Predicate Devices

Reference Devices

Not Found

AI/ML (Artificial Intelligence / Machine Learning)

Yes
The device description explicitly states that ADAS 3D uses "machine-learning-based features" and lists several specific features that utilize machine learning.

Therapeutic

No.
The device is for visualization and analysis of medical images and supports clinical decision-making, it does not directly provide therapy or treatment.

Diagnostic

Yes

The device aids in the non-invasive calculation and quantification of cardiac imaging data to support a comprehensive diagnostic decision-making process for understanding cardiovascular disease. Although it states the data must not be used as an "irrefutable basis or a source of medical advice for clinical diagnosis," it is intended to "support qualified medical professionals for clinical decision making." This indicates its role in the diagnostic process.

SaMD (Software as a Medical Device)

Yes

The device description explicitly states that ADAS 3D is a "stand-alone software tool" and its function is post-processing of medical images. There is no mention of accompanying hardware components required for its operation beyond a standard computing platform capable of running the software.

IVD (In Vitro Diagnostic)

Based on the provided information, this device is not an IVD (In Vitro Diagnostic).

Here's why:

IVD Definition: In Vitro Diagnostics are tests performed on samples taken from the human body, such as blood, urine, or tissue, to detect diseases, conditions, or infections.
ADAS 3D Function: ADAS 3D processes and analyzes medical images (MR and CT) of the heart. It does not perform tests on biological samples. Its purpose is to provide visualization and quantification of anatomical structures and features within the images to support clinical decision-making.

Therefore, ADAS 3D falls under the category of medical imaging software or a medical device that processes imaging data, not an In Vitro Diagnostic device.

PCCP (Predetermined Change Control Plan) Authorized

No
The letter does not state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device. The section "Control Plan Authorized (PCCP) and relevant text" is listed as "Not Found".

Overview

Intended 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 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.

Product codes

QIH, LLZ

Device Description

ADAS 3D is a stand-alone software tool intended to be used 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 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 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 CTA
Standard Initialization of the Coronary Arteries 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

Mentions image processing

Yes

Mentions AI, DNN, or ML

Yes

Input Imaging Modality

MR, CT, CTA, MRA, 2D LGE-MRI, 3D LGE-MRI

Anatomical Site

Heart (Left Ventricle (LV), Left Atrium (LA), Aorta, Coronary Arteries, Left Atrial Appendage (LAA))

Indicated Patient Age Range

Not Found

Intended User / Care Setting

Qualified medical professionals (cardiologists, electrophysiologists, radiologists or trained technicians) / clinical settings

Description of the training set, sample size, data source, and annotation protocol

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.

Standard Initialization of the Left Chambers and Aorta from CTA: 111 DICOM images, Scanner manufacturers: GE (62%), Toshiba (35%), Philips (3%)
Standard Initialization of the Coronaries from CTA: 231 DICOM images, Scanner manufacturers: Toshiba (48%), Siemens (37%), GE (14%) and Philips (1%).
Standard Initialization the LA from CTA: 136 DICOM images, Scanner manufacturers: GE (65%), Toshiba (32%) and Philips (3%)
Standard Initialization LV from 2D DE-MRI: 126 DICOM images, Scanner manufacturers: Siemens (91%), GE (6%), Phillips (3%)
Standard Initialization of the LV from 3D DE-MRI: 110 DICOM images, Scanner manufacturers: Siemens (99%), GE (1%)
Standard Initialization of the LA from 3D DE-MRI: 82 DICOM images, Scanner manufacturers: GE (51%), Philips (49%)

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.

Description of the test set, sample size, data source, and annotation protocol

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.

