Mean absolute errors: 11–21 mL for EDV, 9–12 mL for ESV.
—
—
Independent external validation dataset of 46 subjects.
3 (expert cardiologists)
Right Ventricle Ejection Fraction
PyTorch-based neural network
Absolute error tolerance of 5%
Mean absolute errors: 3–8 percentage points.
—
—
Independent external validation dataset of 46 subjects.
3 (expert cardiologists)
Right Ventricle Curvature Metrics
PyTorch-based neural network
p < 0.05
r = 0.6327–0.8046
—
—
RVENet population
—
Indications for Use
ReVISION 2 is a clinical software package designed for review, quantification, and reporting of right ventricle (RV) structures and function based on 3D echocardiography-derived digital medical data. ReVISION 2 is not intended to be used for reading of mammography images.
Device Story
ReVISION 2 is a web-based SaaS platform for 3D echocardiography analysis; operates as standalone SaMD. Inputs: DICOM files from ultrasound systems (GE, Philips) or UCD files (TomTec). Operation: AI-powered PyTorch-based neural network auto-contours RV to generate 3D surface model; user reviews/edits contours. Outputs: Volumetric metrics (EDV, ESV, SV), ejection fraction (longitudinal, radial, anteroposterior), 3D strain (longitudinal, circumferential, area), and curvature metrics. Used in hospitals/clinics by healthcare professionals. Output presented in structured report for clinical decision support; assists diagnosis of RV structure/function. Benefits: Automated quantification reduces manual contouring variability; provides detailed morphological/functional assessment.
Clinical Evidence
No clinical testing performed. Analytical validation conducted on 46-subject external cohort. RVEF accuracy within 5% absolute error tolerance; EDV/ESV mean absolute errors (11–21 mL and 9–12 mL) consistent with manual inter-observer variability. Curvature validated against Materialise 3-matic Medical (K060950) showing moderate-to-strong correlation (r=0.63–0.80, p<0.05).
Technological Characteristics
Standalone web-based SaaS. Inputs: DICOM/UCD. Processing: PyTorch-based neural network for 3D surface model generation. Outputs: Volumetric, strain, and curvature metrics. Cybersecurity: TLS 1.2/1.3, STRIDE threat modeling, Moderate Level of Concern. Software verification per IEC 62304.
Indications for Use
Indicated for quantification and reporting of right ventricle (RV) structures and function in adults (>21 years) with suspected disease to support physician diagnosis.
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).
{0}
**U.S. FOOD & DRUG**
ADMINISTRATION
September 9, 2026
Argus Cognitive, Inc.
Andrea Marosán
Regulatory-Quality Affairs
35 S. Main St.
Hanover, NH 03755
Re: K251417
Trade/Device Name: ReVISION 2
Regulation Number: 21 CFR 892.2050
Regulation Name: Medical Image Management And Processing System
Regulatory Class: Class II
Product Code: QIH
Dated: September 7, 2026
Received: September 8, 2026
Dear Andrea Marosán:
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.
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
{1}
K251417 - Andrea Marosán
Page 2
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 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
{2}
K251417 - Andrea Marosán
Page 3
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-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,
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 | | |
| --- | --- | --- |
| Please type in the marketing application/submission number, if it is known. This textbox will be left blank for original applications/submissions. | K251417 | ? |
| Please provide the device trade name(s). | | ? |
| ReVISION 2 | | |
| Please provide your Indications for Use below. | | ? |
| Indications for use of ReVISION are quantification and reporting of right ventricle (RV) structures and function of patients (adults only) with suspected disease to support the physician in the diagnosis. | | |
| Please select the types of uses (select one or both, as applicable). | ☑ Prescription Use (Part 21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C) | ? |
ReVISION
Page 8 of 51
{4}
Argus Cognitive, Inc.
ReVISION - K251417
ARGUS Cognitive
# 510(k) SUMMARY
## ReVISION 2
### General Information [807.92(a)(1)]
Submitter:
Argus Cognitive, Inc.
