K211966 · Medviso AB · LLZ · May 6, 2022 · Radiology
Device Facts
Record ID
K211966
Device Name
Segment 3DPrint
Applicant
Medviso AB
Product Code
LLZ · Radiology
Decision Date
May 6, 2022
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.2050
Device Class
Class 2
Attributes
AI/ML, Software as a Medical Device, Pediatric
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Bone segmentation
AI bone segmentation algorithm
—
95th percentile surface distance < 1 mm
Training: 20 data sets
—
Validation: 21 data sets
>1 (expert readers)
Indications for Use
Segment 3DPrint is a software for review and segmentation of images from a medical scanner as well as of medical 3D models. Segment 3DPrint is intended to generate 3D models for diagnostic purposes in both paediatric and adult populations in the field of orthopaedic, maxillofacial, and cardiovascular applications. The models can be used for visualisation, measuring, and treatment planning. Output from Segment 3DPrint can be used to fabricate physical replicas, by use of additive manufacturing methods. Segment 3DPrint is intended to be used by trained professionals in conjunction with expert clinical judgement.
Device Story
Software imports medical images (e.g., CT/MRI) from scanners, network, or portable media; performs manual or semi-automatic segmentation to generate 3D models. Used by trained professionals in clinical settings for visualization, measurement, and treatment planning. Output supports fabrication of physical replicas via additive manufacturing. Device does not alter original imaging data; provides support tool for clinical decision-making. Benefits include improved diagnostic visualization and planning for complex anatomical structures.
Clinical Evidence
Bench and clinical validation studies performed. 12 models (maxillofacial, orthopaedic, cardiovascular) printed to validate accuracy, achieving <1 mm precision. AI bone segmentation algorithm validated on 21 datasets (separate from 20 training sets); results showed Dice coefficient 0.96, Jaccard 0.92, and 95th percentile surface distance <1 mm. No adverse events reported.
Technological Characteristics
Software-based image processing system. Operates on standard PC (Windows 10). Features include DICOM-compliant image import, manual/semi-automatic segmentation, 3D rendering, and linear measurement tools. Connectivity via TCP/IP. Algorithm includes AI-based bone segmentation. No hardware components; software-only.
Indications for Use
Indicated for paediatric and adult populations requiring 3D model generation for diagnostic purposes in orthopaedic, maxillofacial, and cardiovascular applications. Used by trained professionals for visualization, measurement, and treatment planning.
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). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the FDA logo is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
Medviso AB % Einar Heiberg, Ph.D. Founder, Vice President, CTO Griffelvägen 3 Lund. SE-22467 SWEDEN
May 6, 2022
Re: K211966
Trade/Device Name: Segment 3DPrint Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: LLZ Dated: March 30, 2022 Received: April 8, 2022
Dear Einar Heiberg:
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. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
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 801and Part 809); medical device reporting of medical device-related adverse events) (21 CFR
{1}------------------------------------------------
803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; 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 https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely.
For
Thalia T. Mills, Ph.D. Director DHT8B: Division of Radiological Imaging Devices and Electronic Products OHT8: Office of Radiological Health Office of Product Evaluation and Ouality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
#### DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration
## Indications for Use
510(k) Number (if known) K211966
Device Name Segment 3DPrint
### Indications for Use (Describe)
Segment 3DPrint is a software for review and segmentation of images from a medical scanner as well as of medical 3D models. Segment 3DPrint is intended to generate 3D models for diagnostic purposes in both paediativ and adult populations in the field of orthopaedic, maxillofacial, and cardiovascular applications. The models can be used for visualisation, measuring, and treatment planning. Output from Segment 3DPrint can be used to fabrical replical replical replical replical replical replical replical replical by use of additive manufacturing methods. Segment 3DPrint is intended to be used by trained professionals in conjunction with expert clinical judgement.
Type of Use (Select one or both, as applicable)
|X Prescription Use (Part 21 CFR 801 Subpart D)
--- 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 5
#### Submitter 5.1
Medviso AB Griffelvägen 3 SE-224 67 Lund, Sweden +46(0)761-836442
Date Prepared: May 4, 2022 Contact Person: Einar Heiberg, PhD, CTO, +46(0)761-836442, einar@medviso.com
#### 5.2 Device
Device Trade Name: Segment 3DPrint Device Common Name: Image processing system Classification Name: Class II - System, Image Processing Regulation Number: 892.2050(Medical image management and processing system) Product Code: LLZ
#### Predicate Device 5.3
Mimics Medical (K183105) Materialise N.V. Technologielaan 15 3001 Leuven Belgium
#### 5.4 Device Description
# Device Description
Seqment 3DPrint is a software for review and segmentation of images from a medical scanner as well as of medical 3D models. Segment 3DPrint is intended to generate 3D models for diagnostic purposes. The models can be used for visualisation, measuring, and treatment planning. Output from Segment 3DPrint can be used to fabricate physical replicas, by use of additive manufacturing methods.