Standard Initialization of the Left Chambers and Aorta from CTA: 100 cases, Data sources: US (62%) and OUS (38%), Scanner manufacturers: US: SIEMENS (61%), Toshiba (32%) and GE (7%); OUS: SIEMENS (47%), Toshiba (26%), Canon (13%), GE (11%) and Philips (3%)
Standard Initialization of the Coronaries from CTA: 100 cases, Data sources: US (64%) and OUS (36%), Scanner manufacturers: US: SIEMENS (64%), Toshiba (26%), GE (8%) and Phillips (2); OUS: SIEMENS (47%), Toshiba (28%), Canon (14%), GE (8%) and Philips (3%)
Standard Initialization the LA from CTA: 100 cases, Data sources: US (65%) and OUS (35%), Scanner manufacturers: US: SIEMENS (58%), Toshiba (34%) and GE (8%); OUS: SIEMENS (53%), Toshiba (30%), Canon (11%), GE (3%) and Philips (3%)
Automatic Slice Alignment for LV from 2D DE-MRI: 70 cases, Data sources: US (52%) and OUS (48%), Scanner manufacturers: US: SIEMENS (72%), Philips (25%) and GE (3%); OUS: Philips (58%), SIEMENS (18%) and GE (24%)
Standard Initialization of the LV from 2D DE-MRI: 100 cases, Data sources: US (52%) and OUS (48%), Scanner manufacturers: US: SIEMENS (71%), Philips (23%) and GE (6%); OUS: Philips (50%), SIEMENS (19%) and GE (31%)
Standard Initialization of the LV from 3D DE-MRI: 100 cases, Data sources: US (69%) and OUS (31%), Scanner manufacturers: US: SIEMENS (62%), Philips (32%) and GE (6%); OUS: SIEMENS (49%), Philips (45%), Toshiba (3%) and GE (3%)
Standard Initialization of the LA from 3D DE-MRI: 95 cases, Data sources: US (60%) and OUS (35%), Scanner manufacturers: US: Philips (50%), SIEMENS (45%) and GE (5%); OUS: SIEMENS (71%), Philips (26%) and GE (3%)

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

Summary of Performance Studies

Study type: Performance testing of machine learning features using a non-inferiority approach.

Sample size: Total cases across all features: 100 + 100 + 100 + 70 + 100 + 100 + 95 = 665 cases. (Sample sizes for individual features are in the "Description of the test set" section).

Key metrics:

MSD: Mean Surface Distance.
HD: Hausdorff Distance.
MDS: Mean Difference in Shifts.
APD: Average Perpendicular Distance.
DC: Dice Metric.
Color agreement (CA)
Color disagreement by one color (CD1)
Color disagreement by two colors or more (CD2)

Standalone performance / Key results:

Standard Initialization of the Left Chambers and Aorta from CTA:
- LV: DC = 0.93 (Threshold 0.84, yes); MSD = 1.29 (Threshold 2.23, yes)
- LA: DC = 0.94 (Threshold 0.84, yes); MSD = 1.06 (Threshold 2.23, yes)
- AO: DC = 0.94 (Threshold 0.84, yes); MSD = 0.93 (Threshold 2.23, yes)
- LAA: DC = 0.84 (Threshold 0.76, yes); MSD = 1.01 (Threshold 2.23, yes)
Standard Initialization of the Coronary Arteries from CTA:
- LCA: DC = 0.82 (Threshold 0.78, yes); HD = 7.71 (Threshold 10.86, yes)
- RCA: DC = 0.82 (Threshold 0.78, yes); HD = 6.61 (Threshold 10.86, yes)
Standard Initialization of the LA from CTA:
- LA ENDO: MSD = 0.37 (Threshold 0.32, no)
- LA EPI: MSD = 0.56 (Threshold 0.76, yes)
- LA: CA = 56.09 (Threshold 43.90, yes); CD1 = 38.32 (Threshold 49.00, yes); CD2 = 5.58 (Threshold 12.10, yes)
Automatic Slice Alignment for LV from 2D LGE-MRI:
- LV: MDS = 2.39 (Threshold 6.23, yes)
Standard Initialization of the LV from 2D LGE-MRI:
- LV ENDO: DC = 0.90 (Threshold 0.85, yes); APD = 2.01 (Threshold 2.10, no); HD = 9.72 (Threshold 13.25, yes)
- LV EPI: DC = 0.93 (Threshold 0.89, yes); APD = 2.06 (Threshold 1.93, no); HD = 9.81 (Threshold 13.25, yes)
Standard Initialization of the LV from 3D LGE-MRI:
- LV ENDO: DC = 0.88 (Threshold 0.79, yes); HD = 2.40 (Threshold 27.32, yes)
- LV EPI: DC = 0.91 (Threshold 0.78, yes); HD = 9.57 (Threshold 27.32, yes)
Standard Initialization of the LA from 3D LGE-MRI:
- LA: DC = 0.90 (Threshold 0.86, yes); MSD = 1.62 (Threshold 1.39, no); HD = 12.36 (Threshold 16.50, yes)

Four tests did not meet the non-inferiority criteria, but discrepancies were sub-pixel, indicating acceptable performance. Performance was consistent across US and OUS groups. The results 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.

Key Metrics

MSD: Mean Surface Distance.
HD: Hausdorff Distance.
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)

Predicate Device(s)

ADAS 3D (K230803)

Reference Device(s)

Not Found

Predetermined Change Control Plan (PCCP) - All Relevant Information

Not Found

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).