35 South Main street, Hanover, NH 03755
www.arguscognitive.com
Contact person: Andrea Marosan
Director, Quality-Regulatory Affairs
andi@arguscognitive.com
Submission type: 510(k)
Submission date: June 18, 2025, updated on September 7, 2026
510(k) number: K251417
Establishment Registration Number: 3036502204
### Device Information [807.92(a)(2)]
Trade Name: ReVISION 2
Generic Name: Image review and quantification software
Classification: 21CFR 892.2050; Medical Image Management And Processing System
Common Name: Automated Radiological Image Processing Software
Product Code: QIH
Device Class: Class II
1
{5}
Argus Cognitive, Inc.
ReVISION - K251417
[LOGO]
ARGUS Cognitive
## Predicate Device(s) [807.92(a)(3)]
Primary predicate: K201632 — TomTec-Arena TTA2
Secondary predicate: K223322 — Argus Cognitive ReVISION Software Application (ReVISION 1.0)
## Device Description [807.92(a)(4)]
### Device characteristics
ReVISION 2 is a standalone Software as a Medical Device (SaMD) operating as a web-based Software as a Service (SaaS) platform. It is not part of a hardware medical device and operates independently as cloud-based diagnostic support software.
### Environment of use
Healthcare facility/Hospital: ReVISION 2 is intended for use by healthcare professionals qualified to review, quantify, and report right ventricular (RV) structure and function from 3D echocardiographic data, to support the diagnosis of patients with suspected heart disease.
### General description
ReVISION 2 is a software as a medical device (SaMD) designed to assess global and segmental morphology and function of the right ventricle (RV) using 3D echocardiography-derived digital medical data. The device accepts DICOM files acquired directly from compatible ultrasound systems (GE, Philips) and maintains backward compatibility with UCD files from TomTec systems. An AI-powered auto-contouring module automatically generates a 3D surface model of the RV from the input data; the user may review, edit, accept, or reject the generated contours and anatomical landmarks. From the resulting surface model, ReVISION 2 calculates RV volumes (EDV, ESV, SV), ejection fraction (longitudinal, radial, anteroposterior), global and segmental 3D strain (longitudinal, circumferential, area), and global, regional, and segmental curvature metrics characterizing RV shape remodeling. Results are presented in a structured report with comparison to normal reference ranges.
The device is intended to provide information for use by the care professional, in conjunction with other clinically relevant information, to assist in the diagnosis of patients (adults only) with suspected heart disease.
The ReVISION 2 System consists of the following components:
- Web Portal: UI enabling healthcare professionals to upload DICOM/UCD studies and review, edit, accept, or reject auto-generated contours
- API: interfaces between the Analytics Engine and the Web Portal
- Analytics Engine: core computational module producing volumetric, strain, and curvature outputs from the surface model
- AI Contouring Module: PyTorch-based neural network generating the 3D RV surface model
2
{6}
Argus Cognitive, Inc.
ReVISION - K251417
[LOGO]
ARGUS Cognitive
- Outcome Report: structured report presenting calculated metrics with normal-range comparison
## Intended use and Indications for Use [807.92(a)(5)]
Intended Use: ReVISION 2 is a clinical software package designed for review, quantification, and reporting of right ventricle (RV) structures and function based on 3D echocardiography-derived digital medical data. ReVISION 2 is not intended to be used for reading of mammography images.
Indications for Use: Indications for use of ReVISION 2 are quantification and reporting of right ventricle (RV) structures and function of patients (adults only) with suspected disease to support the physician in the diagnosis.
Intended Use Population: Adults (greater than 21 years of age). ReVISION 2 is not intended for use in pediatric populations or individuals under the age of 21.
ReVISION 2's indications for use are a subset of the primary predicate's (TomTec-Arena TTA2) indications, which cover cardiovascular, fetal, and abdominal structures and function; ReVISION 2 addresses only RV structures and function. This narrower scope does not raise new questions of safety or effectiveness, as detailed under Comparison of Technological Characteristics [807.92(a)(6)] below.
3
{7}
Argus Cognitive, Inc.
