Gamma analysis criterion 2%/2mm in 98% of voxels; average dose deviation < 5% or 1 Gy
PTV dose differences < 1%
—
—
—
—
Indications for Use
MRCAT imaging is intended to provide the operator with information of tissue properties for radiation attenuation estimation purposes in photon external beam radiotherapy treatment planning.
Device Story
MRCAT Head & Neck is a software application for Philips Ingenia, Ingenia Ambition, and Ingenia Elition MR systems. It functions as an accessory for radiotherapy treatment planning. The device takes 3D mDixon (in-phase and water) MR images as input. A convolutional neural network (CNN) processes these images to perform automatic tissue characterization, segmenting bones (skull, C-spine, jaw, shoulder girdle) and body outlines. It assigns a continuum of Hounsfield Unit (HU) values based on fat and water intensities to generate CT-like density images. The software runs on the MR console, with processing occurring in the background. The resulting MRCAT images are stored in the MR database and can be exported via DICOM to treatment planning systems. Clinicians use these images to estimate radiation attenuation for dose calculation, potentially enabling MR-only radiotherapy simulation. The device is operated by radiology/radiotherapy staff in a clinical setting.
Clinical Evidence
Bench testing only. Performance validated through comparison of simulated dose accuracy against CT-based plans. Results showed PTV dose differences well below 1% with clinically insignificant bias. Artificial PTV analysis confirmed accuracy in the head and neck region. Geometric accuracy verified to within 1-5mm depending on sphere diameter.
Technological Characteristics
Software plug-in for MR systems. Uses 3D mDixon FFE imaging protocol. Core technology: Convolutional Neural Network (CNN) for image segmentation and HU value assignment. Connectivity: DICOM export. Standards: ANSI/AAMI ES60601-1, IEC 60601-1-6, IEC 60601-2-33, IEC 62304, IEC 62366-1, ISO 14971.
Indications for Use
Indicated for radiotherapy treatment planning for patients with soft tissue tumors in the Head and Neck region.
Regulatory Classification
Identification
A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food & Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
Philips Oy % Anne-Sophie Glantenay Sr. Regulatory Affairs Specialist Avritie 4 Vantaa, 01510 Finland
Re: K214081
Trade/Device Name: MRCAT Head & Neck Regulation Number: 21 CFR 892.5050 Regulation Name: Medical Charged-Particle Radiation Therapy System Regulatory Class: Class II Product Code: MUJ Dated: December 23, 2021 Received: December 27, 2021
Dear Anne-Sophie Glantenay:
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
{1}------------------------------------------------
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 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,
Julie M. Sullivan, PhD Branch Chief Nuclear Medicine and Radiation Therapy Branch 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) K214081
Device Name MRCAT Head & Neck
#### Indications for Use (Describe)
MRCAT imaging is intended to provide the operator with information of tissue properties for radiation attenuation estimation purposes in photon external beam radiotherapy treatment planning.
Indication for use:
MRCAT Head and Neck is indicated for radiotherapy treatment planning for patients with soft tissue tumors in the Head and Neck region.
Type of Use (Select one or both, as applicable)
> Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
#### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
#### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW."
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
FORM FDA 3881 (6/20)
{3}------------------------------------------------
Image /page/3/Picture/0 description: The image shows the text "Philips Oy". The text is written in a simple, sans-serif font. The text is black and the background is white.
Image /page/3/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The font is sans-serif and the letters are evenly spaced. The background is white, providing a strong contrast to the blue letters.
