K132532 · Siemens AG Healthcare · LLZ · Dec 9, 2013 · Radiology
Device Facts
Record ID
K132532
Device Name
SYNGO.PLAZA VB10A
Applicant
Siemens AG Healthcare
Product Code
LLZ · Radiology
Decision Date
Dec 9, 2013
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
syngo.plaza is a Picture Archiving and Communication System intended to display, process, read, report, communicate, distribute, store, and archive digital medical images, including mammographic images. It supports the physician in diagnosis and treatment planning. For primary image diagnosis in Mammography only uncompressed or non-lossy compressed images and only preprocessed DICOM "For Presentation" images must be used. Also monitors (displays) and printers which received FDA clearance for Mammography must be used. syngo.plaza also supports DICOM Structured Reports. In a comprehensive imaging suite, syngo.plaza integrates Hospital / Radiology Information Systems (HIS / RIS) to enable customer specific workflows. syngo.plaza optionally uses a variety of advanced postprocessing applications. Note: Web-based image distribution is not intended for reporting.
Device Story
syngo.plaza VB10A is a software-only Picture Archiving and Communication System (PACS) installed on standard IT hardware. It ingests digital medical images via DICOM and integrates with HIS/RIS for clinical workflow management. The system provides tools for image display, processing, reporting, and archiving. Physicians use the workstation to view images, perform measurements (distance, angle, area, perimeter), and utilize advanced post-processing applications (3D reconstruction, multiplanar reconstruction, intensity projections). The device supports mammography diagnosis when used with specific FDA-cleared hardware and image formats. It facilitates clinical decision-making by providing diagnostic-quality visualization and structured reporting. Benefits include centralized image management, efficient workflow integration, and diagnostic support for radiologists and clinicians in hospital or clinic settings.
Clinical Evidence
Bench testing only. Software verification and validation were performed at unit, integration, and system levels according to standards including IEC 62304, ISO 14971, and DICOM/HL7 standards. No clinical data was required or provided.
Technological Characteristics
Software-only system installed on Windows-based, manufacturer-independent workstations. Connectivity via TCP/IP, DICOM, and HL7. Supports JPEG lossless/lossy, RLE, and MPEG-II compression. Features include 2D/3D image processing, multiplanar reconstruction, and intensity projections. Complies with IEC 62304 (Safety Class B), ISO 14971, and DICOM/HL7 standards.
Indications for Use
Indicated for use by physicians for the display, processing, reading, reporting, communication, distribution, storage, and archiving of digital medical images, including mammography. For primary mammography diagnosis, requires uncompressed or non-lossy compressed images, preprocessed DICOM 'For Presentation' images, and FDA-cleared monitors/printers.
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}------------------------------------------------
# K 132532 DEC - 9 2013
# 510(k) Summary
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 8807.92.
3002808157 .
#### · I. GENERAL INFORMATION
### Establishment:
Address:
Siemens AG, Medical Solutions Henkestrasse 127 D-91052 Erlangen Germany .
Registration Number: .
LLZ
Contact Person: .
#### Viktoria Benz Regulatory Affairs Manager Telephone: +49 (9131) 84-4483 Telefax: +49 (9131) 84-8691
# Device Name and Classification:
Trade Name: syngo.plaza VB10A · Classification Name: Picture Archiving and Communications System Classification Panel: Radiology 21 CFR §892.2050 CFR Section: Device Class: Class II
Product Code:
{1}------------------------------------------------
- II. SAFETY AND EFFECTIVENESS INFORMATION SUPPORTING THE SUBSTANTIAL EQUIVALENCE DETERMINATION
# Device Description and Intended Use:
syngo.plaza is a Picture Archiving and Communication System intended to display, process, read, report, communicate, distribute, store, and archive digital medical images, including mammographic images.
It supports the physician in diagnosis and treatment planning.
For primary image diagnosis in Mammography only uncompressed or non-lossy compressed images and only preprocessed DICOM "For Presentation" images must be used. Also monitors (displays) and printers which received FDA clearance for Mammography must be used.
syngo.plaza also supports DICOM Structured Reports.
In a comprehensive imaging suite, syngo.plaza integrates Hospital / Radiology Information Systems (HIS / RIS) to enable customer specific workflows. syngo.plaza optionally uses a variety of advanced postprocessing applications.
