **0.80** | 0.82 | **0.78** | yes |
| | RCA | 95% HD | 6.91 | 5.37 | **8.45** | **10.86** | yes |
| Standard Initialization of the LA from CTA | LA ENDO | MSD | 0.37 | 0.35 | **0.39** | **0.32** | no |
| | LA EPI | MSD | 0.55 | 0.52 | **0.57** | **0.76** | yes |
| | LA | CA | 61.69 | **60.01** | 63.67 | **43.90** | yes |
| | LA | CD1 | 35.22 | 33.89 | **36.56** | **49.00** | yes |

29-06-2026 V.1.4

{18}

## 510(k) Summary

| Machine Learning feature | Target structure | Metric | Mean | Lower CI95 | Higher CI95 | Threshold | Meets acceptance criteria |
| --- | --- | --- | --- | --- | --- | --- | --- |
| | LA | CD2 | 3.09 | 2.55 | **3.63** | **12.10** | yes |
| Automatic Slice Alignment for LV from 2D LGE-MRI | LV | MDS | 2.77 | 2.44 | **3.10** | **6.23** | yes |
| Standard Initialization of the LV from 2D LGE-MRI | LV ENDO | DC | 0.92 | **0.92** | 0.92 | **0.85** | yes |
| | LV ENDO | APD | 1.91 | 1.83 | **2.00** | **2.12** | yes |
| | LV ENDO | HD | 8.57 | 8.07 | **9.08** | **13.25** | yes |
| | LV EPI | DC | 0.94 | **0.93** | 0.94 | **0.89** | yes |
| | LV EPI | APD | 2.00 | 1.91 | **2.08** | **1.93** | no |
| | LV EPI | HD | 8.72 | 8.24 | **9.20** | **13.25** | yes |
| Standard Initialization of the LV from 3D LGE-MRI | LV ENDO | DC | 0.88 | **0.87** | 0.88 | **0.79** | yes |
| | LV ENDO | HD | 9.44 | 8.82 | **10.07** | **27.32** | yes |
| | LV EPI | DC | 0.90 | **0.90** | 0.91 | **0.78** | yes |
| | LV EPI | HD | 9.89 | 9.23 | **10.54** | **27.32** | yes |
| Standard Initialization of the LA from 3D LGE-MRI | LA | DC | 0.89 | **0.89** | 0.90 | **0.86** | yes |
| | LA | MSD | 1.7 | 1.6 | **1.8** | **1.39** | no |
| | LA | HD | 12.33 | 11.4 | **13.26** | **16.50** | yes |
| Standard Initialization of the LV from CTA | LV ENDO | DC | 0.95 | **0.95** | 0.96 | **0.87** | yes |
| | LV ENDO | MSD | 0.73 | 0.68 | **0.78** | **0.97** | yes |
| | LV EPI | DC | 0.96 | **0.96** | 0.96 | **0.84** | yes |
| | LV EPI | MSD | 0.90 | 0.85 | **0.95** | **1.22** | yes |

Four tests did not meet the non-inferiority criteria. In these four cases, the discrepancies are sub-pixel, indicating that our algorithm's performance is acceptable given the minimum pixel spacing of the input images.

A subgroup analysis found that the algorithms' performance is consistent across US and OUS groups.

### 6.1.3 Performance testing conclusion

The results of the performance testing confirm that the subject device met all acceptance criteria and demonstrate that the performance of the machine learning features is in line with the performance of the predicate device.

29-06-2026 V.1.4

{19}

Adas3D^{}[] Medical

**510(k) Summary**

## 7 Conclusion

The comparison of the subject device with the predicate device shows that they have substantially equivalent indications for use, functional and technological characteristics.

Adas3D Medical believes the subject device is substantially equivalent to the predicate device and is as safe and effective as the predicate device.

29-06-2026 V.1.4