### 510(k) Summary of Safety and Effectiveness
This 510(k) summary of safety and effectiveness information is prepared in accordance with 21 CFR §807.92.
| Date<br>Prepared: | April 05, 2022 | | |
|--------------------------------|---------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------|--|
| Manufacturer: | Philips Oy<br>Äyritie 4<br>01510 Vantaa, Finland | | |
| | Establishment Registration Number: 9680194 | | |
| Primary<br>Contact<br>Person: | Jan van de Kerkhof<br>Sr. Manager Regulatory Affairs<br>Phone: +31-613300542<br>E-mail: jan.van.de.kerkhof@philips.com | | |
| Secondary<br>Contact<br>Person | Anne-Sophie Glantenay<br>Sr. Regulatory Affairs Specialist<br>Phone: +31-611531002<br>E-mail: anne-sophie.glantenay@philips.com | | |
| Device Name: | MRCAT Head & Neck | | |
| Classification: | Classification Name: | Medical charged-particle radiation therapy<br>system (accessory for) | |
| | Classification Regulation: | 21 CFR §892.5050 | |
| | Classification Panel: | Radiology | |
| | Device Class: | Class II | |
| | Product code: | MUJ (System, Planning, Radiation Therapy<br>Treatment) | |
| Predicate<br>Device: | Trade Name: | MRCAT Brain | |
| | Manufacturer: | Philips Oy | |
| | 510(k) Clearance: | K193109 (January 24, 2020) | |
| | Classification Regulation: | 21 CFR, Part 892.5050 | |
| | Classification Name: | Radiation Therapy Planning System | |
| | Classification Panel: | Radiology | |
| | Device Class: | Class II | |
| | Product Code: | MUJ (System, planning, radiation therapy<br>treatment) | |
| Reference<br>Device: | Trade Name: | AcQPlan 5.0 | |
| | Manufacturer: | Philips Medical Systems (Cleveland), Inc. | |
| | 510(k) Clearance: | K013644 (September 12, 2002) | |
| | Classification Regulation: | 21 CFR, Part 892.5840 | |
| | Classification Name: | Radiation Therapy Planning System | |
| | Classification Panel: | Radiology | |
| | Device Class: | Class II | |
| | Product Code: | MUJ (System, planning, radiation therapy<br>treatment) | |
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the word "PHILIPS" in large, bold, blue letters. The font is sans-serif and the letters are evenly spaced. The background is white, providing a strong contrast that makes the word stand out.
# Device
description: MRCAT Head & Neck is a software application to Ingenia, Ingenia Ambition, and Ingenia Elition MR systems. MRCAT Head & Neck is available to the customer as an option to Ingenia MR-RT package, which is a set of accessories for Ingenia systems.
> Automated generation of MRCAT images takes place at the MR console of Ingenia. The embedded image post-processing runs in the background parallel to image acquisition. MRCAT algorithm enables automatic tissue characterization: Bones are segmented from mDixon in-phase and water images using machine learning based segmentation. Body outline is segmented using in-phase and water images. Tissues are then assigned a continuum of HU values depending on the fat and water intensities of the voxels. The HU assignment provides MRCAT images with CT-like density information.
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the word "PHILIPS" in a bold, sans-serif font. The letters are a bright blue color, and the background is white. The word is horizontally oriented and takes up most of the image space.
| Indications for<br>Use: | Intended Use: | |
|------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--|
| | MRCAT imaging is intended to provide the operator with information of<br>tissue properties for radiation attenuation estimation purposes in photon<br>external beam radiotherapy treatment planning. | |
| | Indications for use: | |
| | MRCAT Head and Neck is indicated for radiotherapy treatment planning for<br>patients with soft tissue tumors in the Head and Neck region. | |
| Fundamental<br>Scientific<br>Technology: | MRCAT Head and Neck functionality is implemented as a software plug-in<br>for the MR main software, and it contains the following main features: | |
| | 1) Automatic post-processing tool delivering MRCAT images<br>2) Examcard with mDixon imaging protocol<br>3) DICOM export of MRCAT image. | |
| | MRCAT Image Generation | |
| | MRCAT images are generated with an ExamCard post-processing step, which<br>uses the images from the previous mDixon scan. | |
| | The post-processing logic takes care of launching MRCAT algorithm<br>executable calculating a new 3D MRCAT image. The post-processing is<br>started once the acquired mDixon MR images have been reconstructed. The<br>first step of MRCAT generation is to pre-process the images to ensure that<br>the MRCAT source images have consistent intensities. The intensity | |
normalized images are then used as input in a convolutional neural network (CNN). The CNN is trained using matched pairs of CT and MRCAT source images. The training of the CNN is locked and is not adapted during use. The output of the CNN is post-processed to create images in CT values. The generated MRCAT images are checked for correctness to ensure validity of the generated MRCAT for radiation treatment. The sanity checks ensure that the imaging field of view has been positioned correctly and that the MRCAT body outline matches that of the MR. The HU values for the MRCAT Head and Neck are calibrated using registered CT images. Once the process is running, post-processing logic exchanges information with the algorithm:
- Image source data to algorithm, and image output data back to the ● post-processing step
- Progress notifications
{6}------------------------------------------------
Image /page/6/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The letters are evenly spaced and fill most of the frame. The background is white, providing a strong contrast to the blue letters.
