K193152 · Hermes Medical Solutions AB · KPS · Feb 14, 2020 · Radiology
Device Facts
Record ID
K193152
Device Name
Affinity
Applicant
Hermes Medical Solutions AB
Product Code
KPS · Radiology
Decision Date
Feb 14, 2020
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 892.1200
Device Class
Class 2
Attributes
Software as a Medical Device
Indications for Use
AFFINITY is a software application used to process, display, analyse and manage nuclear medicine and other medical imaging data transferred from other workstations, PACS or acquisition stations. The information acquired from viewing the images is used, in conjunction with other patient related data, for diagnosis and monitoring of disease.
Device Story
Affinity is a software application for 2D/3D visualization and processing of DICOM medical images (PET/CT, MR, SPECT/CT). Used in clinical settings by healthcare providers to manage imaging data; supports coregistration and fusion of studies. Features include 3D ROI analysis and automatic detection of uptake areas via threshold region tools. Quantifies parameters including SUV, SUVR, SUVbsa, SUVlbm, SUVbw, SUV Peak, SUV Mean, TLG, and MTV. Output assists clinicians in diagnosis and monitoring of disease by providing quantitative analysis of patient imaging data.
Clinical Evidence
Bench testing only. Validation performed using NEMA phantoms and studies from GE, Siemens, and Philips cameras. Compared quantitative parameters (SUV, SUVR, SUVPeak, SUVbsa, SUVlbm, SUVMean, TLG, HU, MTV) and linear measurements against Hybrid3D and Hermes Medical Imaging Suite. Results demonstrated good agreement; observed differences (e.g., up to 11% in SUVpeak vs. HybridViewer) were attributed to manual positioning and strict adherence to the Wahl et al. (2009) definition for SUVpeak calculation.
Technological Characteristics
Software application; runs on Microsoft Windows 10 (64-bit); developed using Microsoft Visual Studio on .NET framework. Supports DICOM standard. Features 2D/3D visualization, coregistration, and fusion. Quantification algorithms for SUV metrics based on threshold region tools. Standalone workstation software.
Indications for Use
Indicated for all patients undergoing molecular imaging investigations for diagnosis and monitoring of disease.
Regulatory Classification
Identification
An emission computed tomography system is a device intended to detect the location and distribution of gamma ray- and positron-emitting radionuclides in the body and produce cross-sectional images through computer reconstruction of the data. This generic type of device may include signal analysis and display equipment, patient and equipment supports, radionuclide anatomical markers, component parts, and accessories.
{0}------------------------------------------------
February 14, 2020
Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left side of the logo is the Department of Health & Human Services logo. To the right of that is a blue square with the letters FDA in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
Hermes Medical Solutions AB % Joakim Arwidson VP Quality and Regulatory Strandbergsgatan 16 Stockholm, 11251 SWEDEN
Re: K193152
Trade/Device Name: Affinity Regulation Number: 21 CFR 892.1200 Regulation Name: Emission Computed Tomography System Regulatory Class: Class II Product Code: KPS Dated: February 7, 2020 Received: February 12, 2020
Dear Joakim Arwidson:
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 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for
{1}------------------------------------------------
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 Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
## Indications for Use
510(k) Number (if known) K193152
Device Name Affinity
#### Indications for Use (Describe)
AFFINITY is a software application used to process, display, and manage nuclear medicine and other medical imaging data transferred from other workstations, PACS or acquisition stations. The information acquired from viewing the images is used, in conjunction with other patient related data, for diagnosis and monitoring of disease.
Type of Use (Select one or both, as applicable)
| <span style="font-size: 10pt;">☑ Prescription Use (Part 21 CFR 801 Subpart D)</span> |
|--------------------------------------------------------------------------------------|
| <span style="font-size: 10pt;">☐ Over-The-Counter Use (21 CFR 801 Subpart C)</span> |
#### 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}------------------------------------------------
# 5.0 510 (k) SUMMARY
#### A. Submitted by:
- Submitters name and address: Hermes Medical Solutions AB Strandbergsgatan 16 112 51 Stockholm Sweden
#### . Submitters telephone number Phone: +46 8 19 03 25 E-mail: joakim.arwidson@hermesmedical.com
#### ● Contact person
Joakim Arwidson VP Quality and Requlatory Hermes Medical Solutions AB Strandbergsgatan 16 112 51 Stockholm Sweden
- Registration number 9710645
B. Preparation date: 2019-10-28
#### C. Proprietary/Trade name, Common name, Classification name:
- Proprietary/Trade name ● Affinity
- . Common name Image processing systems
- . Classification name Emission Computer Tomography System, Class II, 21CFR892.1200
#### D. Legally marketed device (predicate device):
The following legally marketed devices have been used for comparison.