ReVISION - K251417
ARGUS Cognitive
# Comparison of Technological Characteristics [807.92(a)(6)]
| **GENERAL COMPARISON** | | | | |
| --- | --- | --- | --- | --- |
| Feature | Predicate Device TOMTEC-ARENA TTA2 (4D RV-Function) | Secondary Predicate Device ReVISION 1.0 | Subject Device ReVISION 2.0 | Discussion / Comment |
| **K-number** | K201632 | K223322 | K251417 | Subject of this submission is ReVISION 2.0. |
| **Regulation Number and Regulation Name** | 21CFR 892.2050; System, Image processing, Radiological – Picture Archiving and Communications System (PACS) | 21CFR 892.2050; System, Image processing, Radiological – Picture Archiving and Communications System (PACS) | 21CFR 892.2050; System, Image processing, Radiological – Picture Archiving and Communications System (PACS) | Identical to predicate device. |
| **Classification Product Code** | QIH | LLZ | QIH | Identical to secondary predicate device. |
| **Class** | 2 | 2 | 2 | Identical to predicate device. |
| **Classification Panel** | Radiology | Radiology | Radiology | Identical to predicate device. |
| **Intended Use** | TOMTEC-ARENA software is a clinical software package designed for review, quantification and reporting of structures and function based on multi-dimensional digital medical data acquired with different modalities.TOMTEC-AREN | ReVISION software is a clinical software package designed for review, quantification and reporting of right ventricle (RV) structures and function based on 3D echocardiography-derived digital medical data. | ReVISION software is a clinical software package designed for review, quantification and reporting of right ventricle (RV) structures and function based on 3D echocardiography-derived digital medical data. | A subset of the predicate device's intended use. |
4
{8}
Argus Cognitive, Inc.
ReVISION - K251417
ARGUS Cognitive
| | A is not intended to be used for reading of mammography images. | ReVISION software is not intended to be used for reading of mammography images. | ReVISION software is not intended to be used for reading of mammography images. | |
| --- | --- | --- | --- | --- |
| Indications for Use | Indications for use of TOMTEC ARENA TTA2 software are quantification and reporting of cardiovascular, fetal, abdominal structures and function of patients with suspected disease to support the physicians in the diagnosis | Indications for use of the Argus Cognitive ReVISION Software are quantification and reporting of right ventricle (RV) structures and function of patients (adults only) with suspected disease to support the physician in the diagnosis. | Indications for use of ReVISION are quantification and reporting of right ventricle (RV) structures and function of patients (adults only) with suspected disease to support the physician in the diagnosis. | A subset of the predicate device's indications. |
| Site of Use | Inside and outside of Hospitals, Clinics, and Physician's offices. | Intended use environments are hospitals, clinics, and physician's offices. | Inside and outside of Hospitals, Clinics, and Physician's offices. | Identical to predicate device. |
| Design | Software as a medical device | Software as a medical device | Software as a medical device | Identical to predicate device. |
# TECHNICAL COMPARISON
| Feature | Predicate Device TOMTEC-ARENA TTA2 (4D RV-Function) | Reference Device ReVISION 1.0 | Subject Device ReVISION 2.0 | Discussion / Comment |
| --- | --- | --- | --- | --- |
| Application Description | The 4D RV-Function is a right ventricular quantification tool for routine clinical work, pulmonary hypertension, and right-sided heart failure. The application helps to overcome | Software function provides a morphological and functional assessment of the right ventricle based on a surface model of the RV. It supports routine workflows for loading, analyzing and saving medical studies. | Software function provides a morphological and functional assessment of the right ventricle based on a surface model of the RV. It supports routine workflows for loading, analyzing and saving medical studies. | ReVISION is identical only in a subset of functions of the predicate device: it can load, analyze and save only 3D echocardiographic models of the right |
5
{9}
Argus Cognitive, Inc.
ReVISION - K251417
ARGUS Cognitive
| | complexity of right ventricle analysis by calculating standard values based on a semi-automatically generated 3D surface model. | Software function provides a platform for uploading, reviewing, analyzing and storing 3D echocardiography-derived surface models of the RV. The results of the analysis support clinical workflows by the morphological and functional assessment of the RV. | Software function provides a platform for uploading, reviewing, analyzing and storing 3D echocardiography-derived surface models of the RV. The results of the analysis support clinical workflows by the morphological and functional assessment of the RV. | ventricle (RV), identical to the "4D RV-Function" module of the predicate device. The scope covers no other imaging modality, cardiac chamber or organ. |
| --- | --- | --- | --- | --- |
| SW version | 3.0 | 1.0 | 2.0 | Updated due to changes to SW code. |
| Measurements | Volume and function of Right Ventricle EDVI ESVI | ☐ EDV: End-diastolic Volume ☐ ESV: End-systolic Volume ☐ EF: Ejection Fraction ☐ SV: Stroke Volume • Longitudinal EF • Radial EF • Anteroposterior EF • Global and segmental 3D longitudinal strain • Global and segmental 3D circumferential strain Global and segmental 3D area strain | Volume and function of Right Ventricle ☐ EDV: End-diastolic Volume ☐ ESV: End-systolic Volume ☐ EF: Ejection Fraction ☐ SV: Stroke Volume • Longitudinal EF • Radial EF • Anteroposterior EF • Global and segmental 3D longitudinal strain • Global and segmental 3D circumferential strain Global and segmental 3D area strain Added: • Global and segmental curvature | Added measurements compared to both primary and secondary predicate devices. |
| Export formats | Beutel value export into .ucd, .ply or .obj or .stl | None | None | No 3D beutel export possibility. |
6
{10}
Argus Cognitive, Inc.