Image /page/3/Picture/14 description: The image shows the word "MEDVISO" in a light blue color. The word is surrounded by a pattern of small, light blue squares that form a semi-circular shape above and below the word. The squares are arranged in a grid-like pattern and appear to be fading out towards the edges of the semi-circle.
Page 5-1 of 5
{4}------------------------------------------------
Medical images and 3D models may be imported from various sources, including images stored on portable media, network storage devices, and other vendor systems.
Segment 3DPrint meets the identification criteria LLZ 892.2050 - Picture archiving and communications system. Segment 3DPrint is a software with the capability to import and display medical images and to perform digital processing of a rendered 3D object. Segment 3DPrint is a support tool with the means of generating 3D models and should be used by medically trained professionals in conjunction with expert clinical judgement.
The user will interact with Seqment 3DPrint through a graphical user interface on a standard PC platform, using Windows operating system.
#### 5.5 Intended Use
Segment 3DPrint is a software for review and segmentation of images from a medical scanner as well as of medical 3D models. Segment 3DPrint is intended to generate 3D models for diagnostic purposes in both paediatric and adult populations in the field of orthopaedic, maxillofacial, and cardiovascular applications. The models can be used for visualisation, measuring, and treatment planning. Output from Segment 3DPrint can be used to fabricate physical replicas, by use of additive manufacturing methods. Segment 3DPrint is intended to be used by trained professionals in conjunction with expert clinical judgement.
# Comparison with Predicate Device
Both Segment 3DPrint and the predicate device Mimics Medical are support tools which provide the healthcare professional(s) with relevant clinical data to support clinical decisions by analyzing the generated 3D models.
Both Seament 3DPrint and Mimics Medical can be used for the fabrication of physical replicas of the output file using additive manufacturing methods.
The intended use for Segment 3DPrint is substantially equivalent to the intended use of the predicate device Mimics Medical.
#### Technological Characteristics 5.6
Seament 3DPrint and the predicate device are both software packages that can be used for visualization and segmentation of medical images. Both Segment 3DPrint and the predicate device provide a user interface with items for selecting images and adjusting image viewing and can be operated from a personal computer. The subject device and predicate device render segmentations of the region of interest either semiautomatically, manually, or in combination, providing digital 3D models. The technological difference between the subject device and the predicate device is that different algorithms are used for the semi-automatic segmentation approaches. There might be slight differences in features and menu, but these differences between the
Image /page/4/Picture/13 description: The image shows the word "MEDVISO" in a light blue color. The word is surrounded by a pattern of small, light blue squares that form a semi-circular shape above and below the word. The squares appear to be pixelated, giving the image a digital or technological feel. The background is white.
{5}------------------------------------------------
predicate device and the proposed device are not significant since they do not raise any new or potential safety risks to the user or patient and questions of safety or effectiveness. Based on the results of software validation and verification tests, we conclude that Segment 3DPrint is substantially equivalent to the predicate device.
| System | Segment 3DPrint | Mimics Medical |
|-----------------------------------------------------|------------------------------------------|--------------------------------------|
| Version | 3.2 | 23.0.2 |
| Manufacturer | Medviso AB | Materialise NV |
| 510(k) number | K211966 | K183105 |
| Classification | 892.2050<br>LLZ, Class II | 892.2050<br>LLZ, Class II |
| Intended use | same | same |
| Patient population | All with images from<br>medical scanner. | Unspecified |
| Graphical user interface | Yes | Yes |
| Platform | PC | PC |
| Operating system | MS Windows 10 | MS Windows 10 |
| Image display monitor | Unspecified | Resolution of 1280x1024 or<br>higher |
| Report display monitor | No | No |
| Patient demographics | Yes | Yes |
| Networking | TCP/IP | TCP/IP |
| DICOM compliant image<br>compression | Lossless | Lossless |
| Image communication | Yes | Yes |
| Image processing annotations | Yes | Yes |
| Linear measurement tools | Yes | Yes |
| Automatic and manual<br>segmentation of object | Yes | Yes |
| Automatic filling and<br>smoothing tools | Yes | Yes |
| Local and remote image<br>storage | Yes | Yes |
| Type of software – custom<br>integrated | Yes | Yes |
| Viewing | Yes | Yes |
| Safety - For use only by a<br>licensed professional | Yes | Yes |
Image /page/5/Picture/4 description: The image shows the word "MEDVISO" in a light blue color. The word is surrounded by a pattern of small, light blue squares that form a semi-circular shape above and below the word. The squares appear to be pixelated, giving the image a digital or technological feel. The overall design is simple and clean, with a focus on the text and the surrounding pattern.
