AI/ML, Software as a Medical Device, Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
K230197 · Feb 22, 2023
BoneMRI v1.6
Mriguidance B.V.
Retrospective clinical imaging data (MRI and CT scans) from previously conducted clinical investigations
Retrospective clinical data from 204 patients (101 pelvic, 103 lumbar) were used to validate the quantitative accuracy of the BoneMRI software by comparing its output against coregistered CT scans.
Quantitative voxel-by-voxel validation; Retrospective validation study
Patients with conditions including sacroiliitis, hip dysplasia, avascular necrosis, degenerative spine diseases, spondylolisthesis, radiculopathy, spondylosis, and spinal fractures.; Sample Size: 204 (101 pelvic region, 103 lumbar spine region); Number of Sites: Multiple (cross-site validation)
Coregistered CT scans
3D bone morphology (cortical delineation error), tissue radiodensity (HU deviation), and radiodensity contrast (HU correlation coefficient).
AI Performance
Output
Algorithm
Acceptance
Observed
Dev DS
Dev Readers
Test DS
Test Readers
Bone morphology, radiodensity, and radiodensity contrast
CNN with cascaded filter banks
p < 0.05
Mean absolute cortical delineation error < 1.0 mm; mean deviation < 25 HU (tissue) and < 55 HU (bone); mean HU correlation coefficient > 0.75 (bone)
—
—
Validation study: 101 patients (pelvic region) and 103 patients (lumbar spine region) from USA, Europe, and Asia.
—
Indications for Use
BoneMRI is an image processing software that can be used for image enhancement in MRI images. It can be used to visualize the bone structures in MRI images with enhanced contrast with surrounding soft tissue. It is to be used in the pelvic region, which includes the bony anatomy of the sacrum, hip bones and femoral heads; and the lumbar spine region, which includes the bony anatomy of the vertebrae from L3 to S1. BoneMRI is not to be used for diagnosis or monitoring of (primary or metastatic) tumors. Warning: BoneMRI images are not intended to replace CT images.
Device Story
BoneMRI is a standalone image processing software that transforms 3D gradient echo MRI scans into 3D tomographic radiodensity contrast images (BoneMRI images). The device uses a convolutional neural network (CNN) to assign Hounsfield Unit (HU) values to voxels based on intensity and contextual information. It operates on hospital/clinic networks, receiving DICOM inputs from PACS and returning enhanced DICOM images for viewing on standard PACS workstations. Used by radiologists or orthopedic surgeons in clinical settings to visualize bone morphology and contrast. The device aids clinical decision-making by providing enhanced bone visualization, though it is not a replacement for CT. It benefits patients by potentially reducing the need for additional CT scans for bone assessment.
Clinical Evidence
Retrospective clinical validation using 101 pelvic and 103 lumbar spine patient datasets. Endpoints compared BoneMRI output to coregistered CT scans (ground truth). Results: mean absolute cortical delineation error < 1.0 mm; mean radiodensity deviation < 25 HU (overall) and < 55 HU (bone); mean HU correlation coefficient > 0.75 for bone. All results met pre-specified acceptance criteria (p<0.05).
Technological Characteristics
Software-based image processing; runs on Linux OS. Uses convolutional neural network (CNN) for image enhancement. Inputs/outputs are DICOM format. Requires specific GPU hardware for on-premise deployment. Operates as a server application within hospital networks.
Indications for Use
Indicated for adult patients requiring visualization of bone structures in the pelvic region (sacrum, hip bones, femoral heads) and lumbar spine (L3-S1) using MRI. Contraindicated for diagnosis or monitoring of primary or metastatic tumors.
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 shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" in blue, and the word "ADMINISTRATION" in a smaller font size below.
February 22, 2023
MRIguidance B.V. % Sujith Shetty Executive Vice President MAXIS Medical 3031 Tisch Way, Suite 1010 San Jose, California 95128
Re: K230197
Trade/Device Name: BoneMRI v1.6 Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: QIH Dated: January 25, 2023 Received: January 25, 2023
Dear Sujith Shetty:
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.
{1}------------------------------------------------
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 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 medical devices and radiation-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.
Daniel M. Krainak, Ph.D. Assistant Director Magnetic Resonance and Nuclear Medicine Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
## Indications for Use
510(k) Number (if known)
K230197
Device Name BoneMRI v1.6
Indications for Use (Describe)
BoneMRI is an image processing software that can be used for image enhancement in MRI images. It can be used to visualize the bone structures in MRI images with enhanced contrast with surrounding soft tissue. It is to be used in the pelvic region, which includes the bony anatomy of the sacrum, hip bones and femoral heads; and the lumbar spine region, which includes the bony anatomy of the vertebrae from L3 to S1. BoneMRI is not to be used for diagnosis or monitoring of (primary or metastatic) tumors.
