K243446 · GE Medical Systems SCS · OWB · Feb 25, 2025 · Radiology
Device Facts
Record ID
K243446
Device Name
3DXR
Applicant
GE Medical Systems SCS
Product Code
OWB · Radiology
Decision Date
Feb 25, 2025
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.1650
Device Class
Class 2
Attributes
AI/ML, Software as a Medical Device, Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K243446 · Feb 25, 2025
3DXR
GE Medical Systems SCS
Retrospective clinical exams (CBCT acquisitions) from 13 clinical sites
A retrospective clinical evaluation was conducted to validate the performance of the CleaRecon DL algorithm in removing streak artifacts from CBCT images. 110 patient exams were reviewed by 13 clinicians to assess image quality, artifact reduction, and diagnostic confidence compared to conventional reconstruction.
3DXR is the AW application which is intended to perform the three-dimensional (3D) reconstruction computation of any images acquired with a 3D Acquisition mode of the X-ray interventional system for visualization under Volume Viewer. The 3D Acquisition modes are intended for imaging vessels, bones and soft tissues as well as other internal body structures. The 3D reconstructed Volume assist the physician in diagnosis, surgical planning, Interventional procedures and treatment follow-up.
Device Story
3DXR is a post-processing software application running on the Advantage Workstation (AW) platform. It processes CBCT 3D acquisition images from fixed interventional X-ray systems. The device performs 3D reconstruction, including a new 'CleaRecon DL' option—a deep-learning convolutional neural network (CNN) designed to remove streak artifacts caused by pulsatile blood flow around contrast-enhanced vessels and stents. Additional features include 3DStent (motion-compensated coronary stent reconstruction), Motion Freeze, Metal Artifact Reduction, Iodine Streaks Reduction, and Scatter Reduction. The software is used by physicians in clinical settings (e.g., interventional suites) to assist in diagnosis, surgical planning, and treatment follow-up. Clinicians view reconstructed volumes via the Volume Viewer application. The output provides clearer images, aiding clinical confidence without obscuring anatomical structures or creating artificial ones.
Clinical Evidence
Retrospective clinical evaluation of 110 independent adult patient exams (Brain, Liver, Prostate, Aorta) across 13 sites. 13 clinicians performed 490 side-by-side comparisons of conventional vs. CleaRecon DL-processed images. Results: 98% of CleaRecon DL images were rated clearer than conventional; no instances of hidden anatomical structures or artificial patterns were identified by clinicians. Bench testing confirmed statistically significant reduction in Mean Absolute Error (MAE) and standard deviation of streak artifacts.
Technological Characteristics
Software-only application; runs on AW VolumeShare workstation. CleaRecon DL utilizes a Deep-Learning Convolutional Neural Network (CNN). Complies with NEMA PS 3.1-3.20 (DICOM). Designed under 21 CFR 820 and ISO 13485. Software level of concern: Basic.
Indications for Use
Indicated for adult patients undergoing interventional procedures requiring 3D reconstruction of CBCT images for visualization of vessels, bones, soft tissues, and internal structures. CleaRecon DL option is validated for adult population only.
Regulatory Classification
Identification
An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.
Special Controls
*Classification.* Class II (special controls). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image shows the logos of the Department of Health & Human Services and the Food and Drug Administration (FDA). The Department of Health & Human Services logo is on the left, and the FDA logo is on the right. The FDA logo is a blue square with the letters "FDA" in white, followed by the words "U.S. FOOD & DRUG ADMINISTRATION" in blue.
February 25, 2025
GE Medical Systems SCS % Ning WEN Regulatory Affairs Program Manager 283 Rue De La Miniere BUC. 78530 FRANCE
Re: K243446
Trade/Device Name: 3DXR Regulation Number: 21 CFR 892.1650 Regulation Name: Image-Intensified Fluoroscopic X-Ray System Regulatory Class: Class II Product Code: OWB, QIH Dated: November 6, 2024 Received: January 24, 2025
Dear Ning WEN:
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,
Lu Jiang
Lu Jiang, Ph.D. Assistant Director Diagnostic X-Ray Systems 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) | K243446 |
|-------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Device Name | 3DXR |
| Indications for Use (Describe) | 3DXR is the AW application which is intended to perform the three-dimensional (3D) reconstruction computation of any images acquired with a 3D Acquisition mode of the X-ray interventional system for visualization under Volume Viewer. The 3D Acquisition modes are intended for imaging vessels, bones and soft tissues as well as other internal body structures. The 3D reconstructed Volume assist the physician in diagnosis, surgical planning, Interventional procedures and treatment follow-up. |
| Type of Use (Select one or both, as applicable) | <label><input checked="" type="checkbox"/> Prescription Use (Part 21 CFR 801 Subpart D)</label><br><label><input type="checkbox"/> Over-The-Counter Use (21 CFR 801 Subpart C)</label> |
| 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/1 description: The image shows the logo for GE HealthCare. The logo consists of the GE monogram in a circle on the left, followed by the text "GE HealthCare" on the right. The logo is purple in color and the text is in a sans-serif font.