ReVISION - K251417
ARGUS Cognitive
| | formats | | | |
| --- | --- | --- | --- | --- |
| Contour Generation | 3D surface model is created automatically using machine learning algorithms without user interaction. User is able to edit, accept or reject the contours or the anatomical landmarks. | None | 3D surface model is created automatically using machine learning algorithms without user interaction. User is able to edit, accept or reject the contours or the anatomical landmarks. | Identical to predicate device. |
# Substantial Equivalence (SE) discussion
Subject Device analyzes the same inputs as the predicate devices but in a more detailed manner and provides novel measures without altering the raw information contained by these inputs (i.e., 3D echocardiographic videos or 3D models). Thus, these novel features do not raise different questions of safety and effectiveness but support clinical decision making with extra information derived from the raw data.
# Key software features and comparisons:
- Independent operation & Direct DICOM processing: Unlike ReVISION 1.0, which required a TomTec 4D RV module to generate the input 3D surface model, ReVISION 2 accepts DICOM files directly from GE and Philips ultrasound systems and generates the 3D RV surface model internally via its AI-powered auto-contouring module, while retaining backward compatibility with UCD files from TomTec systems. This automated contour-generation capability is functionally identical to the auto-contouring already present in the primary predicate (TomTec-Arena TTA2), as reflected in the Technical Comparison table above — it is new relative to the secondary predicate (ReVISION 1.0) but not relative to the primary predicate.
- Curvature Analysis: ReVISION 2 introduces global, regional, and segmental curvature metrics characterizing RV shape remodeling, calculated directly from the same 3D surface model already used for volumetric and strain measurements. This is a novel derived measure not present in either predicate device, but it does not alter or introduce new raw input data — it is computed entirely from the existing, validated surface model — and therefore does not raise different questions of safety or effectiveness.
- Scope: ReVISION 2's functional scope remains a subset of the primary predicate's broader intended use (RV structures and function only, vs. TomTec's coverage of cardiovascular, fetal, and abdominal structures across multiple modalities) — a narrower scope than the predicate, which supports rather than complicates the substantial equivalence argument.
7
{11}
Argus Cognitive, Inc.
ReVISION - K251417
[LOGO]
ARGUS Cognitive
## Performance Data [807.92(b)]
Performance testing supporting substantial equivalence included nonclinical testing - software verification, analytical validation (auto-contouring/volumetric quantification and curvature), and cybersecurity assessment - summarized below.
## Nonclinical Testing Summary [807.92(b)(1)]
### Software verification
Software verification was performed at the unit, integration, and system levels in accordance with IEC 62304:2006 and the FDA's General Principles of Software Validation. Unit-level testing covered individual modules (auto-contouring, curvature calculation, ECG/keyframe detection, DICOM reconstruction) using black-box and white-box strategies; frontend and integration tests covered the full web application (Galactus authentication, ReVISION workflow) end-to-end. System-level testing assessed availability and recovery behavior. Detailed test plans, cases, and results are provided in the Verification and Validation Report (REV2-VVR).
### Analytical validation - Auto-contouring and volumetric quantification
The accuracy of ReVISION 2's automated right ventricular quantification was evaluated using an independent external validation dataset of 46 subjects spanning a broad range of RV sizes and systolic function. Automated measurements were compared against a reference standard generated from averaged manual contours of three expert cardiologists. Auto-contoured RVEF values demonstrated an absolute error tolerance of 5% on average. Performance was further evaluated across demographic and clinical subgroups (four defined clinical study groups spanning heart failure, arrhythmia/hemodynamic symptoms, ischemic/valvular/structural disease, and cerebrovascular/systemic conditions): mean absolute errors ranged approximately 11–21 mL for EDV, 9–12 mL for ESV, and 3–8 percentage points for RVEF, depending on subgroup. Observed variability was comparable to published inter-observer variability of manual RV contouring.