Summary

0

September 9, 2024

Image /page/0/Picture/1 description: The image shows the logo for the U.S. Food and Drug Administration (FDA). The logo consists of two parts: on the left, there is an emblem representing the Department of Health & Human Services - USA, and on the right, there is the text "FDA U.S. FOOD & DRUG ADMINISTRATION" in blue. The word "FDA" is in a larger, bolder font, and the words "U.S. FOOD & DRUG" are stacked above the word "ADMINISTRATION".

Adas3D Medical S.L Antoni Riu General Manager Rambla Catalunya 53, 4H BARCELONA, 08007 SPAIN

Re: K240791

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: August 9, 2024 Received: August 9, 2024

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.

1

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" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30. Design controls; 21 CFR 820.90. Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-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-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatory

2

assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Samal for

Jessica Lamb, Ph.D. Assistant Director Imaging Software Team DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

3

Indications for Use

Submission Number (if known)

K240791

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 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, guantification 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.

Type of Use (Select one or both, as applicable)

Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

4

Image /page/4/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue swoosh across it, positioned above the text "Adas3D Medical". The text is in a simple, sans-serif font, with "Adas3D" on the first line and "Medical" on the second line. The heart graphic is slightly offset to the right of the text.

General Information 1

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

DATE:	September 9, 2024
SUBMITTER:	Adas3D Medical S.L.
Rambla Catalunya 53, 4-H
08036 Barcelona
Barcelona
Spain
CONTACT:	Antoni Riu
+34 93 328 3964
antoni.riu@adas3d.com
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:	Picture archiving and communications system
PREDICATE DEVICE:	ADAS 3D (K230803)

5

Image /page/5/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue arc over it, set against a background of small gray squares. Below the heart graphic, the text "Adas3D Medical" is written in a simple, sans-serif font, with "Adas3D" on the top line and "Medical" on the bottom line.

Device Description ম

ADAS 3D is a stand-alone software tool intended to be used 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 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 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 CTA
Standard Initialization of the Coronary Arteries 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

6

Image /page/6/Picture/0 description: The image contains the logo for Adas3D Medical. The logo features a stylized red heart with a blue swoosh across it, positioned above the text "Adas3D Medical." The text is in a simple, sans-serif font, with "Adas3D" on the top line and "Medical" on the bottom line. The background is plain white.

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

ന 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 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, radiologists or trained technicians) for the calculation, quantification 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.

7

Image /page/7/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue arc passing over it, set against a background of small gray squares. Below the heart graphic, the text "Adas3D Medical" is written in a simple, sans-serif font, with "Adas3D" on the first line and "Medical" on the second.

4 Comparison with Predicate Device

Adas3D Medical SL is modifying its own device [ADAS 3D; K230803] 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 Device
ADAS 3D
(Adas3D Medical S.L.) | Predicate Device
ADAS 3D
(K230803) |
|--------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 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 | LLZ |
| 510(k) Number | K240791 | K230803 |
| 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 | Same |
| Elements of Comparison | Subject Device | Predicate Device |
| | ADAS 3D
(Adas3D Medical S.L.) | ADAS 3D
(K230803) |
| | 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. | |
| 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 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: | 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: |
| Elements of
Comparison | Subject Device
ADAS 3D
(Adas3D Medical S.L.) | Predicate Device
ADAS 3D
(K230803) |
| | Visualization of the distribution of the
enhancement in a three-dimensional
(3D) chamber of the heart. | 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. | 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. | 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). | 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: | 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. | 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: | Additionally, ADAS 3D imports DICOM Magnetic
Resonance Angiography (MRA) images to
support: |
| | Identification and Visualization of
other 3D anatomical structures. | Identification and Visualization of
other 3D anatomical structures. |
| | | It is designed to be used by qualified medical
professionals (cardiologists, radiologists or |
| Elements of
Comparison | Subject Device
ADAS 3D
(Adas3D Medical S.L.) | Predicate Device
ADAS 3D
(K230803) |
| | Additionally, ADAS 3D uses the following
machine-learning-based features:
Standard Initialization of the LV, LA,
and Aorta from CTA Standard Initialization of the
Coronary Arteries 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 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. | trained technicians) experienced in examining
and evaluating cardiovascular MR and CTA
images as part of the comprehensive diagnostic
decision-making process. |

8

Image /page/8/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue swoosh above it, set against a background of small gray dots. Below the graphic is the text "Adas3D Medical" in a simple, sans-serif font.

