CAAS Workstation is a modular software product intended to be used by or under supervision of a cardiologist or radiologist in order to aid in reading, co-registering and interpreting cardiovascular X-Ray images to support diagnoses and for assistance during intervention of cardiovascular conditions.

CAAS Workstation features segmentation of cardiovascular structures, 3D reconstruction of vessel segments and catheter path based on multiple angiographic images, measurement and reporting tools to facilitate the following use:

Calculate the dimensions of cardiovascular structures;
Quantify stenosis in coronary and peripheral vessels;
Quantify the motion of the left and right ventricular wall;
Perform density measurements;
Determine C-arm position for optimal imaging of cardiovascular structures;
Enhance stent visualization and measure stent dimensions;
Quantify pressure drop in coronary vessels;
Co-registration of angiographic X-Ray images with IVUS and OCT images.
CAAS Workstation is intended to be used by or under supervision of a cardiologist or radiologist.

Device Description

The CAAS Workstation is designed as a stand-alone software package to run on a PC with a Windows operating system. It can read DICOM X-ray images from an directory, or received from the X-ray or PACS system. Intravascular images (such as intravascular ultrasound (IVUS) and optical coherence tomography (OCT) in DICOM format can be read from a directory, or received from the intravascular imaging console or PACS system. IVUS images can also be received realtime as a video stream from an intravascular imaging console via a DVI streamer. The CAAS Workstation product has a moderate level of concern.

CAAS Workstation is composed out of the following analysis workflows: QCA, QCA3D, QVA, LVA, RVA, StentEnhancer and IV-LINQ of the previously cleared predicate device CAAS Workstation (K151780) for calculating dimensions of coronary and peripheral vessels and the left and right ventricles, quantification of stenosis, performing density measurements, determination of optimal C-arm position for imaging of vessel segments and functionality to enhance the visualization of a stent and to measure stent dimension. Semi-automatic contour detection forms the basis for the analyses. Functionality to co-register X-ray angiographic imaging techniques (such as IVUS and OCT) is added by means of the analysis module IV-LINQ.

In the newly added vFFR workflow the user can calculate the pressure drop and a vFFR value on coronary vessels. To obtain these values for a specific lesion in a coronary vessel, the user has to start with a QCA3D detection using two angiographic images. In each of these images a classic 2D coronary detection is performed after which a reconstruction of the coronary segment is obtained in 3D space. Based on the 3D reconstruction and the user input of systolic and diastolic aortic root blood pressure drop and the vFFR values can be assessed. The functionality is based on a combination of the QCA3D workflow available in predicate device CAAS Workstation (K151780) and technology available in the predicate device CAAS (K052988).

Results can be displayed on the screen, printed or saved in a variety of formats to hard disk, network, PACS system or CD. Results and clinical images with overlay can also be printed as a hardcopy and exported in various electronic formats. The functionality is independent of the type of vendor acquisition equipment.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in a quantitative table format for the new "quantification of pressure drop in coronary vessels" functionality. Instead, it describes a validation approach and comparative analysis.

However, based on the performance data section, we can infer the acceptance criteria for the new "quantification of pressure drop in coronary vessels" module were related to agreement with known pressure drops and improvement compared to the predicate device K052988.

Acceptance Criteria (Inferred)	Reported Device Performance (Quantified/Qualitative)
For existing functions (from K151780): Equivalence in numerical results as demonstrated by regression testing.	Demonstrated with regression testing for equivalence in numerical results.
For new "quantification of pressure drop in coronary vessels" (from K052988 with 3D reconstruction): Agreement between calculated pressure drops and known pressure drops.	Differences (mean and standard deviation) of the calculated pressure drops with respect to known pressure drops of the used datasets were calculated. A Pearson correlation between the known and calculated pressure drop values was also performed.
For new "quantification of pressure drop in coronary vessels": Improvement compared to predicate device K052988.	"This demonstrated that the quantification of pressure drop in coronary vessels in the new CAAS Workstation is improved compared to the predicate device K052988." (No specific quantitative metric for improvement is provided in the document).