- Error and warning notifications ●
The 3D MRCAT image from the post-processing step is stored into the MR image database.
### mDIXON scan
A T1-weighted Fast Field Echo (FFE) 3D mDixon dual echo imaging protocol, with imaging parameters optimized for MRCAT image post-processing and for geometric accuracy, is delivered as a part of MRCAT Head and Neck option. The mDixon imaging sequence provides two image contrasts for the MRCAT algorithm: inphase and water images. MRCAT Head and Neck uses fixed parameters for the mDixon scan, only the image stack location is configurable. An mDixon imaging protocol, with imaging parameters optimized for MRCAT image post-processing and for geometric accuracy, is delivered as a part of MRCAT Head and Neck option. MRCAT Head and Neck uses fixed parameters for mDixon scan, only the image stack location is configurable.
### DICOM Export
The MRCAT post-processing step stores the image data returned by the MRCAT algorithm into MR database.
MRCAT images can be exported in DICOM format enabling the use as primary images in the treatment planning systems
### Hardware platform description
The new software extensions introduced by MRCAT Head and Neck run on the MR console of Ingenia.
Based on the information provided above, the MRCAT Head and Neck is considered substantially equivalent to the primary currently marketed and predicate device (K193109, January 24, 2020) in terms of fundamental scientific technology.
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image shows the word "PHILIPS" in large, bold, blue letters. The letters are slightly stylized with a horizontal line running through each letter, giving them a layered effect. The background is plain white, which makes the blue letters stand out.
## Comparison of technological characteristics with the predicate device:
# Table 1 Comparison of the primary currently marketed and predicate device, MRCAT Brain versus the proposed MRCAT Head & Neck
| Device | MRCAT Brain | MRCAT Head & Neck | Similarities<br>and<br>Differences |
|------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Manufacturer | Philips Oy | Philips Oy | - |
| 510(k)<br>Number | K193109 | - | - |
| Product Code | MUJ | MUJ | Identical |
| Regulation<br>Number | 892.5050 | 892.5050 | Identical |
| Regulation<br>Name | Accelerator, Linear,<br>Medical | Accelerator, Linear,<br>Medical | Identical |
| Intended use | MRCAT imaging is<br>intended to provide the<br>operator with<br>information of tissue<br>properties for radiation<br>attenuation estimation<br>purposes in photon<br>external<br>beam radiotherapy<br>treatment planning. | MRCAT imaging is<br>intended to provide<br>the operator with<br>information of tissue<br>properties for<br>radiation attenuation<br>estimation purposes<br>in photon external<br>beam radiotherapy<br>treatment planning. | Identical |
| Indications<br>for use | MRCAT Brain is<br>indicated for<br>radiotherapy treatment<br>planning for primary<br>and metastatic brain<br>tumor patients. | MRCAT Head and<br>Neck is indicated for<br>radiotherapy<br>treatment planning<br>for patients with soft<br>tissue tumors in the<br>Head and Neck<br>region | No significant<br>difference.<br>MRCAT Brain<br>and MRCAT<br>Head & Neck<br>are both<br>indicated for<br>radiotherapy<br>treatment<br>planning in a<br>defined<br>region.<br>Brain tumors<br>are soft tissue<br>tumors. |
{8}------------------------------------------------
Image /page/8/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The font is sans-serif and the letters are evenly spaced. The word is centered and takes up most of the frame. The background is white.