- Hybrid3D (K181468) primary ●
- Hermes Medical Imaging Suite (K171681) reference .
#### E. Description of the device that is subject of this premarket notification:
The Affinity v1.0 is a Viewer that will be the first Hermes application released on the new development platform Affinity.
The application provides 2D and 3D visualization and processing of medical images in Digital Imaging and Communications in Medicine (DICOM) format from different modalities, such
{4}------------------------------------------------
as PET/CT, MR and tomographic reconstructed SPECT from SPECT/CT. Affinity supports coregistration, with the exception of 2D images, and fusion of multiple time points with studies in the same frame of reference, different tracers, and modalities.
Affinity is developed with Microsoft Visual Studio on the .NET framework environment and designed for high throughput clinical scenarios with fast image loading and configurable workflows and layouts. In the design, emphasis has been placed on ease of use, where the user can easily access tools for 3D ROI and uptake analysis. The application supports pre-selection and automatic detection of all uptake areas within the body above a certain threshold level, by using threshold region tool. Where the user can define a threshold for any modality and unit within that modality to include all pixels of the study in a region or islands of regions.
Based on selected regions, quantification of the following parameters can be done SUV, SUVR, SUVbsa, SUVlbm, SUVbw, SUV Peak, SUV Mean, TLG and MTV.
Reference: RECIST to Percist: Evolving Considerations for PRT Response Criteria in Solid Tumors, Wahl R.L et al, Journal of Nuc Med:2009:Vol 50:122S-150S.
#### F. Intended use
AFFINITY is a software application used to process, display, analyse and manage nuclear medicine and other medical imaging data transferred from other workstations, PACS or acquisition stations. The information acquired from viewing the images is used, in conjunction with other patient related data, for diagnosis and monitoring of disease.
{5}------------------------------------------------
#### G. Technological characteristics
Comparison of the proposed device Affinity and the primary predicate device Hybrid3D (K181468) and reference device I Imaging Suite (K171681).
| Trade Name | Affinity | Hybrid3D | Hermes Medical Imaging<br>Suite | Comparison |
|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 510k # | This application | K181468 | K171681 | N/A |
| Operating System | Microsoft® Windows 10,<br>64 bit | Microsoft® Windows 7<br>and 10, 64 bit | Microsoft® Windows 7<br>and10, 64 bit | Affinity supports Windows 10 OS |
| Indications for<br>use | AFFINITY is a software<br>application used to<br>process, display, analyse<br>and manage nuclear<br>medicine and other<br>medical imaging data<br>transferred from other<br>workstations, PACS or<br>acquisition stations. The<br>information acquired from<br>viewing the images is<br>used, in conjunction with<br>other patient related data,<br>for diagnosis and<br>monitoring of disease. | Hybrid3D is a software<br>application that can be<br>used to process, display,<br>analyze and manage<br>nuclear medicine and<br>other medical imaging<br>data transferred from<br>other workstations or<br>acquisition stations. | HERMES Medical Imaging<br>suite provides software<br>applications used to<br>process, display, analyze<br>and manage nuclear<br>medicine and other<br>medical imaging data<br>transferred from other<br>workstation or acquisition<br>stations. | Equivalent Intended Use. Affinity<br>also includes the specification<br>that "The information acquired<br>from viewing the images is used,<br>in conjunction with other patient<br>related data, for diagnosis and<br>monitoring of disease." |
| Patient population | All patients undergoing<br>molecular imaging<br>investigations. | All patients undergoing<br>molecular imaging<br>investigations. | All patients undergoing<br>molecular imaging<br>investigations. | Equivalent patient population |
| Software Input /<br>Modalities<br>PET/CT | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| Trade Name | Affinity | Hybrid3D | Hermes Medical Imaging<br>Suite | Comparison |