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

Test set for existing functions (regression testing): Not explicitly stated, but it's implied that a comprehensive set of test cases was used for regression testing to demonstrate equivalence.
Test set for "quantification of pressure drop in coronary vessels": A "series of X-ray angiographic datasets with known pressure drops" was used. The exact number of datasets is not specified.
Data Provenance: Not explicitly stated, but the mention of "known pressure drops" suggests these were either simulated datasets or pre-adjudicated clinical cases where pressure drops were definitively measured (e.g., using a reference standard). The document does not specify country of origin or whether it was retrospective or prospective.

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

For existing functions: Not stated, as regression testing was used to compare against the previous version of the software.
For "quantification of pressure drop in coronary vessels": The ground truth was based on "known pressure drops." The document does not specify if experts were involved in establishing these "known pressure drops" or what their qualifications would be. It's possible these were derived from a separate reference standard (e.g., invasive pressure wire measurements) or simulated data.

4. Adjudication Method

For existing functions: Not applicable, as regression testing compared against the predicate device's output.
For "quantification of pressure drop in coronary vessels": Not applicable, as the comparison was against "known pressure drops" rather than expert consensus on unknown cases.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, the document does not describe an MRMC comparative effectiveness study involving human readers with and without AI assistance. The performance evaluation focused on the standalone algorithm's accuracy and comparison to a previous device version.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, the performance evaluation for the "quantification of pressure drop in coronary vessels" was a standalone evaluation of the algorithm. The device calculated pressure drops, which were then compared to "known pressure drops."

7. The Type of Ground Truth Used

For existing functions: The ground truth for regression testing would be the output of the predicate device (K151780).
For "quantification of pressure drop in coronary vessels": The ground truth was "known pressure drops." As mentioned, this could refer to measurements from a highly accurate reference standard (e.g., invasive physiological measurements) or carefully constructed simulated data. It does not explicitly state "expert consensus," "pathology," or "outcomes data."

8. The Sample Size for the Training Set

The document does not explicitly state the sample size used for the training set. The description in the "Performance Data" section refers to validation and verification, implying a test set, rather than a training set for model development. The device is described as an "Angiographic X-ray system," implying traditional software rather than a deep learning AI, though modern software often incorporates machine learning components that require training. Given the context, the "known pressure drops" dataset mentioned is very likely the test set used for validation.

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

Since a training set size is not provided, the method for establishing its ground truth is also not elaborated upon in the provided text. If the device uses machine learning, information on its training set and ground truth establishment would typically be found in a more detailed technical report.

Summary

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

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and 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.

May 23, 2019

Pie Medical Imaging B.V. % Annemiek Bouts Regulatory Affairs Coordinator Philipsweg 1 6227 AJ Maastricht, Limburg THE NETHERLANDS

Re: K180019

Trade/Device Name: CAAS Workstation Regulation Number: 21 CFR 892.1600 Regulation Name: Angiographic x-ray system Regulatory Class: Class II Product Code: QHA, LLZ Dated: March 28, 2018 Received: April 2, 2018

Dear Annemiek Bouts:

This letter corrects our substantially equivalent letter of May 3, 2018.

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

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

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/CombinationProducts/GuidanceRegulatoryInformation/ucm597488.html; 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 http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). 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 (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

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) K180019

Device Name CAAS Workstation

Indications for Use (Describe)

· Calculate the dimensions of cardiovascular structures;
· Quantify stenosis in coronary and peripheral vessels;
· Quantify the motion of the left and right ventricular wall;
· Perform density measurements;
· Determine C-arm position for optimal imaging of cardiovascular structures;
· Enhance stent visualization and measure stent dimensions;
· Quantify pressure drop in coronary vessels;
· Co-registration of angiographic X-Ray images with IVUS and OCT images.

