K133937 · Morpheus Imaging, Inc. · LLZ · Mar 3, 2014 · Radiology
Device Facts
Record ID
K133937
Device Name
HEARTSCAN SOFTWARE
Applicant
Morpheus Imaging, Inc.
Product Code
LLZ · Radiology
Decision Date
Mar 3, 2014
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.2050
Device Class
Class 2
Attributes
Software as a Medical Device, 3rd-Party Reviewed
Indications for Use
HeartScan consists of software that analyzes DICOM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. HeartScan specifically analyzes the blood flow to the heart and its major vessels using multi-slice, multi-phase and velocity encoded MR images. It provides clinically relevant and reproducible, quantitative data and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. The data produced by HeartScan is intended to be used to support qualified cardiologist, radiologist or other licensed professional healthcare practitioners for clinical decision making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient.
Device Story
HeartScan is a web-accessible software application for analyzing cardiac MRI data. It imports pre-existing DICOM-compliant cardiovascular images (multi-slice, multi-phase, velocity-encoded) from MR scanners. The software performs image corrections, including eddy current correction, and utilizes automated vessel segmentation and analysis algorithms to quantify blood flow parameters, such as net blood flow rate and volume. Users interact with the software to browse, load, and manipulate images (pan, zoom, window/level adjustment) and perform manual or automated ROI contour detection. The system provides multi-planar reconstruction (MPR) with color flow fusion and generates quantitative reports. Used in clinical settings by cardiologists or radiologists, the software serves as a decision-support tool to automate time-consuming manual tracing tasks, providing reproducible data to assist in clinical decision-making. It does not interface directly with MR hardware.
Clinical Evidence
Bench testing only. Verification and validation testing confirmed the device meets design requirements and specifications. Reproducibility was established by analyzing the same ROI within datasets multiple times. Validation against the predicate device involved analyzing identical datasets and ROIs to ensure HeartScan outputs were within a clinically acceptable range. Compliance with standards including DICOM (PS 3.1-3.20), IEC 62304 (Software Life Cycle), ISO 14971 (Risk Management), and ISO 62366 (Usability) was demonstrated.
Technological Characteristics
Web-accessible software application; DICOM 3.0 compliant; supports 1.5T and 3.0T MR image inputs. Features include multi-planar reconstruction (MPR), color flow fusion, automated vessel segmentation, and eddy current correction. Software life cycle follows IEC 62304; risk management per ISO 14971; usability per ISO 62366. Standalone analysis tool; does not interface with MR hardware.
Indications for Use
Indicated for use by cardiologists, radiologists, or licensed healthcare practitioners to analyze DICOM-compliant cardiovascular MR images (multi-slice, multi-phase, velocity-encoded) from 1.5T or 3.0T scanners to quantify blood flow to the heart and major vessels. Not for medical advice or treatment recommendations.
Regulatory Classification
Identification
A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.
Special Controls
*Classification.* Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
Predicate Devices
MedVoxel Systems Inc. MedVoxel HeartPro Software System (K103565)
Submission Summary (Full Text)
{0}------------------------------------------------
## leus
APR 0 3 2014
K133937
Page 1 of 4
## 510(k) Summary Prepared November 6, 2013 (Revised: March 14, 2014)
| Sponsor: | Morpheus Imaging, Inc |
|-----------------------------------------------------------------------------------|-----------------------------------------------------------------------------|
| Contact Person: | John Axerio-Cilies Ph.D. |
| Address: | 1700 4th St. MC 2522 Byers Hall 214<br>San Francisco, California 94158-2330 |
| Telephone: | 650 391 7111 |
| Fax: | 650 319 7231 |
| Submission Date: | November 6, 2013 |
| Device Name: | HeartScan Software |
| Common Name: | Radiology Imaging Software |
| Classification:<br>Regulatory Class:<br>Review Category:<br>Classification Panel: | II<br>21 CFR 892.2050 (LLZ)<br>Radiology |
## A. Legally Marketed Predicate Devices
The Morpheus HeartScan software device is substantially equivalent to the MedVoxel Systems Inc. Med Voxel HeartPro Software System (K103565).
## B. Device Description:
Morpheus HeartScan is a web-accessible image analysis software application. The application is intended to visualize and quantify cardiac-specific MRI data in DICOM format. HeartScan has features for loading, saving, generating screen displays, and aggregating flow statistics.
Pre-existing MR images are uploaded via the web to the HeartScan software application where image corrections (specific to aliasing errors) are applied to the set of images prescribed by the user. Automatic or manual vessel segmentation is performed and advanced analysis algorithms are applied to quantify blood flow. The images and blood flow can be simultaneously visualized at any plane using multi-planar reconstruction (MPR) with color flow fusion. Reproducible test results are produced and stored in the image study.