| Primary<br>image<br>dataset | MRCAT | MRCAT | Identical |
|--------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Secondary<br>image<br>dataset | mDixon, MRI | mDixon, MRI | Identical<br>MR images<br>obtained in<br>the same<br>imaging<br>session are<br>inherently in<br>the same<br>frame of<br>reference. |
| Registration<br>between<br>primary and<br>secondary<br>image<br>datasets | Secondary mDixon MR<br>image, source data to<br>MRCAT, is inherently<br>registered as part of<br>MRCAT algorithm with<br>MRCAT image, which<br>simplifies workflow.<br>Other MR images, like<br>T2w and fiducial<br>marker detection<br>images are registered<br>using tools available in<br>RTP system | Secondary mDixon<br>MR image, source<br>data to MRCAT, is<br>inherently registered<br>as part of MRCAT<br>algorithm with<br>MRCAT image, which<br>simplifies workflow.<br>Other MR images,<br>like T2w images are<br>registered using tools<br>available in RTP<br>system | No significant<br>difference<br>Secondary MR<br>images are<br>obtained in<br>the same<br>imaging<br>session<br>reducing the<br>possibility of<br>patient<br>motion<br>between<br>images. |
| Primary<br>image<br>density<br>information | MRCAT image intensity<br>information is provided<br>in Hounsfield Unit (HU)<br>values. | MRCAT image<br>intensity information<br>is provided in<br>Hounsfield Unit (HU)<br>values. | Identical.<br>MRCAT Brain<br>and MRCAT<br>Head & Neck<br>both have<br>continuous<br>HU value<br>approach. |
| Conversion<br>from primary<br>image to<br>density<br>values used<br>in dose<br>calculation | Primary image HU<br>values are converted to<br>densities through<br>density table specific<br>for the MRCAT. | Primary image HU<br>values are converted<br>to densities through<br>density table specific<br>for the MRCAT. | No significant<br>difference<br>MRCAT has<br>specific<br>density table<br>that is used in<br>a similar<br>manner to CT<br>specific<br>density tables. |
| MRCAT<br>algorithm | Bones are segmented<br>from mDixon in-phase<br>and water images using<br>machine learning based<br>segmentation. The<br>segmented bones are<br>in skull, upper C-spine<br>and jaw.<br>Body outline is<br>segmented using in-<br>phase and water<br>images.<br>Bones are assigned a<br>continuum of HU<br>values between dense<br>cortical bone and light<br>spongy bone depending<br>on the fat and water<br>intensities of the<br>voxels.<br>Soft tissue are assigned<br>a continuum of HU<br>values depending on<br>the fat and water<br>intensities of the<br>voxels.<br>The HU values for the<br>MRCAT Brain are<br>calibrated using<br>registered CT images<br>from several sites.<br>MRCAT Brain algorithm<br>is fully trained before<br>product release, after | Bones are segmented<br>from mDixon in-<br>phase and water<br>images using<br>machine learning<br>based segmentation.<br>The segmented<br>bones are in skull, C-<br>spine, jaw, and<br>shoulder girdle.<br>Body outline is<br>segmented using in-<br>phase and water<br>images.<br>Bones are assigned a<br>continuum of HU<br>values between<br>dense cortical bone<br>and light spongy<br>bone depending on<br>the fat and water<br>intensities of the<br>voxels.<br>Soft tissue are<br>assigned a<br>continuum of HU<br>values depending on<br>the fat and water<br>intensities of the<br>voxels.<br>The HU values for the<br>MRCAT Head & Neck<br>are calibrated using | No significant<br>difference<br>Segmentation<br>is done for<br>both MRCAT<br>Brain and<br>MRCAT Head<br>& Neck using<br>the mDIXON<br>image<br>contrasts.<br>HU value<br>assignment is<br>done based<br>on mDixon<br>image<br>intensities.<br>The models<br>used are<br>equivalent in<br>relation to<br>dose and<br>positioning<br>accuracy.<br>Both<br>algorithms are<br>locked; they<br>do not change<br>after<br>installation<br>based on new<br>data during<br>the use. |
| | | | |
