EmboGuide is a post processing software medical device intended to assist physicians in performing embolization of hypervascular tumors in the liver using interventional X-ray. It provides tools to help the user with the analysis of 3D rotational angiography images. Its output is intended as an adjunct means to help with the planning and guidance of the embolization procedure. It provides real time overlay of 3D rotational angiography images of the same anatomy to support device/catheter guidance.

Device Description

EmboGuide is a post processing software medical device intended to assist physicians in performing embolization of hypervascular tumors in the liver using interventional X-ray. EmboGuide is an extension of XperCT and intended to be used in combination with an Allura interventional X-ray system. Like the primary predicate device 3D Roadmap, EmboGuide adds specific functionality to the Allura system but does not change the overall intended use of the Allura system or the overall risk profile.

EmboGuide uses a 3D volume reconstructed from 3D rotational angiography images acquired on the Allura X-ray system and the segmentation of lesions on previously acquired CT, MR or XperCT datasets as input data for the planning of the embolization. The physician can use this input data to analyze the vasculature of lesions, and to identify and annotate the blood vessels that shall be embolized (feeding vessels). The real-time overlay and registration of the 3D volume on live 2D X-ray images from the Allura X-ray system of the same anatomy can be used as additional 3D image guidance to support the navigation of the device/catheter. Planning data, like the earlier annotated feeding vessels and/or 3D landmarks can be displayed on 2D-3D fused images as supporting information.

AI/ML Overview

Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

The document explicitly states acceptance criteria for the "overall agreement among readers for identification of feeding vessels" and reports sensitivity for EmboGuide. It also implicitly compares EmboGuide's performance to CBCT.

Acceptance Criteria Category	Acceptance Criteria	Reported Device Performance
Sensitivity for Identification of Tumor Feeding Vessels (for HCC patients with diagnostic quality CBCT and no tumors/vessels outside CBCT volume)	Not explicitly stated as an AC, but sensitivity is a key performance metric.	83% +/- 8% with a 95% CI. This is stated as the sensitivity in clinical routine use.
Overall Agreement Among Readers for EmboGuide AFD and EmboGuide in Clinical Practice	Greater than 0.7 (70%)	EmboGuide AFD and routine use: Greater than 0.7. This indicates consistent identification of feeding vessels across different readers.
Overall Agreement Among Readers for EmboGuide AFD Alone	Not explicitly stated as an AC, but reported for comparison.	Close to one (0.99 with lower bound of 95% CI of 0.986). This indicates exceptionally high consistency among readers when using EmboGuide AFD alone.
Overall Agreement Among Readers for CBCT	Less than 0.7 (70%) (implied to be an insufficient level)	0.69 with lower 95% CI of 0.648. This was less than the pre-selected acceptance criteria of 0.7, indicating that identification of feeding vessels using CBCT alone may not be consistent for different readers, thereby highlighting EmboGuide's comparative advantage in consistency.
Comparison to CBCT for Identifying Feeding Vessels (Sensitivity)	EmboGuide should provide higher sensitivity than CBCT	EmboGuide in normal clinical practice: Higher sensitivity to identify feeding vessels compared to CBCT. EmboGuide AFD alone: Higher sensitivity to identify feeding vessels compared to CBCT.

2. Sample Size Used for the Test Set and Data Provenance:

Sample Size: The clinical validation study was based on a retrospective image collection of 63 patients. Within this, 44 subjects were included in the study, and 19 were excluded. This means the test set comprised data from 44 subjects.
Data Provenance: The data was collected retrospectively. The patients were located outside the United States.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications:

Number of Experts: Two experienced interventional radiologists established the ground truth.
Qualifications: They were described as "experienced interventional radiologists" who also performed the procedures. Specific years of experience are not mentioned.

4. Adjudication Method for the Test Set:

The ground truth was established by consensus of two experienced interventional radiologists. This implies a form of consensus adjudication (e.g., 2/2 agreement, or discussion until agreement is reached).