{1}------------------------------------------------
Image /page/1/Picture/0 description: The image shows the word "orpheus" with a heart symbol replacing the "O". The text is written in a simple, handwritten style, giving it a personal and informal feel. The heart symbol adds a touch of affection or love to the name, creating a unique visual representation.
HeartScan does not interface directly with any MR or data collection equipment, instead HeartScan imports data files previously generated by such equipment. The software application applied advanced automated methods to avoid tedious, time-consuming manual methods. The software does not perform any functions which cannot be accomplished by a trained user utilizing manual tracing methods; the purpose of the software is to save time and automate potential error-prone manual tasks.
## C. Intended Use
HeartScan consists of software that analyzes DICOM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. HeartScan specifically analyzes the blood flow to the heart and its major vessels using multi-slice, multi-phase and velocity encoded MR images. It provides clinically relevant and reproducible, quantitative data and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. The data produced by HeartScan is intended to be used to support qualified cardiologist, radiologist or other licensed professional healthcare practitioners for clinical decision making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient.
### D. Substantial Equivalence
The submission device is substantially equivalent to MedVoxel Systems Inc. MedVoxel HeartPro Software Application (K103565) as described in the table below:
| Feature/Specification | Predicate Device | Subject Device |
|-----------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| | MedVoxel HeartPro Software | Morpheus HeartScan Software |
| | Application K103565 | |
| Indication for use | HeartPro consists of software that analyzes DICOM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. HeartPro specifically analyzes the blood flow to the heart and its major vessels using multi-slice, multi-phase and velocity encoded MR images. It provides clinically relevant and reproducible. quantitative data and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. The data produced by HeartPro is intended to be used to support qualified cardiologist, radiologist or other licensed professional health care practitioners for clinical decision making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient. | HeartScan consists of software that analyzes DICOM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. HeartScan specifically analyzes the blood flow to the heart and its major vessels using multi-slice, multi-phase and velocity encoded MR images. It provides clinically relevant and reproducible. quantitative data and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. The data produced by HeartScan is intended to be used to support qualified cardiologist, radiologist or other licensed professional health care practitioners for clinical decision making. It is a support tool that provides relevant clinical data as a resource to the clinician and is not intended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient. |
| Intended Users | qualified cardiologist, radiologist or other licensed professional health care practitioners | qualified cardiologist, radiologist or other licensed professional health care practitioners |
| Class | II | II |
## Table 1 Comparison Table
{2}------------------------------------------------
| C |
|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| വനന്തവുമാനായിരുന്നു. അവലംബം പ്രശസ്തമായി പ്രവർത്തിച്ചു. അവലംബം പ്രശസ്തമായി പ്രവർത്തിച്ചു. അവലംബം പ്രശസ്തമായി പ്രവർത്തിച്ചു. അവലംബം പ്രശസ്തമായി പ്രവർത്തിച്ചു. അവലംബം പ്ര |
| |
| ا ان ان ان الحدث ت |
:
・
:
.
| Feature/Specification | Predicate Device<br>MedVoxel HeartPro Software<br>Application K103565 | Subject Device<br>Morpheus HeartScan Software |
|---------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Regulation | 21CFR 892.2050 | 21CFR 892.2050 |
| Code | LLZ | LLZ |
| Data Acquisition | | |
| Workstation | Yes | Yes |
| operating system | | |
| Images from all MRI<br>scanners supported | Yes both 1.5T and 3.0 T | Yes both 1.5T and 3.0 T |
| Image input | Supports DICIOM 3.0 | Supports DICOM 3.0 |
| Data acquisition<br>protocol for blood<br>flow analysis | Cardiovascular images: multi-phase.<br>multi-slice and velocity encoded<br>images acquired from MRI scanners | Cardiovascular images: multi-phase.<br>multi-slice and velocity encoded<br>images acquired from MRI scanners |
| Workflow | | |
| User Interactions | User can browse, select and load<br>CMRI scan files: save and load<br>analyses; export to files; generate<br>reports with quantitative data; display<br>DICOM information | User can browse, select and load CMRI<br>scan files; save and load analyses;<br>export to files; generate reports with<br>quantitative data; display DICOM<br>information |
| Image manipulation | Pan/zoom; magnify; maximize and<br>minimize; adjust window level,<br>contrast, brightness; single image<br>ROI placement; automated 2D ROI<br>copy/edit functions; 2D velocity<br>color map. | Pan/zoom; magnify; maximize and<br>minimize; scroll through slice stack;<br>adjust window level, contrast,<br>brightness; single image ROI<br>placement; automated 2D ROI<br>copy/edit functions; 2D velocity color<br>map. |
| ROI vessel contour<br>detection and editing | Automatic contour detection with<br>user input; can be changed manually | Automatic contour detection with user<br>input; can be changed manually |
| Data Analysis | | |
| 2D measurements | ROI tools and statistics | ROI tools and statistics |
| Quantitative<br>assessment of cardiac<br>function | Measurement algorithm generates<br>clinical data, including parameters<br>such as net blood flow rate, and net<br>blood flow volume. | Measurement algorithm generates<br>clinical data, including parameters such<br>as net blood flow rate, and net blood<br>flow volume. |
| Phase Aliasing Error<br>Correction | Phase alias error correction provided<br>via user interface | No |
| Eddy Current<br>Correction (ECC) | Yes | Yes |
| Data Output: | | |
| Dynamic display of<br>ventricular<br>contractions | Yes | Yes |
| Comparative review | 2D | 2D |
| Measurement<br>Information | Blood flow chart displayed; Net<br>blood flow rate; Net blood flow<br>volume | Blood flow chart displayed; Net blood<br>flow rate; Net blood flow volume |
.