| | which the algorithm is<br>locked. | registered CT images<br>from several sites.<br><br>MRCAT Head & Neck<br>algorithm is fully<br>trained before<br>product release, after<br>which the algorithm<br>is locked. | |
| Patient<br>positioning | Ingenia MR-RT with<br>MRCAT Brain supports<br>MR Only simulation<br>with relative patient<br>marking.<br><br>Patient positioning in<br>the treatment machine<br>must be checked either<br>with cone beam<br>computed tomography<br>(CBCT) or plain<br>radiographs by<br>registering bone<br>structures. | Ingenia MR-RT with<br>MRCAT Head & Neck<br>supports MR Only<br>simulation with<br>relative patient<br>marking.<br><br>Patient positioning in<br>the treatment<br>machine must be<br>checked either with<br>cone beam<br>computed<br>tomography (CBCT)<br>or plain radiographs<br>by registering bone<br>structures. | No significant<br>difference<br><br>The visibility<br>of bone<br>structures is<br>equivalent for<br>both<br>products. |
| Dose<br>accuracy | The simulated dose<br>based on MRCAT Brain<br>images shall not differ<br>in 95% of the indicated<br>patients (gamma<br>analysis criterion<br>2%/2mm realized in<br>98% of voxels within<br>the PTV or exceeding<br>75% of the maximum<br>dose) when compared<br>with CT-based plan.<br>The average simulated<br>dose based on MRCAT<br>Brain shall not deviate<br>more than 5% or 1 Gy,<br>which ever is greater, in<br>99% of the indicated<br>patients in the volume<br>of sensitive organs<br>when compared with<br>CT based plan. | The simulated dose<br>based on MRCAT<br>Head & Neck images<br>shall not differ in<br>95% of the indicated<br>patients (gamma<br>analysis criterion<br>2%/2mm realized in<br>98% of voxels within<br>the PTV or exceeding<br>75% of the maximum<br>dose) when<br>compared with CT-<br>based plan.<br>The average<br>simulated dose based<br>on MRCAT Head &<br>Neck shall not<br>deviate more than<br>5% or 1 Gy, which<br>ever is greater, in<br>99% of the indicated<br>patients in the<br>volume of sensitive | Identical<br>The same<br>dose<br>evaluation<br>methodology<br>is used for<br>both<br>products. The<br>criteria are<br>selected<br>based on the<br>needs of the<br>application. |
| Geometric<br>accuracy | MRCAT accuracy:<br>± 1 mm accuracy: 200<br>mm diameter sphere<br>± 2 mm accuracy: 400<br>mm diameter sphere<br>(limited in the bore<br>direction by +/- 160<br>mm from the z=0 mm<br>plane)<br>± 5 mm accuracy: 500<br>mm diameter sphere<br>(limited in the bore<br>direction by +/- 160<br>mm from the z=0 mm<br>plane) | organs when<br>compared with CT<br>based plan.<br>MRCAT accuracy:<br>± 1 mm accuracy:<br>200 mm diameter<br>sphere<br>± 2 mm accuracy:<br>400 mm diameter<br>sphere (limited in the<br>bore direction by +/-<br>160 mm from the z=0<br>mm plane)<br>± 5 mm accuracy:<br>500 mm diameter<br>sphere (limited in the<br>bore direction by +/-<br>160 mm from the z=0<br>mm plane) | Identical |
| MRCAT<br>source<br>imaging<br>sequence | mDIXON 3D scan with<br>acquired voxel size of<br>1.10/1.10/1.40 mm (1.5<br>T) and 1.1/1.1/1.1 mm<br>(3T), and<br>bandwidth/pixel 481Hz<br>(1.5T) or 868Hz (3T).<br>Most scanning<br>parameters locked | mDIXON 3D scan<br>with acquired voxel<br>size of 1.2/1.2/1.2<br>mm (1.5 T) and<br>1.1/1.1/1.1 mm (3T),<br>and bandwidth/pixel<br>481Hz (1.5T) or<br>868Hz (3T).<br>Most scanning<br>parameters locked | No significant<br>difference<br>In both<br>solutions the<br>essential<br>parameters<br>are locked to<br>avoid user<br>errors<br>potentially<br>affecting the<br>accuracy and<br>reliability of<br>the method.<br>The voxel<br>sizes do not<br>differ<br>significantly. |
| DICOM RT<br>export | yes | yes | Identical |
{9}------------------------------------------------
Image /page/9/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The font is sans-serif and the letters are evenly spaced. The word is centered and takes up most of the frame.