9

Image /page/9/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue arc wrapping around it, positioned above the text "Adas3D Medical." The text is in a simple, sans-serif font. There is a grid of dots in the background behind the heart.

10

Image /page/10/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue arc sweeping across it, positioned above the text "Adas3D Medical." The text is stacked, with "Adas3D" on the top line and "Medical" on the bottom line. There are also some small dots in the background.

11

Image /page/11/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue swoosh across it, positioned above the text "Adas3D Medical". The text is in a simple, sans-serif font and is stacked in two lines. The background is white.

| Feature | Subject Device
ADAS 3D
(Adas3D Medical S.L.) | Predicate Device
ADAS 3D
(Adas3D Medical S.L.)
(K230803) | Comparison |
|--------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Supported
Operating
Systems | Linux RHEL 8, Windows 11 and
Windows 10 | Windows 10 | Added support for
Linux RHEL 8 and
Windows 11 |
| Initial
Identification
of structures | 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 | Semi-automatic using Machine
Learning technique:
Left Chambers from CTA Left Ventricle from 2D DE-MRI Coronaries from CTA Manual:
Left Ventricle from 3D DE-MRI Left Atrium from 3D DE-MRI Left Atrium Wall Thickness from
CTA | Added three new
semi-automatic
segmentations using
Machine Learning
technique.

Improved the already
existing three semi-
automatic
segmentations. |

Changes from the predicate device ട്

Summary of Non-Clinical Testing 6

The subject device has undergone design reviews, risk analyses, and verification and validation testing, to ensure its safety and effectiveness. The subject device has been assessed using well-established methods to validate that is substantial equivalent to the predicate device.

Machine Learning features 6.1

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

12

Image /page/12/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue arc across it, positioned above the text "Adas3D Medical". The text is in a simple, sans-serif font, with "Adas3D" on the top line and "Medical" on the bottom line. There is also a grid of dots in the upper left corner of the image.

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 |
|-----------------------------------------------------------------------|---------------------------|-------------------------------------------------------------|
| Standard Initialization of
the Left Chambers and
Aorta from CTA | 111 | GE (62%), Toshiba (35%), Philips (3%) |
| Standard Initialization of
the Coronaries from CTA | 231 | Toshiba (48%), Siemens (37%), GE (14%) and Philips
(1%). |
| Standard Initialization the
LA from CTA | 136 | GE (65%), Toshiba (32%) and Philips (3%) |
| Standard Initialization LV
from 2D DE-MRI | 126 | Siemens (91%), GE (6%), Phillips (3%) |
| Standard Initialization of
the LV from 3D DE-MRI | 110 | Siemens (99%), GE (1%) |
| Standard Initialization of
the LA from 3D DE-MRI | 82 | GE (51%), Philips (49%) |

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.

Performance testing 6.1.2

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 |
|-------------------------------------------------|--------------------|--------------|----------------------------------------------|
| Standard Initialization
of the Left Chambers | 100 | US (62%) and | US: SIEMENS (61%), Toshiba (32%) and GE (7%) |

13

Image /page/13/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue arc passing over it, set against a background of small dots. Below the heart graphic, the text "Adas3D Medical" is written in a clear, sans-serif font, with "Adas3D" on the top line and "Medical" on the bottom line.

| and Aorta from CTA | | OUS (38%) | OUS: SIEMENS (47%), Toshiba (26%), Canon (13%), GE
(11%) and Philips (3%) |
|----------------------------------------------------------|-----|---------------------------|----------------------------------------------------------------------------------------------------------------------------------------------|
| Standard Initialization
of the Coronaries from
CTA | 100 | US (64%) and
OUS (36%) | US: SIEMENS (64%), Toshiba (26%), GE (8%) and
Phillips (2)
OUS: SIEMENS (47%), Toshiba (28%), Canon (14%), GE
(8%) and Philips (3%) |
| Standard Initialization
the LA from CTA | 100 | US (65%) and
OUS (35%) | US: SIEMENS (58%), Toshiba (34%) and GE (8%)
OUS: SIEMENS (53%), Toshiba (30%), Canon (11%), GE
(3%) and Philips (3%) |
| Automatic Slice
Alignment for LV from
2D DE-MRI | 70 | US (52%) and
OUS (48%) | US: SIEMENS (72%), Philips (25%) and GE (3%)
OUS: Philips (58%), SIEMENS (18%) and GE (24%) |
| Standard Initialization
of the LV from 2D DE-
MRI | 100 | US (52%) and
OUS (48%) | US: SIEMENS (71%), Philips (23%) and GE (6%)
OUS: Philips (50%), SIEMENS (19%) and GE (31%) |
| Standard Initialization
of the LV from 3D DE-
MRI | 100 | US (69%) and
OUS (31%) | US: SIEMENS (62%), Philips (32%) and GE (6%)
OUS: SIEMENS (49%), Philips (45%), Toshiba (3%) and
GE (3%) |
| Standard Initialization
of the LA from 3D DE-
MRI | 95 | US (60%) and
OUS (35%) | US: Philips (50%), SIEMENS (45%) and GE (5%)
OUS: SIEMENS (71%), Philips (26%) and GE (3%) |

