AmCAD-UT is a Windows-based computer-aided detection (CADe) device intended to assist the medical professionals in analyzing thyroid ultrasound images, acquired from FDA-cleared ultrasound systems. The region of interest (ROI) of a user-selected thyroid nodule is defined by users or suggested by an AI contouring algorithm. After the initial review of the ultrasound images by the physicians, the device further provides detailed information with quantification and visualization of sonographic characteristics of thyroid nodules. The device is intended for use on ultrasound images of discrete thyroid nodules larger than 1cm, for which a biopsy recommendation is required.
Device Story
AmCAD-UT is a Windows-based CADe software for clinical use by physicians. It processes digital thyroid ultrasound images (DICOM, Bitmap, JPEG) from FDA-cleared systems. Users select a thyroid nodule; the device allows manual ROI definition or provides an AI-suggested contour. Once the ROI is confirmed, the device quantifies and visualizes sonographic characteristics (hyperechoic foci, echogenicity, texture, margin, orientation, anechoic areas). The software generates clinical reports based on user inputs and annotated findings, which can be printed or saved as PDFs on a PC or review station. By providing standardized quantification and visualization, the device assists physicians in interpreting thyroid nodules, potentially improving diagnostic consistency and supporting biopsy decision-making.
Clinical Evidence
Bench testing only. Standalone performance studies validated the AI-suggested ROI contouring function against ground truth labeled by a panel of specialists. Results demonstrated the device is effective in determining thyroid nodule contours on images from FDA-cleared ultrasound systems.
Technological Characteristics
Windows-based software for standard PC/review station. Inputs: DICOM, Bitmap, JPEG ultrasound images. Features AI-based contouring, statistical pattern recognition, and quantification algorithms. Connectivity: standalone PC/networked review station. Output: annotated images and automated reports (PDF/print).
Indications for Use
Indicated for medical professionals analyzing thyroid ultrasound images of discrete thyroid nodules >1cm requiring biopsy recommendation.
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 logos of the Department of Health & Human Services and the Food and Drug Administration (FDA). The Department of Health & Human Services logo is on the left, and the FDA logo is on the right. The FDA logo includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION" in blue text.
AmCad BioMed Corporation % Nathan Liu Product Specialist FL.5-2, NO.167, Fu Hsing N. RD. Taipei 105 TAIWAN
September 8, 2021
#### Re: K203555
Trade/Device Name: AmCAD-UT Regulation Number: 21 CFR 892.2050 Regulation Name: Medical image management and processing system Regulatory Class: Class II Product Code: QIH Dated: July 30, 2021 Received: August 2, 2021
Dear Nathan Liu:
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) K203555
Device Name AmCAD-UT
#### Indications for Use (Describe)
AmCAD-UT is a Windows-based computer-aided detection (CADe) device intended to assist the medical professionals in analyzing thyroid ultrasound images, acquired from FDA-cleared ultrasound systems. The region of interest (ROI) of a user-selected thyroid nodule is defined by users or suggested by an AI contouring algorithm. After the initial review of the ultrasound images by the physicians, the device further provides detailed information with quantification and visualization of sonographic characteristics of thyroid nodules. The device is intended for use on ultrasound images of discrete thyroid nodules larger than 1cm, for which a biopsy recommendation is required.
Type of Use (Select one or both, as applicable)
| <span style="font-family: Arial, sans-serif;"> <span style="font-size: 10pt;"></span> <span style="font-size: 10pt;"></span> <span style="font-size: 10pt;"> <b> <span style="font-size: 10pt;"> <span style="text-decoration: overline;">X</span> </span> </b> </span> <span style="font-size: 10pt;"> Prescription Use (Part 21 CFR 801 Subpart D)</span> </span> |
|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <span style="font-family: Arial, sans-serif;"> <span style="font-size: 10pt;"> 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/0 description: The image shows the logo and contact information for AmCad BioMed Corporation. The logo features a stylized blue "A" with a "C" inside. Next to the logo is the company name in both Chinese and English. The address is listed as FL.5, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC, and the telephone number is +886-2-27136227, while the fax number is +886-2-25140245.