Warning: BoneMRI images are not intended to replace CT images.
Type of Use (Select one or both, as applicable)
| Prescription Use (Part 21 CFR 801 Subpart D) | <span> ☑ </span> |
|----------------------------------------------|--------------------------|
| Over-The-Counter Use (21 CFR 801 Subpart C) | <span> ☐ </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}------------------------------------------------
Image /page/3/Picture/1 description: The image shows the logo for MRI Guidance. The logo consists of a circle with an arrow pointing to the upper right, followed by the text "MRI guidance". The text is in a sans-serif font, with "MRI" in a larger, bolder font than "guidance". The logo is in shades of blue.
## 5.1 510(k) Summary
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CRF 807.92.
#### 510(k) number: K230197 5.2
## 5.3 Applicant Information
MRIguidance B.V. Maliesingel 23 3581 BG, Utrecht The Netherlands info@mriguidance.com www.mriquidance.com +31 681741711
#### 5.4 Contact Person
Marijn van Stralen Chief Technology Officer MRIguidance B.V. Email: marijn@mriguidance.com Tel.: +31 610 505 649 Date Prepared: January 27, 2023
#### Official Correspondent 5.5
Dr. Sujith Shetty Executive Vice President MAXIS LLC Email: sjshetty@maxismedical.com
#### 5.6 Device Information
| Trade Name: | BoneMRI v1.6 |
|----------------------|------------------------------------------------|
| Common Name: | MRI image enhancement software |
| Classification Name: | Medical image management and processing system |
| Regulation Number: | 21 CRF 892.2050 |
| Regulatory Class: | Class II |
| Product Code: | QIH |
{4}------------------------------------------------
Image /page/4/Picture/1 description: The image shows the logo for MRI guidance. The logo consists of a circle with an arrow pointing to the upper left, followed by the text "MRI" in a bold, sans-serif font, and the word "guidance" in a lighter, sans-serif font. The logo is in a teal color and is set against a dark blue background.
#### 5.7 -Predicate Device
| Name | Manufacturer | 510(k)# |
|--------------|------------------|---------|
| BoneMRI v1.4 | MRIquidance B.V. | K221762 |
This predicate has not been subject to a design-related recall. No reference devices were used in this submission.
#### 5.8 Device Description
The BoneMRI application is a standalone image processing software application that analyses 3D gradient echo MRI scans acquired with a dedicated MRI scan protocol. From the analysis, 3D tomographic radiodensity contrast images, called BoneMRI images, are constructed.
The BoneMRI images can be used to visualize the bone structures in MR images with enhanced contrast with respect to the surrounding soft tissue. The application is designed to be used by imaging experts, such as radiologists or orthopedic surgeons, typically in a physician's office.
The BoneMRI application is a server application running on the clinic or hospital networks. It is available as fully on-premise software with specific GPU hardware requirements, or partly running as a managed service, for which the environment in which the managed modules run is controlled by MRIquidance, but the managed service will not receive protected health information (PHI). Within the hospital network, the application communicates with a DICOM compatible imaging archive (e.g., a PACS) to receive input MRI and to return BoneMRI images. Reading of the resulting BoneMRI images is performed using reqular DICOM compatible medical imaging viewing software.
The application uses an algorithm to detect bone images from MRIs obtained using a specific acquisition sequence. The algorithm training sets included information from multiple clinical sites, multiple anatomies, and multiple scanners to ensure that the trained algorithm was robust with respect to the approved indications for use. None of the data used in the training dataset was used subsequently in the validation dataset.
#### Indications for Use 5.9
BoneMRI is an image processing software that can be used for image enhancement in MRI images. It can be used to visualize the bone structures in MRI images with
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the logo for MRI Guidance. The logo consists of a circle with an arrow pointing up and to the right, followed by the text "MRI" in a larger font and "guidance" in a smaller font. The logo is in a teal color and is set against a dark blue background.
enhanced contrast with respect to the surrounding soft tissue. It is to be used in the pelvic region, which includes the bony anatomy of the sacrum, hip bones, and femoral heads; and the lumbar spine region, which includes the bony anatomy of the vertebrae from L3 to S1. BoneMRI is not to be used for diagnosis or monitoring of (primary or metastatic) tumors.
Warning: BoneMRI images are not intended to replace CT images.