Note:
Web-based image distribution is not intended for reporting.
#### Technological Characteristics:
syngo.plaza is a "software only"-system. which will be delivered on DVD to be installed on common IT hardware, matching the syngo.plaza hardware requirements.
syngo.plaza will be installed by Siemens implementation engineers.
The integration into customer specific 17 environments is offered based on professional services. Updates / upgrades are offered based on service contracts and fulfilled by trained service technicians.
This is also applicable for the predicate device syngo.plaza VA20A (K101666).
{2}------------------------------------------------
he following matrix compares the functionality of the syngo.plaza VBI0A to the predicate device syngo.plaza VA20A
| nctionalit | vngo.plaza VB10A | syngo.plaza VA20A |
|-------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| lanufacture | emens AG Medical Solutions | Siemens AG Medical Solutions |
| ntended Use | yngo.plaza is a Picture Archiving and Communication tystem intended to display, process, read, report,<br>communicate, distribute, store, and archive digital medical images, including mammographic images. supports the physician in diagnosis and treatment planning. | ngo.plaza is a Picture Archiving and Communicatio<br>medical images, including mammographic images. supports the physician in diagnosis and treatment<br>System intended to display, process, read, report,<br>olanning. |
| | For primary image diagnosia in Mammography andy unggunan aran masar Press Premarianian Marin Marin Marin Marin Marin Marin Marin Marin Marin Marina Maceined FDA monimors (dis | or primary image diagnosis in Mammography only compressed or non-lossy compressed images and only eprocessed DICOM "For Presentation" images must<br>oe used. Also monitors (displays) and printers which<br>Reports. |
| | Integrates Hospital / Radiological Information System Integrates Hospital / Radiological Information System (HIS / RIS) to enable customer specific workflows. | a comprehensive imaging suite, syngo.plaza egrates Hospital / Radiological Information Syst<br>(HIS / RIS) to enable customer specific workflow |
| | yngo.plaza optionally uses a variety of advance ostprocessing applications. | go.plaza optionally uses a variety of advance<br>stprocessing applications |
| | ote: Web-based image distribution is not intended for | Note: Web-based image distribution is not intended |
| Functionality | syngo.plaza VB10A | syngo.plaza VA20A |
| | reporting. | reporting. |
| Image communication | Standard network protocols like TCP / IP and standard<br>communication protocol DICOM. Additional fast<br>image transfer protocol for use inside syngo.plaza<br>VB10A | Standard network protocols like TCP / IP and standard<br>communication protocol DICOM. Additional fast<br>image transfer protocol for use inside syngo.plaza<br>VA20A. |
| Image data<br>compression | JPEG lossless with compression factor 2 to 3 on storage<br>(RAID) and before archiving (e.g. on NAS)<br>- Uncompressed - lossless JPEG<br>- Lossless JPEG - lossless JPEG<br> | JPEG lossless with compression factor 2 to 3 on storage<br>(RAID) and before archiving (e.g. on NAS)<br>- Uncompressed - lossless JPEG<br>- Lossless JPEG - lossless JPEG<br>- Lossless JPEG 2000 - lossless<br>JPEG 2000<br>- Lossy JPEG - displayed as received<br>- RLE - displayed as received<br>MPEG-II support |
| Image Short<br>Term storage | Internal and External online storage on configurable<br>RAID systems. Industrial standards apply. | Internal and External online storage on configurable<br>RAID systems. Industrial standards apply. |
| Image Long<br>Term storage | External archiving on external (not inside syngo.plaza)<br>archiving to either NAS storage systems or to any<br>external DICOM Long Term Archive. Industrial<br>standards apply. | External archiving on external (not inside syngo.plaza)<br>archiving devices (e.g. NAS and DVD-RAM).<br>Industrial standards apply. |