#### K203555 510(k) Summary of Safety and Effectiveness
This 510(k) summary of safety and effectiveness information is submitted as part of the Premarket Notification in compliance with requirements of CFR Part 807, Subpart E and Section 807.92
# 5.1 Identification of Submitter:
| Submitter: | AmCad BioMed Corporation |
|---------------|-------------------------------------------------------------|
| Address: | FL.5-2, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, R.O.C. |
| Phone: | 886-2-2713-6227 |
| Fax: | 886-2-2514-0245 |
| Contact: | Nathan Liu |
| Title: | Product Specialist |
| Phone: | 886-2-2713-6227 ext.2337 |
| Fax: | 886-2-2514-0245 |
| Email: | Nathan.liu@amcad.com.tw |
| Manufacturer: | AmCad BioMed Corporation |
| Date prepared: | November 27, 2020 |
|----------------|--------------------|
| Date revised: | September 02, 2021 |
## 5.2 Identification of Product
| Submission Number: | K203555 |
|------------------------------|------------------------------------------------|
| Device Trade Name: | AmCAD-UT |
| Device Classification Name: | Medical Image Management and Processing System |
| Regulation Number: | 21 CFR 892.2050 |
| Classification Product Code: | QIH |
| Classification Panel: | Radiology |
| Classification: | Class II |
| Manufacturer: | AmCad BioMed Corporation |
## 5.3 Predicate Device
This subject software medical device is substantially equivalent to the device listed below:
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the logo and contact information for AmCad BioMed Corporation. The logo features a blue stylized letter "A" with a white circle inside. The text includes the company name in both Chinese and English, followed by the address: FL.5, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC. The telephone number is +886-2-27136227 and the fax number is +886-2-25140245.
Model: AmCAD-UT Detection 2.2 Manufacturer: AmCad BioMed Corporation 510(k) Number: K180006
## 5.4 Device Description
AmCAD-UT is a Windows-based computer-assisted detection (CADe) software application device designed to assist medical professionals in analyzing thyroid ultrasound images with the region of interest (ROI) of a selected nodule defined by users or suggested by an Al algorithm after the user specifies the location of the nodule.
After the initial review of thyroid ultrasound images by the physician, he/she can use AmCAD-UT to analyze thyroid images for further interpretation. Once the ROI is confirmed, the physician may process the image for detection and quantification of sonographic characteristics (i.e., hyperechoic foci, echogenicity, texture, margin, orientation and anechoic areas) by AmCAD-UT. The device provides more detailed information with quantification and visualization of the sonographic characteristics of thyroid nodule that may assist physician in his/her complete interpretation.
The software application automatically generates reports given the user preference inputs (e.g., the nodule size, nodule location and shape, and the presence or absence of the sonographic characteristics) annotated during the image analysis process. A report form has been designed by AmCad to be consistent with the conventional clinical thyroid report form. An output of the report may be viewed and sent to paper printers or saved on the standalone PC or review station as PDF file.
## 5.5 Indications for Use
AmCAD-UT is a Windows-based computer-aided detection (CADe) device intended to assist the medical professionals in analyzing thyroid ultrasound images, acquired from FDA-cleared ultrasound systems. The region of interest (ROI) of a user-selected thyroid nodule is defined by users or suggested by an AI contouring algorithm. After the initial review of the ultrasound images by the physicians, the device further
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the logo and contact information for AmCad BioMed Corporation. The logo features a blue stylized letter "C" next to the company's name in both Chinese and English. Below the name is the company's address: FL.5, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC. The telephone number is +886-2-27136227 and the fax number is +886-2-25140245.
provides detailed information with quantification and visualization of sonographic characteristics of thyroid nodules. The device is intended for use on ultrasound images of discrete thyroid nodules larger than 1cm, for which a biopsy recommendation is required.