{10}------------------------------------------------
Image /page/10/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The font is sans-serif and the letters are evenly spaced. The word is centered and takes up most of the frame.
{11}------------------------------------------------
Image /page/11/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The font is sans-serif and the letters are evenly spaced. The word is centered and takes up most of the frame.
{12}------------------------------------------------
Image /page/12/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The letters are evenly spaced and aligned horizontally. The background is white, providing a strong contrast to the blue letters.
# Summary of
Non-Clinical Performance Data:
The MRCAT Head and Neck complies with the following international and FDA-recognized consensus standards:
International and FDA-recognized consensus standards:
- . ANSI/AAMI ES60601-1: 2012, Medical electrical equipment - Part 1: General requirements for basic safety and essential performance
- . IEC 60601-1-6:2010, Medical electrical equipment - Part 1-6: General requirements for safety - Collateral standard: Usability.
- IEC 60601-2-33:2015, Medical electrical equipment - Part 2-33: Particular requirements for the safety of magnetic resonance equipment for medical diagnosis.
- . IEC 62304:2016, Medical device software - Software life-cycle processes
- IEC 62366-1:2020, Medical devices – Application of usability engineering to medical devices
- . ISO 14971:2019, Medical devices – Application of risk management to medical devices
{13}------------------------------------------------
Image /page/13/Picture/0 description: The image shows the text "Philips Oy" in a simple, sans-serif font. The text is black and appears against a white background. The letters are evenly spaced and clearly legible.
Image /page/13/Picture/1 description: The image shows the word "PHILIPS" in large, bold, blue letters. The font is sans-serif and the letters are evenly spaced. The word is centered and takes up most of the frame. The background is white.
Non-Clinical verification and or validation tests have been performed with regards to the intended use, the technical claims, the requirement specifications and the risk management results.
Non-Clinical verification and or validation test results demonstrate that the MRCAT Head and Neck:
- Complies with the aforementioned international and FDA-recognized consensus standards
- . Meets the acceptance criteria and is adequate for its intended use.
Therefore, the MRCAT Head and Neck is substantially equivalent to the primary currently marketed and predicate device (K193109, January 24, 2020) in terms of safety and effectiveness.
Summary of The resulting dose accuracy for MRCAT Head and Neck is similar to CT. The Clinical Data: PTV dose differences obtained when using MRCAT in place of CT are well below 1% with a very small bias, and therefore clinically insignificant.
> The dose analysis was further expanded with artificial PTV analysis, using PTVs that were automatically placed around the head and neck region. The results for the artificial PTVs agreed well with the clinical plan results and strengthen the conclusion that MRCAT provides accurate dose calculations for the head and neck region.
In summary, the MRCAT Head and Neck images are spatially accurate radiation attenuation estimates that can aid in the EBRT planning of soft tissue tumors in the head and neck region.
### Substantial Equivalence
The MRCAT Head and Neck is substantially equivalent to the primary currently marketed and predicate device (K193109, January 24, 2020) in Conclusion: terms of design features, fundamental scientific technology, indications for use, and safety and effectiveness. Additionally, substantial equivalence was demonstrated with non-clinical performance (verification and validation) tests, which complied with the requirements specified in the international and FDA-recognized consensus standards, IEC 62304, IEC 62366-1 and ISO 14971. The results of these tests demonstrate that MRCAT Head and Neck met the acceptance criteria and is adequate for this intended use.
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.