CAAS Workstation is intended to be used by or under supervision of a cardiologist.

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

ü 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."

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

510(k) Summary	CAAS Workstation Pie Medical Imaging BV
Submitter/Owner Name	Pie Medical Imaging BV
Address	Philipsweg 1, 6227 AJ Maastricht, The Netherlands
Phone Number	+31 43 32 81 328
Fax Number	+31 43 32 81 329
Contact Person	Annemiek Bouts, Regulatory Affairs Coordinator
Email Address	annemiek.bouts@pie.nl
Preparation Date	23-May-19
Trade Name	CAAS Workstation
Common Name	CAAS (Cardiovascular Angiographic Analysis System)
Classification	Regulation Name: Angiographic X-ray SystemRegulation Class: Class IIRegulation number: 21 CFR 892.1600Classification Product Code: QHASubsequent Product Code: LLZ
Predicate Device	CAAS Workstation (K151780, Angiographic X-ray System, 21 CFR 892.1600, IZI, LLZ)CAAS (K052988, Image Processing System, 21 CFR 892.2050, LLZ)

Device Description

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

Intended Use

Indications for Use

Calculate the dimensions of cardiovascular structures; .
. Quantify stenosis in coronary and peripheral vessels;
. Quantify the motion of the left and right ventricular wall;
Perform density measurements;
Determine C-arm position for optimal imaging of cardiovascular structures;
Enhance stent visualization and measure stent dimensions;
. Quantify pressure drop in coronary vessels;
Co-registration of angiographic X-Ray images with IVUS and OCT images.
CAAS Workstation is intended to be used by or under supervision of a cardiologist or radiologist.

Substantial equivalence

A comparison of the technological characteristics of the predicate and subject device is given the table below.

	New Device	Predicate Device	Predicate Device
Device name	CAAS Workstation	CAAS Workstation	CAAS
Manufacturer	Pie Medical Imaging	Pie Medical Imaging	Pie Medical Imaging
510(k) number	K180019	K151780	K052988
Intended use	Intended Use and Indications for Use
Intended use	CAAS Workstation is a modularsoftware product intended to beused by or under supervision of acardiologist or radiologist in orderto aid in reading, co-registering andinterpreting cardiovascular X-Rayimages to support in diagnoses andfor assistance during interventionof cardiovascular conditions.	CAAS Workstation is a modularsoftware product intended to beused by or under supervision of acardiologist or radiologist in orderto aid in reading, co-registering andinterpreting cardiovascular X-Rayimages to support in diagnoses andfor assistance during interventionof cardiovascular conditions.	The intended use of CAAS is:• Quantification of coronary arterydimensions;• Quantification of peripheralarteries and aorta;• Quantification of left and rightventricles;• Management of data resulting ofthe quantitative analysis.CAAS is used online or offline inhospitals and offline for researchpurposes. In hospitals, the softwarewill be used by cathlab personnelunder supervision of cardiologistsand radiologists. In researchinstitutes, the users are principalinvestigators and other researchpersonnel operating undersupervision of cardiologists andradiologists as well.
Indications foruse	CAAS Workstation featuressegmentation of cardiovascularstructures, 3D reconstruction ofvessel segments based on multipleangiographic images, measurementand reporting tools to facilitate thefollowing use:• Calculate the dimensions ofcardiovascular structures;• Quantify stenosis in coronary andperipheral vessels;• Quantify the motion of the leftand right ventricular wall;• Perform density measurements;	CAAS Workstation featuressegmentation of cardiovascularstructures, 3D reconstruction ofvessel segments based on multipleangiographic images, measurementand reporting tools to facilitate thefollowing use:• Calculate the dimensions ofcardiovascular structures;• Quantify stenosis in coronary andperipheral vessels;• Quantify the motion of the leftand right ventricular wall;• Perform density measurements:	CALCalculate the pixel size of the imageto be analysed.MEASPerform basic length, angle anddensity measurements.QCADetect the contour of the coronaryvessel in the angiographic X-rayimage- Calculate the dimensions of thecoronary artery segment.