Ground truth annotations were generated using 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 stateof-the-art algorithms. Performance testing follows a non-inferiority approach, with a predefined noninferiority 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.
HD: Hausdorff Distance.
. 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.

14

Image /page/14/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue curved line running across it, positioned above the text "Adas3D Medical". The text is in a simple, sans-serif font, with "Adas3D" on the first line and "Medical" on the second line.

. 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 | 0.93 | 0.92 | 0.94 | | LV | | LA | | LA | | AO | | AO | | LAA | | LAA | Standard
Initialization of
the Coronary
Arteries from
CTA | LCA | DC | 0.82 | 0.80 | 0.84 | | LCA | | RCA | | RCA | Standard
Initialization of
the LA from CTA | LA ENDO | MSD | 0.37 | 0.32 | | LA EPI | | LA | | LA | | LA | Automatic Slice
Alignment for LV
from 2D LGE-MRI | LV | MDS | 2.39 | 2.22 | Standard
Initialization of | LV ENDO | | LV ENDO | | LV ENDO ------------------|--------|-------|---------------|----------------|-----------|---------------------------------|
| 0.84 | yes |
| MSD | 1.29 | 1.03 | 1.56 | 2.23 | yes |
| DC | 0.94 | 0.94 | 0.95 | 0.84 | yes |
| MSD | 1.06 | 0.95 | 1.17 | 2.23 | yes |
| DC | 0.94 | 0.94 | 0.95 | 0.84 | yes |
| MSD | 0.93 | 0.51 | 1.34 | 2.23 | yes |
| DC | 0.84 | 0.83 | 0.85 | 0.76 | yes |
| MSD | 1.01 | 0.91 | 1.1 | 2.23 | yes |
| 0.78 | yes |
| HD | 7.71 | 6.05 | 9.37 | 10.86 | yes |
| DC | 0.82 | 0.80 | 0.83 | 0.78 | yes |
| HD | 6.61 | 5.24 | 7.97 | 10.86 | yes |
| 0.41 | 0.32 | no |
| MSD | 0.56 | 0.51 | 0.61 | 0.76 | yes |
| CA | 56.09 | 53.56 | 58.63 | 43.90 | yes |
| CD1 | 38.32 | 36.37 | 40.28 | 49.00 | yes |
| CD2 | 5.58 | 4.73 | 6.44 | 12.10 | yes |
| 2.55 | 6.23 | yes |
| DC | 0.90 | 0.90 | 0.91 | 0.85 | yes |
| APD | 2.01 | 1.89 | 2.13 | 2.10 | no |
| HD | 9.72 | 9.04 | 10.40 | 13.25 | yes |

15

Image /page/15/Picture/0 description: The image shows the logo for Adas3D Medical. The logo features a stylized red heart with a blue ribbon wrapping around it. Above the heart are several small dots arranged in a grid pattern. Below the heart is the text "Adas3D Medical" in a simple, sans-serif font.

| the LV from 2D

LGE-MRI	LV EPI	DC	0.93	0.93	0.94	0.89	yes
	LV EPI	APD	2.06	1.95	2.17	1.93	no
	LV EPI	HD	9.81	9.11	10.51	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	2.40	2.15	2.64	27.32	yes
	LV EPI	DC	0.91	0.90	0.92	0.78	yes
	LV EPI	HD	9.57	8.81	10.33	27.32	yes
Standard
Initialization of
the LA from 3D
LGE-MRI	LA	DC	0.90	0.89	0.91	0.86	yes
	LA	MSD	1.62	1.45	1.78	1.39	no
	LA	HD	12.36	11.17	13.55	16.50	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.

Conclusion 7

The comparison of the subject device with the predicate device show 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.