{6}------------------------------------------------
#### 5.7 Performance Data
The following performance data were provided in support of the substantial equivalence determination.
The accuracy of the final 3D model generated by Segment 3DPrint is < 1 mm.
## Software Verification and Validation Testing
Software verification and validation testing were conducted and documented according to FDA's Guidance "Guidance for the Content of Premarket Submission for Software Contained in Medical Devices". It was concluded that Segment 3DPrint was considered to be of "moderate" level of concern. Extensive testing of the software package is performed by an automated test suite prior to commercial release. As a complement to this, manual testing is performed by Application specialists and the software is evaluated at one beta test site.
## Bench and Clinical Studies
The features for Segment 3DPrint have been clinically evaluated using bench and clinical studies. The studies are validation or application studies using established methods as reference standards, and were performed in Europe.
The device validation study validates digital models and 3D models from additive manufacturing (low force stereolithography), representative of the three different application areas. In total 12 models, representing the most complex structures and worst-case scenarios, were printed. The patient characteristics for the validation of the print accuracy included four females and eight males. Mean age was 26 ± 29 years, range 15 days - 79 years. Five cases were maxillofacial, three cases were orthopaedic, and four cases were cardiovascular. This yielded replicas with an accuracy of <1 mm, well suited for clinical use in all intended patient population groups.
Al bone segmentation algorithm was trained on 20 data sets, and 21 data sets were used for its validation. There was no overlap of data between the two sets, and care was taken to include a great variety of data (such as scanner model, image quality, and anatomy). The maximum 95th percentile surface distance between the ground truth segmentation and the resulting image was <1 mm.
The patient characteristics for the validation of the Al bone segmentation includes ten females, four males and seven of unknown sex. Mean age was 33 ± 26 years, range 15 days - 76 years. Table 1 below presents the agreement between reference segmentation by expert readers and the segmentation by the automatic segmentation algorithm.
Image /page/6/Picture/12 description: The image shows the word "MEDVISO" in a light blue color. The word is surrounded by a pattern of small, light blue squares that form a curved shape above and below the word. The squares are more concentrated near the word and become more sparse as they move away from it, creating a gradient effect.
Page 5-4 of 5
{7}------------------------------------------------
| Set | Dice | Jacc | Dist <br>[mm] | Dist<br>[mm] | 95th percentile<br>[mm] |
|------|------|------|----------------|--------------|-------------------------|
| Mean | 0.96 | 0.92 | 0.23 | 0.03 | - |
| SD | 0.03 | 0.05 | 0.18 | 0.26 | - |
| Max | - | - | - | - | 0.93 |
Table 1 - Dice is dice coefficient, Jacc is Jaccard score, IIDistII is mean±SD absolute distance, Dist is signed distance difference, and 95th is the 95th percentile of the absolute distance.
The results of the studies show that the values from the evaluated features in Segment 3DPrint were in good agreement with values from the reference method.
No adverse events, or complications, associated with the subject device were observed in the studies. Based on the clinical performance as documented in the performance studies, Segment 3DPrint was found to have a safety and effectiveness profile that is similar to the predicate device.
#### 5.8 Conclusion
We conclude that the subject device Segment 3DPrint is as safe and effective as the predicate device. All identified hazards for Segment 3DPrint have been mitigated to acceptable levels, and the overall residual risk evaluation concluded that the residual risk of Segment 3DPrint is acceptable. The risks associated with the use of Segment 3DPrint are acceptable when weighed against the benefits for the patient. Segment 3DPrint performs in accordance with its intended use as well as the predicate device. ldentical to the predicate device, Segment 3DPrint does not in any way alter the imaging data in the analytical process. Segment 3DPrint provides assistance to a medically trained professional and all of the information is subject to his/her oversight, control, and clinical judgement. Medviso AB considers the features of Segment 3DPrint to be substantially equivalent to the subset of features in the predicate device Mimics Medical.
MEDVISO AB Griffelvägen 3 SE-224 67 Lund, Sweden tel: +46-76-1836442 www.medviso.com
Image /page/7/Picture/8 description: The image shows the word "MEDVISO" in a light blue sans-serif font. The word is surrounded by a pattern of small, light blue squares that form a semi-circular shape above and below the word. The squares are arranged in a grid-like pattern, and they appear to be pixelated. The overall effect is a modern and technological look.
Page 5-5 of 5
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.