DenSeeMammo is a software application intended for use with Full Field Digital Mammography systems. DenSeeMammo estimates BI-RADS breast density category by analyzing processed digital 2D mammograms using a fully automated comparison procedure. DenSeeMammo provides a BI-RADS breast density 5th Edition category to aid radiologists in the assessment of breast density. DenSeeMammo produces adjunctive information. It is not a diagnostic aid since the final assessment of breast density category is made by an MQSA qualified interpreting physician. DenSeeMammo core software has been built and tested on OS X based computers. DenSeeMammo graphical use interface software has been built and tested on Windows, OS X and Linux based computers. DenSeeMammo is compatible for images obtained from GE Senographe Essentials and Hologic Selenia Dimension systems.
Device Story
DenSeeMammo is a software application for radiologists to estimate breast density. It accepts processed digital 2D mammograms (DICOM) from GE Senographe Essentials or Hologic Selenia Dimension systems as input. The device uses a proprietary, fully automated comparison algorithm to match patient images against a qualified database of images previously assessed by MQSA-qualified radiologists. It outputs a BI-RADS 5th Edition breast density category per breast and per patient (based on the maximum density of both breasts). The system operates in a client-server mode on a local network, with a web browser interface for image selection and result display. It is intended as an adjunctive tool; it is not a diagnostic aid. The final assessment remains the responsibility of an MQSA-qualified interpreting physician. The device benefits patients by providing standardized, objective breast density information to support clinical decision-making.
Clinical Evidence
Bench testing only. Verification included reproducibility testing on image datasets, comparison of left/right breast density results, and performance evaluation against MQSA-qualified radiologist visual assessments. Testing utilized substantial datasets of two-view (CC+MLO) and single-view (CC or MLO) images from GE and Hologic systems. Clinical validation consisted of beta site testing to assess system integration and usability for target users. All testing met established acceptance criteria.
Technological Characteristics
Software-based image processing system. Operates in client-server mode on local networks. Developed using Java 1.8 with a 3-component web application architecture (Model-View-Controller pattern). Compatible with GE Senographe Essentials and Hologic Selenia Dimension systems. Core software tested on OS X; GUI tested on Windows, OS X, and Linux. Compliant with IEC 62304 (software lifecycle) and ISO 14971 (risk management).
Indications for Use
Indicated for symptomatic and asymptomatic women undergoing mammography to aid radiologists in assessing breast density using BI-RADS 5th Edition categories.
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}------------------------------------------------
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo features the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION" in blue text.
STATLIFE % Mrs. Valérie Hélin Authorized Correspondent EPIDEMIO3D 50 Milk Street, 16th Floor BOSTON MA 02109
June 26th, 2018
Re: K173574
Trade/Device Name: DenSeeMammo Regulation Number: 21 CFR 892.2050 Regulation Name: Picture Archiving And Communications System Regulatory Class: Class II Product Code: LLZ Dated: May 29, 2018 Received: May 31, 2018
Dear Mrs. Hélin:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820);
{1}------------------------------------------------
## Page 2 - Mrs. Valérie Hélin
and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). 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 (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Jeff Balyer
for Robert Ochs, Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
# Indications for Use
Form Approved: OMB No. 0910-0120 Expiration Date: January 31, 2017 See PRA Statement below.
510(k) Number K173574
Device Name DenSeeMammo
### Indications for Use (Describe)
DenSeeMammo is a software application intended for use with Full Field Digital Mammography systems.
DenSeeMammo estimates Bl-RADS breast density category by analyzing processed digital 2D mammograms using a fully automated comparison procedure.
DenSeeMammo provides a BI-RADS breast density 5th Edition category to aid radiologists in the assessment of breast density. DenSeeMammo produces adjunctive information. It is not a diagnostic aid since the final assessment of breast density category is made by an MQSA qualified interpreting physician.
DenSeeMammo core software has been built and tested on OS X based computers.
DenSeeMammo graphical use interface software has been built and tested on Windows, OS X and Linux based computers. DenSeeMammo is compatible for images obtained from GE Senographe Essentials and Hologic Selenia Dimension systems.
Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D) র
__ Over-The-Counter Use (21 CFR 801 Subpart C)
### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
## 510(K) SUMMARY
Prepared June 20, 2018
#### Submitter Information 1
| Company Name: | STATLIFE |
|--------------------------------|-----------------------------------------------------------------------------|
| Company Address: | 39 RUE CAMILLE DESMOULINS<br>94800 VILLEJUIF FRANCE |
| Company Phone: | +33 660 848 385 |
| Company Facsimile: | +33 185 091 475 |
| Contact Person: | Stéphane Ragusa, CEO |
| Authorized Correspondent Phone | Valérie Hélin, Director of medical and regulatory affair<br>+33 682 437 010 |
#### 2 Trade name and Common name
| Trade Name: | DenSeeMammo |
|-------------------|------------------|
| Software Version: | 1.2 |
| Common Name: | Imaging Software |
#### 3 Device Classification
| Regulatory Class: | II |
|-----------------------|----------------------------------------------------------|
| Review category: | Class II |
| Classification Panel: | Radiology; |
| Product Code: | LLZ |
| Classification: | System, Image Processing, Radiological: 21 CFR § 892.205 |
#### Identification of Predicate Device 4
The modified software is substantially equivalent to DenSeeMammo Software version 1.0 cleared pursuant to K152009 cleared December 5吨, 2017
{4}------------------------------------------------
#### 5 Predicate Device Description
DenSeeMammo analyzes processed digital 2D mammograms in a fully automated comparison procedure that produces a BI-RADS breast density category.
DenSeeMammo handles processed images extracted from DICOM files as input.
DenSeeMammo core software has been built and tested on OS X based computers.
DenSeeMammo graphical user interface software has been built and tested on Windows, OS X and Linux based computers.
DenSeeMammo software is a component which accepts digital mammography images as an input. The software processes and analyses the image according to proprietary algorithms which allow comparison to qualified databases containing images previously assessed by radiologists. For each patient it provides measures of BI-RADS breast density category. DenSeeMammo provides results per patient based on the maximum density category of the two breasts.
The patient population is symptomatic and asymptomatic women undergoing mammography. The software does perform illustrative image display but only for illustrative purposes and not for interpretation or diagnostic.
#### б Comparison with Predicate device
DenSeeMammo software version 1.2 works in the same way as DenSeeMammo software 1.0 but is updated to make it compatible with digital mammograms from Hologic mammography systems and can work with a pair of images composed of two views (craniocaudal (CC) and mediolateral oblique (MLO)) or with an image composed of one view (CC for GE images, and CC or MLO for Hologic images).
{5}------------------------------------------------
#### Table 1 Substantial Equivalence comparison table
| Characteristics | Predicate Device<br>DENSEEMAMMO v1.0 (K152009) | Submission Device<br>DENSEEMAMMO v1.2 |
|---------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Classification | LLZ | LLZ |
| Classification | 892.2050 | 892.2050 |
| Software level of concern | Moderate | Moderate |
| Device type | Not an interpretive or diagnostic aid | Not a diagnostic aid |
| Intended Use | DenSeeMammo is a software<br>application intended for use with digital<br>mammography systems.<br>DenSeeMammo estimates BI-RADS<br>breast density value by analyzing<br>processed digital 2D mammograms<br>using a fully automated comparison<br>procedure.<br>DenSeeMammo provides a BI-RADS<br>breast density 5th Edition category to<br>aid radiologists in the assessment of<br>breast density.<br>DenSeeMammo produces adjunctive<br>information. It is not an interpretive or<br>diagnostic aid when the final<br>assessment of breast density category is<br>made by an MQSA-qualified interpreting<br>physician.<br>DenSeeMammo core software has been<br>built and tested on OS X based<br>computers. DenSeeMammo graphical<br>use interface software has been built<br>and tested on Windows, OS X and Linux<br>based computers. | DenSeeMammo is a software application<br>intended for use with Full Field Digital<br>Mammography systems.<br>DenSeeMammo estimates BI-RADS<br>breast density category by analyzing<br>processed digital 2D mammograms using<br>a fully automated comparison procedure.<br>DenSeeMammo provides a BI-RADS<br>breast density 5th Edition category to aid<br>radiologists in the assessment of breast<br>density.<br>DenSeeMammo produces adjunctive<br>information. It is not a diagnostic aid<br>since the final assessment of breast<br>density category is made by an MQSA<br>qualified interpreting physician.<br>DenSeeMammo core software has been<br>built and tested on OS X based<br>computers.<br>DenSeeMammo graphical use interface<br>software has been built and tested on<br>Windows, OS X and Linux based<br>computers.<br>DenSeeMammo v1.2 is compatible for<br>images obtained from GE Senographe<br>Essentials and Hologic Selenia Dimension<br>systems. |
| Intended users | Radiologists | Radiologists |
| Patient population | Symptomatic and asymptomatic women<br>undergoing mammography | Symptomatic and asymptomatic women<br>undergoing mammography |
| Image source | Digital mammography images | Digital mammography images |
| Compatibility | GE Digital Mammography systems | GE and Hologic Digital Mammography<br>systems |
| Anatomical area | Breast | Breast |
| Assessment scope | Provides results per patient based on<br>the maximum density category of the<br>two breasts | Provides results per patient based on the<br>maximum density category of the two<br>breasts |
| Assessment type | Comparison to qualified databases<br>containing images previously visually<br>assessed by MQSA-qualified radiologists<br>using ACR BI-RADS V recommendations | Comparison to qualified databases<br>containing images previously visually<br>assessed by MQSA-qualified radiologists<br>using ACR BI-RADS V recommendations |
| Characteristics | Predicate Device<br>DENSEEMAMMO v1.0 (K152009) | Submission Device<br>DENSEEMAMMO v1.2 |
| Measures provided | For each breast: BI-RADS V breast<br>density category<br>For each patient: BI-RADS V breast<br>density category | For each breast: BI-RADS V breast<br>density category<br>For each patient: BI-RADS V breast<br>density category |
| Operating environment | Software core: OS X based computers<br>Software graphical user interface:<br>Windows, OS X or Linux based<br>computers | Software core: OS X based computers<br>Software graphical user interface:<br>Windows, OS X or Linux based<br>computers |
| Deployment | Stand-alone computer | Stand-alone computer |
{6}------------------------------------------------
#### 7 Indications for Use
DenSeeMammo is a software application intended for use with Field Digital Mammography systems.