	• Determine C-arm position foroptimal imaging of cardiovascularstructures;• Enhance stent visualization andmeasure stent dimensions;• Quantify pressure drop incoronary vessels;• Co-registration of angiographic X-Ray images with IVUS and OCTimages.CAAS Workstation is intended to beused by or under supervision of acardiologist or radiologist.	• Determine C-arm position foroptimal imaging of cardiovascularstructures;• Enhance stent visualization andmeasure stent dimensions;• Co-registration of angiographic X-Ray images with IVUS and OCTimages.CAAS Workstation is intended to beused by or under supervision of acardiologist or radiologist. Whenthe results provided by CAASWorkstation are used in a clinicalsetting to support diagnoses andfor assistance during interventionof cardiovascular conditions, theresults are explicitly not to beregarded as the sole, irrefutablebasis for clinical decision making.	QVADetect the contour of theperipheral vessel in theangiographic X-ray image- Calculate the dimensions of theperipheral vessel segment.LVADelineate the outline of the leftventricular wall automaticallyand/or manually in angiographic X-ray images – either monoplane orbiplane analysis; absolutemeasurements of left ventricularvolumes; calculations of derivedparameters; quantification of themotion of the left ventricular wall;estimations of the dimensions ofthe myocardial wall.RVADelineate the outline of the rightventricular wall semi-automaticallyand/or manually in angiographic X-ray images - either monoplane orbiplane analysis; absolutemeasurements of right ventricularvolumes based on severalestablished models for children andadults; calculations of derivedparameters; quantification of themotion of the right ventricular wall.
		Technological Characteristics
Data type	• X-Ray angiography in DICOMformat (vendor independent);• IVUS and OCT data in DICOMformat (vendor independent);• IVUS data as video stream	• X-Ray angiography in DICOMformat (vendor independent);• IVUS and OCT data in DICOMformat (vendor independent;)• IVUS data as video stream	• X-Ray angiography in DICOMformat (vendor independent);• n/a• n/a
Import of patientdata	• Manual through keyboard;• Command line interface	• Manual through keyboard;• Command line interface	• Manual through keyboard;• Command line interface
Contourdefinition	• Manual and semi-automaticcentreline definition basedcontour detection of coronaryand peripheral vessels;• Manual and semi-automatic leftventricular contour definition;• Manual right ventricular contourdefinition;• Manual stent contour definition;• Contour correction andrestriction;• Manual catheter path definition	• Manual and semi-automaticcentreline definition basedcontour detection of coronaryand peripheral vessels;• Manual and semi-automatic leftventricular contour definition;• Manual right ventricular contourdefinition;• Manual stent contour definition;• Contour correction andrestriction;• Manual catheter path definition	• Manual and semi-automaticcentreline definition basedcontour detection of coronaryand peripheral vessels;• Manual and semi-automatic leftventricular contour definition;• Manual right ventricular contourdefinition;• Manual stent contour definition;• Contour correction andrestriction;• Manual catheter path definition
Image display	• 2D X-ray image;• 3D reconstruction based on 2 X-ray images;• 2D intravascular image;	• 2D X-ray image;• 3D reconstruction based on 2 X-ray images;• 2D intravascular image;	• 2D X-ray image• n/a• n/a• n/a
	reconstruction	reconstruction
Imageassessment	• Manual and automaticcalibration;• Basic length, diameter, densityand angle measurements;• Vessels and ventricle dimensions(diameters, areas, volumes);• Automatic and manual stenosisassessment;• Left and right ventricular wallmotion;• Left ventricular myocardiumdimensions;• Enhanced stent visualization;• Stent dimensions;• Pressure drop calculation incoronary vessels;• Providing common frame ofreference for IVUS and OCT datawith X-ray angiographic data	• Manual and automaticcalibration;• Basic length, diameter, densityand angle measurements;• Vessels and ventricle dimensions(diameters, areas, volumes);• Automatic and manual stenosisassessment;• Left and right ventricular wallmotion;• Left ventricular myocardiumdimensions;• Enhanced stent visualization;• Stent dimensions;• n/a• Providing common frame ofreference for IVUS and OCT datawith X-ray angiographic data	• Manual and automaticcalibration;• Basic length, diameter, densityand angle measurements;• Vessels and ventricle dimensions(diameters, areas, volumes);• Automatic and manual stenosisassessment;• Left and right ventricular wallmotion;• Left ventricular myocardiumdimensions;• n/a• n/a• Pressure drop calculation incoronary vessels (in stenotic flowreserve and hemodynamic datafunctionality);• n/a
Storage of results	• Printout;• Images;• XML;• DICOM SC;• PDF• n/a	• Printout;• Images;• XML;• DICOM SC;• PDF• n/a	• Printout;• Images;• XML;• DICOM SC;• n/a• DICOM SR
Operating system	• Windows	• Windows	• Windows