## 5.10 Comparison of Technological Characteristics with the Predicate Device:
A comparison of the intended use, indication for use, and technological characteristics of the BoneMRI application to the predicate device, BoneMRI v1.4, is presented below. We have included the attributes suggested in FDA's website guidance for this comparison.
### A. Intended Use
| | Predicate Device<br>BoneMRI v1.4 | Subject Device<br>BoneMRI | Comment |
|---------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------|
| Intended Use | BoneMRI is an image<br>processing software that can<br>be used for image<br>enhancement in MRI<br>images. It can be used to<br>visualize the bone structures<br>in MRI images with<br>enhanced contrast with<br>respect to the surrounding<br>soft tissue. It is to be used in<br>the pelvic region, which<br>includes the bony anatomy<br>of the sacrum, hip bones<br>and femoral heads; and the<br>lumbar spine region, which<br>includes the bony anatomy<br>of the vertebrae from L3 to<br>S1. BoneMRI is not to be<br>used for diagnosis or<br>monitoring of (primary or<br>metastatic) tumors.<br>Warning: BoneMRI images<br>are not intended to replace<br>CT images. | BoneMRI is an image<br>processing software that can<br>be used for image<br>enhancement in MRI<br>images. It can be used to<br>visualize the bone structures<br>in MRI images with<br>enhanced contrast with<br>respect to the surrounding<br>soft tissue. It is to be used in<br>the pelvic region, which<br>includes the bony anatomy<br>of the sacrum, hip bones<br>and femoral heads; and the<br>lumbar spine region, which<br>includes the bony anatomy<br>of the vertebrae from L3 to<br>S1. BoneMRI is not to be<br>used for diagnosis or<br>monitoring of (primary or<br>metastatic) tumors.<br>Warning: BoneMRI images<br>are not intended to replace<br>CT images. | The same |
| 21CFR Section | 892.2050 | 892.2050 | The same |
| Product Code | QIH | QIH | The same |
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image shows the logo for MRI guidance. The logo consists of a circle with an arrow pointing to the right and up, followed by the text "MRI guidance". The text is in a sans-serif font and is a lighter shade of blue than the background.
# Special 510(k) Notification
| | Predicate Device<br>BoneMRI v1.4 | Subject Device<br>BoneMRI | Comment |
|-------------------|----------------------------------|---------------------------|----------|
| Target Population | Adults | Adults | The same |
# B. Technological Characteristics
| | Predicate Device<br>BoneMRI v1.4 | Subject Device<br>BoneMRI | Comment |
|--------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------|
| Device Nature | Software package | Software package | The same |
| Operating System | Linux | Linux | The same |
| Data input | MRI images in DICOM<br>format | MRI images in DICOM<br>format | The same |
| Data output | MRI images in DICOM<br>format | MRI images in DICOM<br>format | The same |
| Processing<br>Algorithms | MRIguidance software<br>implements an image<br>enhancement algorithm<br>using convolutional neural<br>network. Original images are<br>enhanced by running them<br>through a cascade of filter<br>banks, where thresholding<br>and scaling operations are<br>applied. Separate neural<br>network-based filters are<br>obtained to assign a<br>Hounsfield Unit (HU) value<br>to a single volume element,<br>based on intensity and<br>contextual information. The<br>parameters of the model<br>were obtained through an<br>algorithm development<br>pipeline. | MRIguidance software<br>implements an image<br>enhancement algorithm<br>using convolutional neural<br>network. Original images are<br>enhanced by running them<br>through a cascade of filter<br>banks, where thresholding<br>and scaling operations are<br>applied. Separate neural<br>network-based filters are<br>obtained to assign a<br>Hounsfield Unit (HU) value<br>to a single volume element,<br>based on intensity and<br>contextual information. The<br>parameters of the model<br>were obtained through an<br>algorithm development<br>pipeline. | The same |
| User Interface | None - enhanced images<br>are viewed on existing<br>PACS workstations | None - enhanced images<br>are viewed on existing<br>PACS workstations | The same |
| Workflow | The software operates on<br>DICOM files on the file<br>system, enhances the<br>images, and stores the<br>enhanced images on the file<br>system. The receipt of<br>original DICOM image files<br>and delivery of enhanced<br>images as DICOM files | The software operates on<br>DICOM files on the file<br>system, enhances the<br>images, and stores the<br>enhanced images on the file<br>system. The receipt of<br>original DICOM image files<br>and delivery of enhanced<br>images as DICOM files | The same |
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image contains the logo for MRI guidance. The logo consists of a circle with an arrow pointing to the upper right inside of it. To the right of the circle are the words "MRI guidance" stacked on top of each other.
| Predicate Device<br>BoneMRI v1.4 | Subject Device<br>BoneMRI | Comment |
|------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------|---------|
| depends on other software<br>systems. Enhanced images<br>co-exist with the original<br>images. | depends on other software<br>systems. Enhanced images<br>co-exist with the original<br>images. | |
### 5.11 Performance Data:
BoneMRI conducted the following performance testing:
- 1. Software verification and validation testing
- 2. Studies that utilized retrospective clinical data to demonstrate the software enhanced imaging quality in MR images via an enhancement of bone.