.
.
.
.
{3}------------------------------------------------
# orpheus
K133937
Page 4 of 4
## E. Performance Data
Nonclinical verification and validation test results established that the device meets its design requirements and intended use, that it is as safe, as effective, and performs as well as the predicate device, and that no new issues of safety and effectiveness were raised. The HeartScan software was designed, verified, and validated according to the company's Design Control process and has been subjected to extensive safety and performance testing as shown in the test results provided in this submission. Verification and validation testing data demonstrate that the device meets all of its specifications including compliance with the following standards:
- Digital Imaging and Communications in Medicine (DICOM); PS 3.1 3.20 . (2011)
- Medical device software Software Life Cycle Process, IEC 62304 .
- Medical devices Application of risk management to medical devices, 14971 ● Second edition 2007-03-01
- Medical Devices Application of Usability Engineering to Medical Devices, ISO 62366
Nonclinical verification and validation test results establish that the device generates reproducible data. Specific test cases were created during verification that included multiple analysis of the same ROI within the same dataset to confirm that the device generated the same output within an acceptable criterion. Additionally, validation between HeartScan and the predicate device included analyzing the same datasets and ROI to confirm that HeartScan outputs were within a clinically acceptable range compared to that of the predicate. Results conclude that HeartScan is capable of generating clinically acceptable reproducible data in comparison with a similar currently marketed device.
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the text "DEPARTMENT OF HEALTH & HUMAN SERVICES". The text is in all caps and in a bold, sans-serif font. The words are arranged on a single line and are centered horizontally.
#### Public Health Service
Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002
April 3, 2014
Morpheus Imaging, Inc. % John Axerio-Cilies, Ph.D. CEO 1700 4th Street MC 2522 Byers Hall 214 SAN FRANCISCO CA 95158-2330
Re: K133937
Trade/Device Name: HeartScan Software Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: II Product Code: LLZ Dated: March 14, 2014 Received: March 25, 2014
Dear Dr. Axerio-Cilies:
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 or any i 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 803); good manufacturing practice requirements as set
forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
{5}------------------------------------------------
Page 2-Dr. Axerio-Cilies
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Small Manufacturers, International and Consumer Assistance at its tollfree number (800) 638 2041 or (301) 796-7100 or at its Internet address
http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to
http://www.fdagov/McdicalDevices/Salietv/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.
You may obtain other general information on your responsibilities under the Act from the Division of Small Manufacturers, International and Consumer Assistance at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.
Sincerely yours,
Smh.7)
for
Janine M. Morris Director. Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health
Enclosure
{6}------------------------------------------------
#### DEPARTMENT OF HEALTH AND HUMAN SERVICES . Food and Drug Administration
## Indications for Use
Form Approved: OMB No. 0910-0120 Expiration Date: January 31, 2017 See PRA Statement on last page.
#### 510(k) Number (if known) K133937
Device Name Morpheus HeartScan
#### Indications for Use (Describe)
HeartScan consists of software that analyzes DICOM-compliant cardiovascular images acquired from magnetic resonance (MR) scanners. HeartScan specifically analyzes the blood flow to the heart and its multi-slice, multi-phase and velocity encoded MR images. It provides clinically relevant and reproducible, quantitative data and has been tested and validated on MR images acquired from both 1.5T and 3.0 T MR Scanners. The data produced by HeartScan is intended to support qualified cardiologist, radiologist or other licensed professional healthcare practitioners for clinical decision making. It is a support tool that provides relevant clinical data as a resource to the clintended to be a source of medical advice or to determine or recommend a course of action or treatment for a patient.
Type of Use (Select one or both, as applicable)
> Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
## PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON A SEPARATE PAGE IF NEEDED.
FOR FDA USE ONLY
Concurrence of Center for Devices and Radiological Health (CDRH) (Signature)
FORM FDA 3881 (1/14)
September (301) 443-6740 EF
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.