### Analytical validation - Curvature
Curvature values calculated by ReVISION 2 were validated against Materialise 3-matic Medical 18.0 (K060950), an FDA-cleared reference method, using the RVENet population. Global, free wall, and septal curvature values demonstrated moderate-to-strong correlation with the reference device (r = 0.6327–0.8046, all p < 0.05), meeting pre-specified acceptance criteria. Systematic differences between the two methods were attributable to underlying algorithmic differences (vertex-based vs. face-based curvature estimation) and were concentrated in planar valve-annulus regions, which are geometric artifacts of mesh generation rather than true myocardial structures and carry no diagnostic significance. Clinically meaningful curvature - pertaining to the right ventricular free wall and interventricular septum, which are directly involved in remodeling and contractile function - showed strong agreement with the reference method.
### Cybersecurity
Security assessment activities were performed in accordance with FDA's "Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions" (September 2023). ReVISION 2 is classified as Moderate Level of Concern. Threat modeling was conducted using the STRIDE methodology across all system trust boundaries (authentication, web service, database, processing modules, file storage, network infrastructure). DICOM input handling implements two-layer defense-in-depth validation.
8
{12}
Argus Cognitive, Inc.
ReVISION - K251417
[LOGO]
ARGUS Cognitive
TLS 1.2/1.3 cipher suites conform to current NIST-recommended cryptographic standards.
## Clinical Testing Summary [807.92(b)(2)]
Not applicable — no clinical testing was performed; substantial equivalence is supported by nonclinical/analytical validation described above
## CONCLUSION AND SUBSTANTIAL EQUIVALENCE STATEMENT
ReVISION 2 is substantially equivalent to its predicate devices based on:
1. Similar Intended Use: ReVISION 2's intended use and indications for use are a subset of the primary predicate's (TomTec-Arena TTA2): both provide review, quantification, and reporting of cardiac structures and function from digital medical imaging data to support physician diagnosis. ReVISION 2's scope is narrower than the primary predicate's (RV only, vs. cardiovascular/fetal/abdominal structures across modalities) and identical in scope to the secondary predicate (ReVISION 1.0).
2. Similar fundamental scientific technology: All three devices are software-only medical devices (SaMD) that generate a 3D surface model from echocardiographic data and derive quantitative morphological and functional measurements from that model. ReVISION 2's AI-powered auto-contouring is functionally equivalent to the automatic 3D surface model generation already present in the primary predicate. Curvature analysis is calculated entirely from the same validated surface model used for volumetric and strain measurements, introducing no new raw input data or measurement modality.
3. Performance characteristics: Analytical validation against an independent 46-subject external cohort demonstrated RVEF accuracy within a 5% absolute error tolerance, with EDV and ESV mean absolute errors consistent with published inter-observer variability of manual RV contouring. Curvature values showed moderate-to-strong correlation (r = 0.63–0.80, p < 0.05) against an FDA-cleared reference method (Materialise 3-matic Medical, K060950), with observed discrepancies confined to clinically insignificant planar regions.
4. Equivalent safety profile: ReVISION 2 operates as a software-only decision support tool with no direct patient contact, consistent with both predicates. Cybersecurity controls (STRIDE threat modeling, DICOM input validation, current NIST-recommended cryptography) are consistent with the Moderate Level of Concern classification shared with the predicate devices.
The technological enhancements in ReVISION 2 (independent DICOM processing and curvature analysis) do not raise different questions of safety and effectiveness. These enhancements provide improved clinical utility and reduced dependency on third-party software while maintaining the fundamental operating principles and risk profile of the predicate devices.
Verification, validation, and cybersecurity testing demonstrate that ReVISION 2 is safe and effective for its intended use and is substantially equivalent to the predicate devices.
9
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Guidance alerts
New and changed FDA guidance documents, emailed as a daily digest.
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the ? button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only Software as a Medical Device, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (Software as a Medical Device), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.