#### K243446 510(k) Summary of Safety and Effectiveness
In accordance with 21 CFR 807.92 the following summary of information is provided.
| Date: | January 24, 2025 |
|-------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|
| Submitter: | GE Medical Systems SCS<br>Establishment Registration Number - 9611343<br>283, rue de la Minière<br>78530 Buc, France |
| Primary Contact: | Ning WEN<br>Regulatory Affairs Program Manager<br>GE HealthCare, (GE Medical Systems SCS)<br>Tel: +33 6 2324 6023<br>Email: ning.wen@gehealthcare.com |
| Secondary Contact | Michelle Huettner<br>Regulatory Affairs Director<br>Tel: +1 901 558 8035<br>Email: michelle.huettner@gehealthcare.com |
| Device Trade Name: | 3DXR |
| Common/Usual Name: | 3DXR, with CleaRecon DL option |
| Regulation Number: | 21CFR 892.1650, Image-intensified fluoroscopic x-ray system |
| Primary Product Code: | OWB |
| Secondary Product Code: | QIH |
| Regulatory Class: | Class II |
| Predicate Device: | |
| Device Name: | 3DXR |
| Manufacturer: | GE Medical Systems SCS |
| 510(k) number: | K181403 |
| Regulation Number: | 21CFR 892.1650, Image-intensified fluoroscopic x-ray system |
| Product Code: | OWB |
| Regulatory Class: | Class II |
#### Device Description and Marketed Devices:
3DXR is a post-processing software-only application, runs on Advantage Workstation (AW) platform [K110834], and performs 3D reconstruction for the CBCT 3D acquisition images (input) acquired from the fixed interventional X-ray system [K181403, K232344]. The reconstructed 3D volume (output) is visualized under Volume Viewer application [K041521].
{5}------------------------------------------------
The proposed 3DXR is a modification from the predicate 3DXR [included and cleared in K181403]. A new option, called CleaRecon DL, based on Deep-Learning (DL) technology, is added in the proposed subject 3DXR application. This new CleaRecon DL option triggered this subject 510(k) submission.
The proposed 3DXR with CleaRecon DL option addresses the same user needs as predicate 3DXR. The goal of CleaRecon DL option is to remove streak artifacts caused by the pulsatile nature of blood flow around contrasted objects such as contrast medium injected vessels and stent structures.
The primary features/functions of the proposed software are:
- . 3D Reconstruction for the CBCT images.
- . CleaRecon DL: powered by a Deep-Learning algorithm, ability to remove streak artifacts caused by the pulsatile nature of blood flow and appearing around contrasted objects such as contrast medium injected vessels and devices.
- . 3DStent: ability to reconstruct coronary stent with the compensation of the respiratory and cardiac motion.
- Ability to read Imaging Purposes information on CBCT images (containing the acquisition system 3D preset information).
- Motion Freeze: ability to reduce the artifacts caused by involuntary respiratory motion.
- Metal Artifact Reduction (MAR): ability to reduce the artifacts induced by the presence of metallic devices.
- . Active Tracker Detection: allowing to localize and record Active Tracker position for future automatic registration of reconstructed volume with Ultrasound images.
- . lodine Streaks Reduction: ability to reduce the streak artifacts induced by the high density of iodine.
- Scatter Reduction: ability to reduce the scatter-induced non-uniformities.
- Extended Range: allowing to increase the dynamic range of the 3D Volume.
- CT Format: labeling the reconstructed 3D Volume with CT format.
- Image Filters.
- 3D Volume Size selection.
- 3D Sub Volume selection.
#### Intended Use:
3DXR is the AW application which is intended to perform the three-dimensional (3D) reconstruction computation of any images acquired with a 3D Acquisition mode of the X-ray interventional system for visualization under Volume Viewer.