| SPECT/CT | Yes (tomographic<br>reconstructed) | Yes (tomographic<br>reconstructed) | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| MR | Yes | Yes | No | Equivalent to Hybrid3D |
| Anatomical sites | Whole body or constrained<br>field of view (e.g.<br>abdomen, brain) | Whole body or<br>constrained field of view<br>(e.g. abdomen, brain) | Whole body or constrained<br>field of view (e.g.<br>abdomen, brain) | Equivalent anatomical sites |
| Software Output<br>Parameters | Methods used for<br>quantification | Methods used for<br>quantification | Methods used for<br>quantification | Affinity uses equivalent algorithms<br>for quantification. |
| SUV | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| SUVR | Yes | Yes (in percist criteria) | No | Equivalent to Hybrid3D |
| SUVbsa | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| SUVIbm | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| SUVbw | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| SUV Peak | Yes | Yes | Yes | See Note 1. |
| SUV Mean | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| TLG | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| MTV | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| Trade Name | Affinity | Hybrid3D | Hermes Medical Imaging<br>Suite | Comparison |
| Clinical modules | | | | |
| Viewing 2D | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| Viewing 3D | Yes | Yes | Yes | Equivalent to Hybrid3D |
| SIRT (Selective<br>Internal Radiation<br>Therapy) - post<br>treatment | No | Yes | No | No support of SIRT in Affinity |
| Lung Lobar<br>Quantification | No | Yes | No | No support of Lung Lobar<br>Quantification in Affinity |
| NM Processing | No | No | Yes | No support of NM Processing<br>modules in Affinity |
| Renogram, Gastric<br>Emptying, DMSA,<br>Gall Bladder EF,<br>Lung<br>Quantification,<br>Sacro Illiac Joint,<br>First Pass Shunt,<br>Functional Gated<br>Analysis, Brain<br>Analysis, Thyroid<br>Analysis, Colonic<br>Transit,<br>Parathyroid,<br>Dosimetry,<br>Oesophageal<br>Transit, Salivary<br>Gland, HIDA,<br>Bone3Phase<br>Analysis | No | No | Yes | No support of NM Processing<br>modules in Affinity |
| Trade Name | Affinity | Hybrid3D | Hermes Medical Imaging<br>Suite | Comparison |
| SPECT Recon-<br>struction | No | No | Yes | Affinity can load and present<br>tomographic reconstructed<br>SPECT data, but not do the<br>reconstruction itself. |
| Communication | | | | |
| DICOM | Yes | Yes | Yes | Equivalent to Hybrid3D / Hermes<br>medical Imaging Suite |
| IF (Interfile) | No | No | Yes | No support of IF (Interfile) in<br>Affinity. |
{6}------------------------------------------------
{7}------------------------------------------------
{8}------------------------------------------------
Note 1) The method for calculating SUVpeak for Affinity is exactly as described in the paper 'RECIST to Percist: Evolving Considerations for PRT Response Criteria in Solid Turnors, Wahl R.L et al, Journal of Nuc Med:2009: Vol 50:122S-150S . Consequently, an SUV peak will not be calculated for a volume which a sphere of at least 1 cubic centimeter (1 cc). The primary predicate device Hybrid3D, on the other hand, uses a spherical volume for calculating SUVpeak which is as close as possible to 1 cc, so it may present an SUVpeak value even if the volume cannot contain a 1cc sphere.
{9}------------------------------------------------
### H. Testing
The tests for verification and validation followed Hermes Medical Solutions AB design-controlled procedures. The Risk analysis was completed, and risk control implemented to mitigate identified hazards. The test results confirm that all the software specifications have met the acceptance criteria.
### I. Substantially Equivalent/Conclusions
The clinical features supported by Affinity are equivalent in comparison to the primary predicate device Hybrid3D (K181468) and the reference device Hermes Medical Imaging Suite(K171681) as presented in 'G Technological characteristics.
When validating Affinity, comparisons were made of the parameters SUV, SUVR, SUVPeak, SUVbsa, SUVIbm, SUVMean, TLG, HU, MTV and linear measurements with the primary predicate device Hybrid3D (K181468) and the reference device Hermes Medical Imaging Suite (K171681, Hybrid Viewer). Comparison of the parameters was done with different NEMA phantom based on studies from cameras by GE, SIEMENS and Philips.