| User administration | Centralized user administration | Centralized user administration |
| Functionality | syngo.plaza VB10A | syngo.plaza VA20A |
| OEM Interface | syngo.plaza VB10A<br>syngo.via20 | EndoMap<br>Expert-i<br>syngo.x<br>syngo MammoReport |
| User Interface | UI is one of the syngo.plaza VB10A workstation deployments. | UI is one of the syngo.plaza VA20A workstation deployments. |
| RIS communication | Via standards HL7 and DICOM. aligned to IHE Framework Rev.1. | Via standards HL7 and DICOM. aligned to IHE Framework Rev.9. |
| Hardware | Windows based, manufacturer independent Workstations | Windows based, manufacturer independent Workstations: PC based with Windows XP or Windows Vista; |
| Client Installation | New: Introduction of a client software distribution for syngo.plaza Reporting Clients | manual installation using MSI packages |
| Application package / workplace function- | syngo 3D Basic<br>syngo 3D Advanced<br>3D VesselMetrix | syngo 3D Basic<br>syngo 3D Advanced<br>3D VesselMetrix |
| Functionality | syngo.plaza VB10A | syngo.plaza VA20A |
| nality | Filming | Filming |
| | Teleradiology | Teleradiology |
| | Patient Media Creation | Scanner |
| | Workflow Support for Mammography | Patient Media Creation |
| | Spine Labeling / Cross Reference | Workflow Support for Mammography |
| | Cardio Thoracic Ratio (CTR10) | Spine Labeling / Triangulations |
| | DSA Viewer | Cardio Thoracic Ratio (CTR10) |
| | New: Token view | DSA Viewer |
| | New: Smart Read feature | |
| | New: Angle on Stack" functionality | |
| | New: Patient ID | |
| Image Processing features | Filming | Filming |
| | 3D Reconstruction | 3D Reconstruction |
| | 3D Vessel Metrix | 3D Vessel Metrix |
| | Rendering | Rendering |
| | Workflow Support for mammography | Workflow Support for mammography |
| | Spine Labeling / Cross Reference | Spine Labeling / Triangulations |
| | Cardio Thoracic Ratio (CTR10) | Cardio Thoracic Ratio (CTR10) |
| | DSA Viewer | DSA Viewer |
| | | |
| Functionality | syngo.plaza VBI0A | syngo.plaza VA20A |
| Image Processing Algorithms | Quantitative Algorithm<br>In syngo.plaza 2D Image processing Library<br>Region Calculation (Mammography) (calculated: Minimum bounding Rect co-ordinates of the tissue area in an image based on pixel intensity)<br>3D Projection (Cross-Reference) (calculated: Co-ordinates of the projected points from one plane on other orthogonal planes)<br>Statistical Algorithms for calculation of Average, Std Deviation, Minimum or Maximum pixel values (calculated: Statistical values based on image pixel intensity in a given ROI)<br>Affine Transformation (Zoom/Pan/Rotate/Flip) (calculated: New position of the given point (x,y) of image in displayed window after performing any of the affine operation) | Quantitative Algorithm<br>In syngo.plaza 2D Image processing Library<br>Region Calculation (Mammography) (calculated: Minimum bounding Rect co-ordinates of the tissue area in an image based on pixel intensity)<br>3D Projection (Cross-Reference) (calculated: Co-ordinates of the projected points from one plane on other orthogonal planes)<br>Statistical Algorithms for calculation of Average, Std Deviation, Minimum or Maximum pixel values (calculated: Statistical values based on image pixel intensity in a given ROI)<br>Affine Transformation (Zoom/Pan/Rotate/Flip) (calculated: New position of the given point (x,y) of image in displayed window after performing any of the affine operation) |
July 30. 2013
Page K 4
510(k) for syngo®0.plaza
{3}------------------------------------------------
July 30. 2013
510(k) for syngo®.plaza
Page K 5
{4}------------------------------------------------
. "