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

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

The basic features and technology of the new CAAS Workstation are the same in terms of indications for use and have the same technological characteristics as the predicate devices CAAS Workstation (K151780) and CAAS (K052988). The cardiovascular functions supported by the CAAS Workstation of functions provided by the predicate devices K151780 and K052988. All software applications use the same types of data and operating principles for the user and technology regarding data import, contour definition, image display and storage of results.

Performance Data

Verification and validation of the CAAS Workstation showed that the system requirements – derived from the intended use and indications for use – as well as risk control measures were implemented correctly and that the device meets its specifications including conformance to the following standards:

· ISO 14971:2007, Medical devices Application of risk management to medical devices
NEMA PS 3.1 3.20 (2016), Digital Imaging and Communication in Medicine (DICOM)
· IEC 62304 Ed 1.1, 2015-06, Medical device software Software life cycle processes
IEC 62336-1 Ed 1.0 2015-02, Medical devices Application of usability engineering to medical devices

For each analysis workflow in CAAS Workstation approach is created and the proper functioning of the algorithms is validated.

Equivalence in numerical results for the analysis workflows already available in predicate device K151780 was . demonstrated with regression testing.
. To demonstrate a proper integration of the functionality 'quantification of pressure drop in coronary vessels' from predicate device K052988 into CAAS Workstation, a series of X-ray angiographic datasets with known pressure drops were analysed and compared with K052988 and the new CAAS Workstation. The functionality 'quantification of pressure drop in coronary vessels' in the new CAAS Workstation is based on a 3D coronary reconstruction out of 2 angiographic images. In the predicate device K052988, which uses a method based on a single angiographic image, the results were generated for both the angiographic images as used for the 3D reconstruction. The results for the pressure drop were compared and differences (mean and standard deviation) of the calculated pressure drops with respect to known pressure drops of the used datasets were

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

calculated. A Pearson correlation between the known and calculated pressure drop values was also performed. This demonstrated that the quantification of pressure drop in coronary vessels in the new CAAS Workstation is improved compared to the predicate device K052988.

The verification and validation results demonstrate the safety and effectiveness of CAAS Workstation to its intended use and therefore CAAS Workstation can be considered as safe and effective as its predicate devices.

Conclusion

Based on the application of risk management and performance testing inherent to PMI's QA system (compliant with recognized standards as stated above) we conclude that CAAS Workstation is as safe and effective as its predicate devices in terms of intended use, indications for use, technological characteristics, measurements and operating environment and does not raise any new issues related to safety and effectiveness compared to the predicate devices.

Regulation Number and Section

§ 892.1600 Angiographic x-ray system.

(a)
Identification. An angiographic x-ray system is a device intended for radiologic visualization of the heart, blood vessels, or lymphatic system during or after injection of a contrast medium. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.