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, what was the effect size of how much human readers improve with AI vs without AI assistance:

Yes, a multi-reader study was performed. It involved three independent interventional radiologists determining feeding vessels.
The study compared EmboGuide AFD alone, EmboGuide used in normal clinical practice (human-in-the-loop, adding/deleting vessels), and CBCT (without EmboGuide assistance).
The effect size of human readers improving with AI assistance (EmboGuide AFD and EmboGuide in clinical practice) vs. without AI assistance (CBCT alone) is indicated by:
- Higher sensitivity: EmboGuide (AFD alone and clinical practice) provided higher sensitivity for identifying feeding vessels compared to CBCT. Specific numerical effect size for this improvement is not given, only the qualitative statement "higher sensitivity."
- Higher Inter-Reader Agreement:
  - EmboGuide AFD alone showed exceptionally high agreement (0.99).
  - EmboGuide in clinical practice showed agreement greater than 0.7.
  - CBCT alone showed lower agreement (0.69), which was below the acceptance criterion.
- This implies that EmboGuide significantly improves consistency among readers.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:

Yes, the performance of "EmboGuide AFD alone" was evaluated. This represents the algorithm's standalone performance in identifying feeding vessels.

7. The Type of Ground Truth Used:

The ground truth was established by expert consensus (two experienced interventional radiologists) based on "all available information (2D angiography, MR and /or CT, Cone Beam CT (CBCT) and EmboGuide)". This is a form of clinical expert opinion/reference standard.

8. The Sample Size for the Training Set:

The document does not provide information regarding the sample size for the training set. The clinical validation study is described as based on a "retrospective image collection," and the focus is on testing the performance, not on training data.

9. How the Ground Truth for the Training Set Was Established:

As the document does not provide information about the training set, it also does not describe how the ground truth for any training set was established.

Summary

{0}------------------------------------------------

Food and Drug Administration 10903 New Hampshire Avenue Document Control Center - WO66-G609 Silver Spring, MD 20993-0002

January 30, 2015

Philips Medical Systems Nederland B.V. % Ms. Liselotte Kornmann Regulatory Affairs Manager Veenpluis 4-6 Best, 5684 PC THE NETHERLANDS

Re: K142273

Trade/Device Name: EmboGuide Regulation Number: 21 CFR 892.1650 Regulation Name: Image-intensified fluoroscopic x-ray system Regulatory Class: II Product Code: OWB, LLZ, JAK Dated: December 16, 2014 Received: January 12, 2015

Dear Ms. Kornmann:

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. 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 (reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

{1}------------------------------------------------

If you desire specific advice for your device on our labeling regulation (21 CFR Part 801), please contact the Division of Industry and Consumer Education at its toll-free number (800) 638 2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/Resourcesfor You/Industry/default.htm. 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

http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

You may obtain other general information on your responsibilities under the Act from the Division of Industry and Consumer Education at its toll-free number (800) 638-2041 or (301) 796-7100 or at its Internet address

http://www.fda.gov/MedicalDevices/ResourcesforYou/Industry/default.htm.

Sincerely yours,

Robert A Ochs

Robert Ochs. Ph.D. Acting Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known)

K142273

Device Name

EmboGuide

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)

2 Prescription Use (Part 21 CFR 801 Subpart D)

Over-The-Counter Use (21 CFR 801 Subpart C)

PLEASE DO NOT WRITE BELOW THIS LINE - CONTINUE ON A SEPARATE PAGE IF NEEDED.

FOR FDA USE ONLY

Concurrence of Center for Devices and Radiological Health (CDRH) (Signature)

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

510(k) Summary of Safety and Effectiveness

This 510(k) summary of safety and effectiveness information is prepared in accordance with 21 CFR §807.92.

Date Prepared:	December 16, 2014
Manufacturer:	Philips Medical Systems Nederland B.V.Veenpluis 4-65684 PC BestThe NetherlandsEstablishment Registration Number: 3003768277
Contact Person:	Mr. Hans VeningsDirector of Regulatory AffairsPhone: +31 611348827E-mail: hans.venings@philips.com
Device:	Trade Name:	EmboGuide
	Device Name:	EmboGuide Rel. 1.0
	Classification Name:	Image-intensified fluoroscopic x-ray system
	Classification Regulation:	21CFR §892.1650
	Classification Panel:	Radiology
	Device Class:	Class II
	Primary Product Code:Secondary Product Code:	OWB (Interventional x-ray system)LLZ (system, image processing, radiological),JAK (system, x-ray, tomography, computed)
Primary PredicateDevice:	Trade Name:	3D Roadmap Rel. 1
	Manufacturer:	Philips Medical Systems Nederland B.V.
	510(k) Clearance:	K121772 (March 21, 2013)
	Classification Regulation:	21 CFR, Part 892.1650
	Classification Name:	Image-intensified fluoroscopic x-ray system
	Classification Panel:	Radiology
	Device Class:	Class II
	Primary Product Code:Secondary Product Code:	OWB (Interventional x-ray system)LLZ (system, image processing, radiological),JAK (system, x-ray, tomography, computed)

{4}------------------------------------------------

Image /page/4/Picture/0 description: The image shows the word "PHILIPS" in a bold, sans-serif font. The color of the text is a medium blue. The background is white, providing a clear contrast that makes the brand name easily visible.