# 5.6 Comparison with Predicate Devices
AmCAD-UT is a computer-assisted detection (CADe) device which provides viewing and post-acquisition image processing and analysis of thyroid ultrasound images with regions of interest (ROI) and automatically generates reports from user inputs annotated during the image analysis process. This software medical device is substantially equivalent to the predicate device listed below:
| Model: | AmCAD-UT® Detection, Version 2.2 |
|----------------|----------------------------------|
| Manufacturer: | AmCad BioMed Corporation |
| 510(k) Number: | K180006 |
The comparison as described in the following table:
| | AmCAD-UT | AmCAD-UT® Detection 2.2 |
|---------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Manufacturer | AmCad BioMed Corp. | AmCad BioMed Corp. |
| 510(k) Number | K203555 | K180006 |
| Regulation<br>Number | 21 CFR 892.2050 - Class II | 21 CFR 892.2050 - Class II |
| Regulation<br>Name | Medical Image Management<br>and Processing System | Medical Image Management<br>and Processing System |
| Product Code | QIH | LLZ |
| Intended Use | AmCAD-UT is intended to<br>assist the medical<br>professionals in analyzing<br>thyroid ultrasound images by<br>quantification and visualization<br>of sonographic characteristics<br>of thyroid nodules. | AmCAD-UT® Detection 2.2 is<br>intended to assist the medical<br>professionals in analyzing<br>thyroid ultrasound images of<br>user-selected regions of<br>interest (ROI). After the initial<br>review of the ultrasound<br>images by the physicians, the<br>device further provides<br>detailed information with |
| | AmCAD-UT | AmCAD-UT® Detection 2.2 |
| Indications for<br>Use | AmCAD-UT is a<br>Windows-based<br>computer-aided detection<br>(CADe) device intended to<br>assist the medical<br>professionals in analyzing<br>thyroid ultrasound images,<br>acquired from FDA-cleared<br>ultrasound systems. The<br>region of interest (ROI) of a<br>user-selected thyroid nodule is<br>defined by users or suggested<br>by an Al contouring algorithm.<br>After the initial review of the<br>ultrasound images by the<br>physicians, the device further<br>provides detailed information<br>with quantification and<br>visualization of sonographic<br>characteristics of thyroid<br>nodules. The device is<br>intended for use on ultrasound<br>images of discrete thyroid<br>nodules larger than 1cm, for<br>which a biopsy<br>recommendation is required. | AmCAD-UT® Detection 2.2 is a<br>Windows-based<br>computer-aided detection<br>(CADe) device intended to<br>assist the medical<br>professionals in analyzing<br>thyroid ultrasound images,<br>acquired from FDA-cleared<br>ultrasound systems, with<br>user-selected regions of<br>interest (ROI). After the initial<br>review of the ultrasound<br>images by the physicians, the<br>device further provides<br>detailed information with<br>quantification and visualization<br>of sonographic characteristics<br>of thyroid nodules. The device<br>is intended for use on<br>ultrasound images of discrete<br>thyroid nodules larger than<br>1cm, for which a biopsy<br>recommendation is required. |
| Functional<br>Capability of<br>Image<br>Processing | AmCAD-UT analyzes the<br>user-defined or Al-suggested<br>regions of interest (ROI) of a<br>user-selected thyroid nodule<br>for detection and<br>quantification of sonographic<br>characteristics (hyperechoic | AmCAD-UT® Detection 2.2<br>analyzes the user-selected<br>regions of interest (ROI) of<br>thyroid ultrasound image for<br>the detection and<br>quantification of sonographic<br>characteristics (hyperechoic |
| | AmCAD-UT | AmCAD-UT® Detection 2.2 |
| | foci, echogenicity, texture,<br>margin, orientation and<br>anechoic areas). The device<br>further provides detailed<br>information with visualization<br>of sonographic characteristics<br>of thyroid nodules. | foci, echogenicity, texture,<br>margin, orientation and<br>anechoic areas). The device<br>further provides detailed<br>information with visualization<br>of sonographic characteristics<br>of thyroid nodules. |
| Reading<br>Paradigm | AmCAD-UT is to provide<br>quantification and<br>visualization of sonographic<br>characteristics after<br>physicians' initial review of the<br>images. | AmCAD-UT® Detection 2.2 is<br>to provide quantification and<br>visualization of sonographic<br>characteristics after<br>physicians' initial review of the<br>images. |
| Output<br>Generated by<br>the CAD Device | The image can be annotated<br>with the detected sonographic<br>characteristics and be<br>recorded by the device. The<br>software also automatically<br>generates reports given the<br>user preference inputs in the<br>analysis process. | The image can be annotated<br>with the detected sonographic<br>characteristics and be<br>recorded by the device. The<br>software also automatically<br>generates reports given the<br>user preference inputs in the<br>analysis process. |
| Type of Film to<br>be Processed<br>by the CAD<br>Device | Digital ultrasound image | Digital ultrasound image |
| Software<br>Design | Based on Al, Statistical Pattern<br>Recognition and Quantification<br>method | Based on Statistical Pattern<br>Recognition and Quantification<br>method |
| Ground Truth<br>Establishment | The ground truth to be<br>established for performance<br>studies of the device is the ROI<br>labeled by a panel of<br>specialists. | The ground truth to be<br>established for performance<br>studies of the device includes<br>the ROI, the presence of each<br>sonographic characteristic, and<br>the surgical pathology<br>examination result. |
| Platform | Window-based | Window-based |
| Operating<br>System | Standard PC or review station | Standard PC or review station |
| Clinical<br>Application | Thyroid cancers | Thyroid cancers |
| | AmCAD-UT | AmCAD-UT® Detection 2.2 |
| Image Type | Ultrasound Image | Ultrasound Image |
| Image Format | DICOM3.0, Bitmap, JPEG | DICOM3.0, Bitmap, JPEG |
| ROI<br>Quantification | Yes | Yes |
| Automatically<br>Generating<br>Report | Yes | Yes |
| Report Storage | Paper printers, Local disk | Paper printers, Local disk |
| Performance<br>Testing Data to<br>Support SE<br>Determination | Results from standalone<br>performance testing of the AI<br>suggested ROI's of<br>user-selected nodules | Results from standalone<br>performance testing and<br>clinical performance testing<br>(MRMC study) |
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image shows the logo of Anke Bio Co., Ltd. The logo consists of a blue circle with a white "C" inside, followed by the company name in traditional Chinese characters. The characters are arranged horizontally and are black in color. The logo is simple and professional, and it is likely used on the company's website, marketing materials, and other official documents.