10 Via internal reorganization syngo.x was renamed to syngo,via.
July 30, 2013
510(k) for syngo®.plaza
Page K 6
{5}------------------------------------------------
ﻨﻨﻪ،
Page K 7
I
{6}------------------------------------------------
ﯩﺪ :
Page K 8
510(k) for syngo®.plaza
July 30. 2013
for syngas plants
{7}------------------------------------------------
| syngo.plaza VB10A | syngo.plaza VA20A |
|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| image in displayed window after performing any of the<br>affine operation) | image in displayed window after performing any of the<br>affine operation) |
| Distance: Line Measurement between 2 points,<br>calculation based on image pixel spacing value and the<br>length of the line between start and end points | Distance: Line Measurement between 2 points,<br>calculation based on image pixel spacing value and the<br>length of the line between start and end points |
| Angle: The angle between the two lines measured in<br>anti-clockwise direction | Angle: The angle between the two lines measured in<br>anti-clockwise direction |
| Area: The calculation of area of Circle, Ellipse,<br>Rectangle | Area: The calculation of area of Circle, Ellipse,<br>Rectangle |
| Perimeter: The calculation of perimeter for Circle,<br>Rectangle: Average, Minimum and Maximum pixel<br>value and Standard Deviation calculation for the pixels<br>inside Circle, Ellipse and Distance line. | Perimeter: The calculation of perimeter for Circle,<br>Rectangle: Average, Minimum and Maximum pixel<br>value and Standard Deviation calculation for the pixels<br>inside Circle, Ellipse and Distance line. |
| Volume: no volume measurements in syngo.plaza | Volume: no volume measurements in syngo.plaza |
| Rendering Algorithm<br>In 3D application by Voxar | Rendering Algorithm<br>In 3D application by Voxar |
| Multiplanar Reconstruction (calculated: Images in one<br>plane are used to reconstruct images of other orthogonal<br>planes) | Multiplanar Reconstruction (calculated: Images in one<br>plane are used to reconstruct images of other orthogonal<br>planes) |
| Maximum and Minimum Intensity Projection<br>(calculated: Visualization of Maximum and minimum<br>voxel values that are visible projected to parallel plane) | Maximum and Minimum Intensity Projection<br>(calculated: Visualization of Maximum and minimum<br>voxel values that are visible projected to parallel plane) |
| Volume Rendering Technique (calculated: Visualization of<br>3D volume) | Volume Rendering Technique (calculated: Visualization of<br>3D volume) |
| Shaded Surface Display (calculated: Visualization of<br>Surface rendered 3D volume) | Shaded Surface Display (calculated: Visualization of<br>Surface rendered 3D volume) |
| In syngo.plaza 2D Image processing Library | In syngo.plaza 2D Image processing Library |
ﻨﺪ ﻟﻠ
Page K 9
510(k) for syngo®.plaza
July 30, 2013
for single p.i.d.
{8}------------------------------------------------
| Functionality | syngo.plaza VB10A | syngo.plaza VA20A |
|------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| | Nearest-Neighbour interpolation (Smoothing)<br>(calculated: Estimated Pixel intensity based on nearest<br>neighbour algorithm)<br>Bilinear interpolation (Smoothing) (calculated:<br>Estimated Pixel intensity based on bilinear algorithm)<br>Bicubic interpolation (Smoothing) (calculated:<br>Estimated Pixel intensity based on bicubic algorithm)<br>8-bit Greyscale image display using Windows GDI<br>(calculated: Rendered pixel intensity on the screen co-<br>ordinates)<br>24- bit colour Image display using Windows GDI<br>(calculated: Rendered pixel intensity on the screen co-<br>ordinates)<br>Windowing and LUT Mapping (Windowing)<br>(calculated: Pixel intensity transformation based on VOI<br>LUT and Presentation LUT information and convert to<br>raster format which can be rendered)<br>Image subtraction (DSA) (calculated: Pixel intensity<br>after subtracting the mask frame pixel intensity) | Nearest-Neighbour interpolation (Smoothing)<br>(calculated: Estimated Pixel intensity based on nearest<br>neighbour algorithm)<br>Bilinear interpolation (Smoothing) (calculated:<br>Estimated Pixel intensity based on bilinear algorithm)<br>Bicubic interpolation (Smoothing) (calculated:<br>Estimated Pixel intensity based on bicubic algorithm)<br>8-bit Greyscale image display using Windows GDI<br>(calculated: Rendered pixel intensity on the screen co-<br>ordinates)<br>24- bit colour Image display using Windows GDI<br>(calculated: Rendered pixel intensity on the screen co-<br>ordinates)<br>Windowing and LUT Mapping (Windowing)<br>(calculated: Pixel intensity transformation based on VOI<br>LUT and Presentation LUT information and convert to<br>raster format which can be rendered)<br>Image subtraction (DSA) (calculated: Pixel intensity<br>after subtracting the mask frame pixel intensity) |
| Introduction<br>Warnings<br>and Cautions | WARNINGS (Operator Manual)<br>No warnings are applicable for the medical device<br>syngo.plaza. The device is classified as Safety Class B<br>according to IEC 62304. Therefore cautions are<br>sufficient. The generic chapter in the introduction was…
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.