Reference Device:	Trade Name:Manufacturer:510(k) Clearance:Classification Regulation:Classification Name:Classification Panel:Device Class:Product Code:	FlightPlan for LiverGE HealthcareK121200 (November 2, 2012)21 CFR, Part 892.2050Picture Archiving and Communications SystemRadiologyClass IILLZ
Device description:	EmboGuide is a post processing software medical device intended to assistphysicians in performing embolization of hypervascular tumors in the liver usinginterventional X-ray. EmboGuide is an extension of XperCT and intended to beused in combination with an Allura interventional X-ray system. Like theprimary predicate device 3D Roadmap, EmboGuide adds specific functionalityto the Allura system but does not change the overall intended use of the Allurasystem or the overall risk profile.EmboGuide uses a 3D volume reconstructed from 3D rotational angiographyimages acquired on the Allura X-ray system and the segmentation of lesions onpreviously acquired CT, MR or XperCT datasets as input data for the planning ofthe embolization. The physician can use this input data to analyze the vasculatureof lesions, and to identify and annotate the blood vessels that shall be embolized(feeding vessels). The real-time overlay and registration of the 3D volume on live2D X-ray images from the Allura X-ray system of the same anatomy can be usedas additional 3D image guidance to support the navigation of the device/catheter.Planning data, like the earlier annotated feeding vessels and/or 3D landmarks canbe displayed on 2D-3D fused images as supporting information.
Indications for Use:	EmboGuide is a post processing software medical device intended to assistphysicians in performing embolization of hypervascular tumors in the liver usinginterventional X-ray. It provides tools to help the user with the analysis of 3Drotational angiography images. Its output is intended as an adjunct means tohelp with the planning and guidance of the embolization procedure. It providesreal time overlay of 3D rotational angiography images on live 2D X-ray imagesof the same anatomy to support device/catheter guidance.EmboGuide has similar indications for use as its primary predicate device 3DRoadmap:Similar to 3D Roadmap, EmboGuide is a supportive tool to help thephysician with performing an interventional procedure on the Allura X-rayXper system.Similar to 3D Roadmap, EmboGuide provides the real time overlay of 3Drotational angiography images on live 2D X-ray images of the same anatomyto support device/catheter guidance.
•	Both EmboGuide and 3D Roadmap are extensions of the Allura interventional X-ray system (K133292).
•	Both EmboGuide and 3D Roadmap use 3D volumes reconstructed from 3D rotational angiography images as input.
•	Both EmboGuide and 3D Roadmap provide the overlay of 3D volume on live fluoroscopic images acquired from the Allura X-ray system.
•	Both EmboGuide and 3D Roadmap provide dynamic update to changes of the position of the X-ray equipment; the 3D volume is automatically adjusted to any gantry changes and any lateral or longitudinal table movements.
•	EmboGuide provides additional functionality to assist the clinical user with identifying arteries that are feeding into hypervascular tumors and to plan for the embolization treatment of these tumors. This is functionality to further support the clinician in performing interventions and does not raise new questions related to safety and effectiveness. Furthermore, the scientific method is comparable to reference device FlightPlan for Liver which also implements an algorithm for detecting vessels leading to a lesion.
Summary of Non-clinical Performance Data:	Non-clinical performance testing has been performed on EmboGuide and demonstrates compliance with the following International and FDA-recognized consensus standards and FDA guidance document:
•	IEC 62304 Medical device software – Software life cycle processes (Ed. 1.0, 2006),
•	IEC 62366 Medical devices – Application of usability engineering to medical devices (Ed. 1.0, 2007),
•	ISO 14971 Medical devices – Application of risk management to medical devices (Ed. 2.0, 2007),
•	NEMA PS 3.1-3.20 Digital Imaging and Communications in Medicine (DICOM) Set (2011), and
•	Guidance for Industry and FDA Staff – Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices" (issued May 11, 2005, document number 337).
	Verification and validation tests have been performed to address intended use, the technical claims, requirement specifications and the risk management results. The test results in this 510(k) premarket notification demonstrate that

{5}------------------------------------------------

Image /page/5/Picture/0 description: The image shows the word "PHILIPS" in a bold, sans-serif font. The color of the text is a medium blue. The letters are evenly spaced and fill most of the frame. The background is white.