| Linear Measurements on a GE CT phantom study (mm) | | | |
|---------------------------------------------------|-----------|----------|----------|
| # | Hybrid 3D | Affinity | Diff (%) |
| 1 | 37.81 | 38.7 | -2.4 |
| 2 | 29.04 | 28.9 | 0.5 |
| 3 | 22.37 | 23.9 | -6.8 |
| 4 | 17.88 | 18.0 | -0.7 |
| 5 | 14.16 | 14.5 | -2.4 |
| Linear Measurements on a Siemens CT phantom (mm) | | | |
|--------------------------------------------------|-----------|----------|----------|
| # | Hybrid 3D | Affinity | Diff (%) |
| 1 | 26.87 | 26.7 | 0.6 |
| 2 | 27.17 | 27.3 | -0.5 |
| 3 | 17.81 | 17.5 | 1.7 |
| 4 | 76.16 | 77.1 | -1.2 |
| 5 | 188.69 | 188.2 | 0.3 |
| Hounsfield Unit Numbers on a GE CT Phantom | | | |
|--------------------------------------------|-----------|----------|----------|
| Parameter | Hybrid 3D | Affinity | Diff (%) |
| VOI1, Vol ml | 2.41 | 2.4 | 0.4 |
| VOI1, Max HU | 37 | 41 | -10.8 |
| VOI1, Mean HU | 5.52 | 6 | -8.7 |
| VOI2, Vol ml | 1.03 | 1.0 | 2.9 |
| VOI2, Max HU | 1140 | 1140 | 0 |
| VOI2, Mean HU | 222 | 239 | -7.7 |
| SUV Threshold VOIs of Phillips PET study | | | |
|------------------------------------------|-----------|----------|----------|
| Parameter | Hybrid 3D | Affinity | Diff (%) |
| Vol ml | 7.55 | 7.6 | -0.7 |
| SUV peak | 15.99 | 16.36 | -2.3 |
| SUV max | 19.3 | 19.3 | 0 |
| SUV mean | 10.5 | 10.5 | 0 |
| TLG | 79.28 | 79.3 | 0 |
{10}------------------------------------------------
| SUV Threshold VOIs of GE PET study | | | |
|------------------------------------|-----------|--------------------------|-----------------------------------------------------------------------------|
| Parameter | Hybrid 3D | Affinity | Diff (%) |
| Vol ml | 1.35 | 1.3 | 3.7 |
| SUV peak | 5.08 | NA<br>(volume too small) | Not applicable<br>See Note 1) in section 'G.<br>Technology Characteristics' |
| SUV max | 7.42 | 7.42 | 0 |
| SUV mean | 5.04 | 5.11 | -1.4 |
| TLG | 6.8 | 6.5 | 4.4 |
| SUV Threshold VOIs of Siemens PET | | | |
|-----------------------------------|-----------|----------|----------|
| Parameter | Hybrid 3D | Affinity | Diff (%) |
| Vol ml | 81.07 | 82.4 | -1.6 |
| SUV peak | 18.07 | 18.28 | -1.2 |
| SUV max | 24.73 | 24.73 | 0 |
| SUV mean | 12.45 | 12.39 | 0.5 |
| TLG | 1009.21 | 1021 | -1.2 |
| SUV values for different modes using VOI on Siemens PET study (Hybrid3D / Affinity) | | | |
|-------------------------------------------------------------------------------------|-----------|----------|----------|
| Parameter | Hybrid 3D | Affinity | Diff (%) |
| SUVBW | | | |
| Vol ml | 81.07 | 81.1 | 0 |
| SUV peak | 18.07 | 18.28 | -1.2 |
| SUV max | 24.73 | 24.45 | 1.1 |
| SUV mean | 12.45 | 12.39 | 0.5 |
| TLG | 1009.21 | 1009 | 0 |
| SUVBSA | | | |
| Vol ml | 81.07 | 81.1 | 0 |
| SUV peak | 5.16 | 5.22 | -1.2 |
| SUV max | 7.06 | 7.06 | 0 |
| SUV mean | 3.55 | 3.55 | 0 |
| SUV min | 1.71 | 1.71 | 0 |
| TLG | 288.07 | 288 | 0 |
| SUV values for different modes using VOI on Siemens PET study (Hybrid Viewer / Affinity) | | | |
|------------------------------------------------------------------------------------------|---------------|----------|----------|
| Parameter | Hybrid Viewer | Affinity | Diff (%) |
| SUVLBM (120) | | | |
| Vol ml | 81.21 | 81.1 | 0.1 |
| SUV peak | 17.67 | 15.73 | 11 |
| SUV max | 21.29 | 21.29 | 0 |
| SUV mean | 10.69 | 10.72 | -0.3 |
| TLG | 868.43 | 869 | -0.1 |
| SUVLBM (128) | | | |
| Vol ml | 81.21 | 81.1 | 0.1 |
| SUV peak | 17.34 | 15.44 | 11 |
| SUV max | 20.9 | 20.9 | 0 |
| SUV mean | 10.49 | 10.52 | -0.3 |
| TLG | 852.34 | 853 | -0.1 |
{11}------------------------------------------------
The quantitative assessment obtained from Affinity is in good agreement with the predicate devices Hybrid3D (K181468) and HybridViewer (Hermes Medical Imaging Suite, K171681). The biggest difference was in SUV peak compared to HybridViewer, where a difference of up to 11% was observed. The difference in SUV peak is due to that the region is manually positioned and a slight difference in the applications algorithm, where Affinity is strictly in accordance with the definition in the paper 'RECIST to Percist: Evolving Considerations for PRT Response Criteria in Solid Tumors, Wahl R.L et al, Journal of Nuc Med:2009:Vol 50:122S-150S'.
In summary, the Affinity v1.0 described in this submission is in our opinion substantially equivalent to the predicate devices.
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.