DenSeeMammo estimates BI-RADS breast density category by analyzing processed digital 2D mammograms using a fully automated comparison procedure.
DenSeeMammo provides a BI-RADS breast density 5th Edition category to aid radiologists in the assessment of breast density.
DenSeeMammo produces adjunctive information. It is not a diagnostic aid since the final assessment of breast density category is made by an MQSA qualified interpreting physician.
DenSeeMammo core software has been built and tested on OS X based computers.
DenSeeMammo graphical use interface software has been built and tested on Windows, OS X and Linux based computers.
DenSeeMammo v1.2 is compatible for images obtained from GE Senographe Essentials and Hologic Selenia Dimension systems.
#### Technological Characteristics 8
DenSeeMammo is a software that aims at assessing the breast density of a woman. The software use processed digital 2D mammograms in a fully automated comparison procedure that produces a BI-RADS breast density category. The software processes and analyses the image according to proprietary algorithms that allow comparison to qualified databases containing images previously visually assessed by radiologists. For each patient it provides measures of BI-RADS breast density category. DenSeeMammo provides results per patient based on the maximum density category of the two breasts.
The software works in a client-server mode and requires that the user computer be on the same local network as the server. Computations are made on the server part of the system that also
{7}------------------------------------------------
provide the graphical user interface to display the results. A web browser is required to display the graphical user interface: to select the patients' images and to display the assessment of the breast density according to the BI-RADS standards and the similar images.
The software was developed using the Java-1.8 language as a 3-component web application (See 11.1 Components). The software was developed following an adapted version of the model – view – controller software architectural pattern.
The device does not contact the patient, nor does it control any life-sustaining devices.
#### ਰੇ Performance Testing
The DenSeeMammo software has been verified and validated according to the company's design control process and particularly according the IEC 62304 standard. A risk analysis compliant with ISO 14971 has been provided. Software testing included both unit level and integrated system level testing.
In addition to the verification and validation testing conducted for the specific modification to the software detailed in this 510(k), complete verification and validation data testing conducted for the predicate was repeated in order to ensure integration and backwards compatibility.
## Verification bench testing included:
- DenSeeMammo v1.2 software was run over twice on data sets of images to test reproducibility.
- DenSeeMammo v1.2 software was run over on a sample of exams and left and right breast densities were compared to test reproducibility.
- DenSeeMammo v1.2 software results were compared to visual assessment from MQSA-qualified radiologists.
- DenSeeMammo v1.2 software was run over substantial data sets of two views images (CC + MLO) from GE and Hologic systems, which had been previously assessed by MQSA-qualified radiologists.
- DenSeeMammo v1.2 software was run over substantial data sets of one view images from GE (CC) and Hologic (CC or MLO) systems, which had been previously assessed by MQSA-qualified radiologists. Visual assessments were performed from two views CC + MLO images.
{8}------------------------------------------------
### Clinical validation testing included:
Beta site testing to assess the ability of physicians to successfully integrate the software into their existing systems as well as assess usability for target users.
All verification and validation testing was successful in that established acceptance criteria was met for all of the tests conducted.
#### 10 General Safety and Effectiveness Concerns
The device contains instructions for use and any necessary cautions and warnings to provide for safe and effective use of this device. Risk management is ensured via a risk analysis, which is used to identify potential hazards. These potential hazards are controlled via software development, verification and validation testing.
#### Conclusions Drawn from Studies 11
The 510(k) Premarket Notification for DenSeeMammo v1.2 contains adequate information and data to demonstrate substantial equivalence to the 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.