Technological characteristics:

EmboGuide employs the same fundamental scientific technology as its primary predicate device 3D Roadmap.

EmboGuide:

complies with the aforementioned international and FDA-recognized ● consensus standards and FDA guidance document, and
. meets the acceptance criteria and is adequate for its intended use.

{6}------------------------------------------------

Image /page/6/Picture/0 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 plain white, which makes the blue letters stand out.

Summary of Clinical Performance Data:

Clinical testing of EmboGuide included an initial reading study to validate the user interaction in the embolization planning workstep and a clinical validation study to validate the correctness and consistency of EmboGuide to identify feeding vessels leading to previously segmented lesions. Substantial equivalence was based in part on the clinical validation study of the EmboGuide software. Clinical Validation Study

The clinical validation study of EmboGuide was based on a retrospective image collection of 63 patients (outside the United States) and included a prospective review of randomized images; 44 subjects were included in the study and 19 were excluded. First, feeding vessels of the lesions were defined by consensus of two experienced interventional radiologists (located outside the United States) who also performed the procedures by using all available information (2D angiography, MR and /or CT, Cone Beam CT (CBCT) and EmboGuide). This was used as the "ground truth". Another three independent interventional radiologists (located out- and inside the United States) determined the feeding vessels based on CBCT, EmboGuide automatic feeder detection (AFD) and by subsequent review i.e., adding and deleting feeding vessels. Finally, the "ground truth" was compared with the determination of feeding vessels by the three independent readers for CBCT, EmboGuide AFD alone, and EmboGuide used in normal clinical practice (i.e., adding or removing vessels). The performance of EmboGuide was evaluated by the sensitivity. The study also evaluated whether consistent results could be obtained across multiple users. The study showed that:

the sensitivity of EmboGuide in clinical routine use for identification of . tumor feeding vessels is 83+/- 8% with a CI of 95% for HCC patients with diagnostic quality CBCT images and no tumors or feeding vessels outside the volume imaged with CBCT.
. EmboGuide as it will be used in normal clinical practice provides for a higher sensitivity to identify feeding vessels compared to CBCT,
EmboGuide AFD alone provides for a higher sensitivity to identify feeding vessels compared to CBCT,
. the overall agreement among readers for identification of feeding vessels using both the EmboGuide AFD and EmboGuide as it will be used in clinical practice was greater than the pre-selected acceptance criteria of 0.7 (i.e., 70%) indicating that for both approaches results in a consistent identification of feeding vessels for different readers,
. the agreement among readers for identification of feeding vessels using the EmboGuide AFD alone was close to one (i.e., 0.99 with the lower bound of the 95% CI of 0.986), and
the overall agreement among readers for identification of feeding vessels using the CBCT (i.e., 0.69 with lower 95%CI of 0.648) was less than the preselected acceptance criteria of 0.7 (i.e., 70%) indicating that identification of feeding vessels using this method may not be consistent for different readers.

The clinical performance data as documented in the clinical validation study demonstrate that EmboGuide performs comparably to the reference device FlightPlan for Liver that is currently marketed.

{7}------------------------------------------------

Image /page/7/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 word is centered and takes up most of the frame. The background is plain white.

Substantial Equivalence Conclusion:

Based on the information and comparison presented in the aforementioned sections, the proposed EmboGuide Rel. 1.0 software medical device is considered substantially equivalent to the currently marketed predicate device: 3D Roadmap, in terms of design features, fundamental scientific technology, indications for use, and safety and effectiveness.

For specific functionality to assist the clinical user in analyzing the 3D images of the vascular tree to plan for the embolization treatment, EmboGuide Rel. 1.0 is comparable to the currently marketed reference device FlightPlan for Liver. The (non-)clinical performance tests provided in this 510(k) premarket notification demonstrates that the proposed EmboGuide Rel. 1.0 is as safe and effective as its predicate device without raising any new safety and/or

effectiveness concerns

Regulation Number and Section

§ 892.1650 Image-intensified fluoroscopic x-ray system.

(a)
Identification. An image-intensified fluoroscopic x-ray system is a device intended to visualize anatomical structures by converting a pattern of x-radiation into a visible image through electronic amplification. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). An anthrogram tray or radiology dental tray intended for use with an image-intensified fluoroscopic x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9. In addition, when intended as an accessory to the device described in paragraph (a) of this section, the fluoroscopic compression device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.