#### Indications for Use:
3DXR is the AW application which is intended to perform the three-dimensional (3D) reconstruction computation of any images acquired with a 3D Acquisition mode of the X-ray interventional system for visualization under Volume Viewer.
The 3D Acquisition modes are intended for imaging vessels, bones and soft tissues as well as other internal body structures.
The 3D reconstructed Volume assist the physician in diagnosis, surgical planning, Interventional procedures and treatment follow-up.
{6}------------------------------------------------
Image /page/6/Picture/1 description: The image shows the logo for GE HealthCare. The logo consists of a purple circular emblem with a stylized "GE" monogram inside. To the right of the emblem, the words "GE HealthCare" are written in a simple, sans-serif font, also in purple. The logo is clean and modern, conveying a sense of trust and innovation.
### Technology:
The proposed device 3DXR employs the same fundamental scientific technology as its predicate device 3DXR [K181403].
In addition, the proposed device 3DXR includes an option CleaRecon DL powered by a Deep-Learning (DL) Convolutional Neural Network (CNN) for removing streak artifacts. The CleaRecon DL algorithm was trained and qualified using pairs of images with and without streak artifacts.
#### Device Modification Overview:
The table below summarizes the substantive feature/technological differences and similarities between the predicate device and the proposed device:
| Specification | Predicate Device:<br>3DXR [K181403] | Proposed Device:<br>3DXR |
|--------------------------|----------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------|
| Indications for Use | Identical | Identical |
| Patient Population | No limitations on the patient<br>population | Same, except for CleaRecon DL<br>option which is validated for adult<br>population only |
| 3D Reconstruction | Yes | Yes |
| CleaRecon DL | No, streak artifacts reduction by<br>Iodine Streaks Reduction only | Yes, streak artifacts removal<br>powered by DL-based algorithm |
| 3DStent | No, 3D reconstruction of moving<br>object with the compensation of<br>the respiratory motion | Yes, 3D reconstruction of coronary<br>stent with the compensation of the<br>respiratory and cardiac motion |
| Imaging Purposes | No, read multiple acquisition<br>system DICOM tags to identify<br>the clinical protocol | Yes, read acquisition system 3D<br>preset in Imaging Purposes DICOM<br>tag |
| Motion Freeze | Identical | Identical |
| Metal Artifact Reduction | Identical | Identical |
| Active Tracker Detection | Identical | Identical |
| lodine Streaks Reduction | Identical | Identical |
| Scatter Reduction | Yes | Yes |
| Extended Range | Identical | Identical |
| CT Format | Identical | Identical |
| Image Filters | Yes | Yes |
| 3D Volume Size selection | Identical | Identical |
| 3D Sub Volume selection | Yes | Yes |
{7}------------------------------------------------
Image /page/7/Picture/1 description: The image shows the GE Healthcare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is a stylized, circular design with intertwined letters, and the text is in a simple, sans-serif font.
#### Determination of Substantial Equivalence:
#### Summary of Non-Clinical, Design Control Testing
The proposed device, 3DXR, has successfully completed the required design control testing per GE HealthCare Quality Management System. No additional hazards were identified, and no unexpected test results were observed. The proposed device complies with NEMA PS 3.1 - 3.20 Digital Imaging and Communications in Medicine (DICOM) Set (Radiology) standard. It was designed and manufactured under the Quality System Regulations of 21CFR 820 and ISO 13485.
The following quality assurance measures were applied to the development of the device:
- . Requirements Definition
- . Risk Analysis
- . Technical Design Reviews
- . Formal Design Reviews
- Software Development Lifecycle
- . Performance testing (Verification, Validation)
- . System Testing (Verification, Validation)
The proposed 3DXR has been successfully verified on the AW VolumeShare workstation [K110834] platform. All of the testing and results did not raise new or different questions of safety and effectiveness other than those already associated with the predicate device.
The substantial equivalence determination is also based on the software documentation for a BASIC level.
#### Additional Non-Clinical Testing
Engineering bench testing was used to demonstrate the performances of the new CleaRecon DL algorithm's capabilities to remove streak artifacts from CBCT reconstructions.