## Software verification and validation testing
Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices," dated May 11, 2005.
## Performance validation
A quantitative voxel-by-voxel validation of BoneMRI was performed on imaging data from 101 and 103 patients for the pelvic region and lumbar spine region, respectively. The demographics of the patient population are described in the table below.
| Validation data demographics | | |
|------------------------------|----------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------|
| Anatomy | Pelvic region | Lumbar spine region |
| Number of patients | 101 | 103 |
| Indications | Sacroiliitis, developmental hip<br>dysplasia, avascular necrosis<br>of femoral head and femoral<br>acetabular impingement. | Sacroiliitis, degenerative spine<br>diseases, spondylolisthesis,<br>radiculopathy, spondylosis and<br>spinal fractures. |
| Gender | Male: 73<br>Female: 28 | Male: 49<br>Female: 54 |
| Age | $52 \pm 21$ years | $55 \pm 15$ years |
| Data origin/Ethnicity | USA, Europe, Asia | USA, Europe, Asia |
{8}------------------------------------------------
Image /page/8/Picture/1 description: The image shows the logo for MRI Guidance. The logo consists of a circle with an arrow pointing upwards and to the left, followed by the text "MRI" in a larger font and "guidance" in a smaller font below it. The logo is in shades of blue and teal.
The imaging data consist of the BoneMRI and CT images from the same patient in the same anatomical region, acquired during previously conducted clinical investigations. The validations were conducted by MRIguidance based on an algorithm to detect bone images from MRIs obtained using a specific sequence.
Training and test datasets were selected and maintained to be appropriately independent of one another. All training and validation activities were recorded to ensure independence. In addition, validation was performed on data from independent sites (cross-site validation) to ensure that validation was performed on data from centers that did not provide training data.
The objective was to validate the quantitative accuracy of BoneMRI for the pelvic region and lumbar spine region using rigorous, objective, and unbiased statistical tests comparing bone morphology, radiodensity, and radiodensity contrast in BoneMRI and CT images. Therefore, the endpoints of this testing were the metrics that described the accuracy of 3D bone morphology, radiodensity, and radiodensity contrast versus coregistered CT scans in terms of voxel-by-voxel HUs and standard deviations around these HU values.
The results from the validation testing were compared to the accuracy acceptance criteria, specified below, and were found to fall within the pre-specified acceptance criteria (p<0.05).
The results demonstrate clinically acceptable accuracy on each of these endpoints.
The data provided demonstrate that BoneMRI application can
- o accurately reconstruct the 3D bone morphology with a mean absolute cortical delineation error below 1.0 mm on average;
- accurately reconstructs the tissue radiodensity, with a mean deviation o below 25 HU on average and a mean deviation below 55 HU specifically for bone;
- o accurately reconstructs the tissue radiodensity contrast, with a mean HU correlation coefficient above 0.75 specifically for bone.
CONCLUSION: BoneMRI demonstrates accurate bone morphology, radiodensity, and radiodensity contrast. Thus, BoneMRI is a useful tool to qualitatively and quantitatively assess the pelvic region and the lumbar spine region.
{9}------------------------------------------------
Image /page/9/Picture/1 description: The image shows the logo for MRI guidance. The logo consists of a circle with an arrow pointing to the upper right, followed by the text "MRI" in a larger font and "guidance" in a smaller font. The logo is in shades of blue.
## 5.12 Conclusions:
The BoneMRI application, based on the indications for use, product performance, and clinical information provided in this notification, have been shown to be substantially equivalent to the currently marketed predicate device, its predecessor, BoneMRI v1.4. The two devices have the same technological characteristics: both algorithms use the same image-based reconstruction, and both methods have optimized parameters to ensure the robustness of the algorithm. This Special 510(k) submission includes information on the BoneMRI technological characteristics, as well as performance data and verification and validation activities demonstrating that BoneMRI is as safe and effective as the predicate and does not raise different questions of safety or effectiveness.
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.