- TT - AmCad BioMed Corporation
FL.5, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC
Tel: +886-2-27136227 Fax: +886-2-25140245
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image contains the logo and name of Anke Biotechnology Co., Ltd. The logo is a blue rounded square with a white "C" inside. The text is in traditional Chinese characters and is arranged in two lines.
- TT - AmCad BioMed Corporation
FL.5, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC
Tel: +886-2-27136227 Fax: +886-2-25140245
FL.3, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC
Tel: +886-2-27136227 Fax: +886-2-25140245
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image contains the logo and name of "Anke Sheng Medical Co., Ltd." The logo is a blue rounded shape with a white "C" inside. The name of the company is written in Chinese characters to the right of the logo. The text is black and in a simple font.
**AmCad Blomed Corporation**
FL.5, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC
Tel: +886-2-27136227 Fax: +886-2-25140245
AmCAD-UT is substantially equivalent to AmCAD-UT® Detection 2.2 that provides display and post-acquisition image analysis of ultrasound images assisting the physician in analyzing the ultrasound images of thyroid nodules. The standalone performance assessment results of AmCAD-UT are shown substantially equivalent to AmCAD-UT® Detection 2.2. The minor technological difference, i.e., the addition of the Al-suggested ROI of a user-selected nodule, do not raise any new questions of safety and effectiveness. Thus, AmCAD-UT is substantially equivalent to the predicate device as a Computer-Assisted Detection (CADe) device intended to assist the physicians in clinical practice.
## 5.7 Performance Standards
No applicable FDA performance standards have been issued under the authority of Section 514.
# 5.8 Software
Software development for the AmCAD-UT follows documented processes for software design, verification and validation testing. A risk assessment has been completed to identify potential design hazards that could cause an error or injury
{9}------------------------------------------------
Image /page/9/Picture/0 description: The image shows the logo and contact information for AmCad BioMed Corporation. The logo features a blue stylized letter "C" next to the company's name in both Chinese and English. Below the name is the address: FL.5, NO.167, Fu Hsing N. RD., Taipei 105, Taiwan, ROC. The telephone number is +886-2-27136227 and the fax number is +886-2-25140245.
based on the use of the quantification results. Appropriate steps have been taken to control all identified risks for this type of image viewing and quantification device.
# 5.9 Summary of Performance Data to Support Substantial Equivalence
AmCad BioMed Corporation has conducted standalone performance studies to validate and assess the performance of the AmCAD-UT for its added function of Al-suggested ROI contouring. The standalone studies evaluated the performance of the contours suggested by the AI algorithm of user-selected nodules on images acquired from FDA-cleared ultrasound systems and showed that the device was effective in determining the contour of thyroid nodules.
# 5.10 Conclusions
AmCAD-UT, being a computer assisted detection (CADe) software device, has the same intended use as the predicate device. The suggested ROI of a user-selected nodule is added in this proposed device and the performance data demonstrates that it performs effectively and the device is as safe and effective as the predicate device. AmCAD-UT is, therefore, substantially equivalent to the predicate devices as the new function of the device assists the medical professionals in identifying the contours of thyroid nodules without interfering with the analysis functions of the device.
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.