Performance was first tested on a segregated test dataset of image pairs (with and without applying CleaRecon DL for streak artifact correction), independent from the dataset for training of CleaRecon DL algorithm. Mean Absolute Error (MAE) and Structural Similarity Index Measure (SSIM) were computed for two samples. Acceptance criteria were reduction of MAE and increase of SSIM. A statistically significant reduction in MAE and increase in SSIM were observed between the two samples. It was thus concluded that the CleaRecon DL option reduces streak artifacts on tested images.
Performance was then tested on phantoms. CBCT images acquisitions made with the fixed interventional X-ray system [K181403, K232344] were performed with simulated streak artifacts conditions and without (reference). MAE with respect to the reference and standard deviation (SD) were computed to quantify streak artifact reduction. Acceptance criteria were reduction of MAE and SD. The reduction of both MAE and SD was observed leading to the conclusion that CleaRecon DL reduces streak artifacts on phantoms.
{8}------------------------------------------------
Image /page/8/Picture/1 description: The image shows the GE HealthCare logo. The logo consists of a purple circular emblem with a stylized "GE" monogram inside. To the right of the emblem, the words "GE HealthCare" are written in a simple, sans-serif font, also in purple.
The engineering bench testing passed the predefined acceptance criteria, demonstrated the CleaRecon DL performance to remove streak artifacts, and no degradation of image quality, nor other concerns related to safety and performance were observed.
#### Summary of Clinical Testing
A retrospective clinical image quality evaluation was conducted to demonstrate the performances of the new CleaRecon DL algorithm's capabilities to remove streak artifacts from CBCT reconstructions and to ensure final validation of CleaRecon DL derived outputs.
110 independent exams (each from a unique patient) coming from 13 clinical sites were used in this evaluation, including:
Brain/Head: 20 patients Liver/Abdomen: 30 patients Prostate/Pelvic: 20 male patients Aorta/Stent-graft: 20 patients Other anatomies: 20 patients
These exams were retrospectively collected from the CBCT acquisitions performed with the fixed interventional X-ray system [K181403. K232344] on adult patients (pediatrics excluded) undergoing interventional procedures. 80 patients came from the US, 26 patients came from France, 4 patients came from Japan. These exams were anonymized. There were no inclusion criteria of age (within adult range) and sex/gender (except for prostate). These exams were independent and never used for the training and tuning of CleaRecon DL algorithm.
13 clinicians were recruited for this evaluation. Each of the 110 exams (with and without applying CleaRecon DL) was prepared so that the conventional reconstruction images and the images reconstructed with CleaRecon DL option were presented side by side on AW, with the same display conditions, and were compared / evaluated at least 3 times independently, resulting in 490 pairs of clinicians' evaluations.
For each image comparison, the physicians were asked (through 8 questions):
- to evaluate the impact of CleaRecon DL on CBCT image quality, -
- । to confirm that CleaRecon DL removes streaks artifacts and assess whether it brings other artifacts when compared to the conventional CBCT reconstruction.
- to assess if CleaRecon DL provides a clearer image and how it impacts their confidence in image interpretation.
- to assess if it brings artificial structures and/or hides important anatomical structures.
The evaluation results met the predefined acceptance criteria and substantiated the performance claims. In 98% of the cases, the CBCT images reconstructed with CleaRecon DL option are evaluated as clearer than the conventional CBCT images.
Within 489 reviews, clinicians did not identify any structure or pattern that has been hidden or artificially created by CleaRecon DL when compared to the original reconstruction.
{9}------------------------------------------------
Image /page/9/Picture/1 description: The image contains the GE Healthcare logo. The logo consists of a purple circular emblem with a stylized "GE" monogram inside. To the right of the emblem, the words "GE HealthCare" are written in a simple, sans-serif font, also in purple. The overall design is clean and corporate, representing the brand identity of GE Healthcare.
#### Substantial Equivalence Conclusion
The changes to the predicate device 3DXR do not create new Intended Use nor Indication for Use. The proposed device 3DXR has identical or substantially equivalent technological characteristics as its predicate device.
GE HealthCare's quality system's design, verification, and risk management processes did not identify any new questions of safety or effectiveness, hazards, unexpected results, or adverse effects stemming from the changes to the predicate.
Based on the development under GE HealthCare's quality system, successful design verification and validation, software documentation for a "Basic" level, along with the engineering bench testing and the clinical evaluation by physicians demonstrate that the proposed 3DXR is substantially equivalent to, and hence as safe and as effective for its Intended Use as the legally marketed predicate device.
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:
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 Tutorial 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-only devices, 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-only devices), 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.