K Number
K120135
Date Cleared
2012-04-13

(87 days)

Product Code
Regulation Number
892.2050
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The clinical application package 2D Cardiac Performance Analysis MR is indicated for cardiac quantification based on digital magnetic resonance images. It provides measurements of myocardial function (displacement, velocity and strain) that is used for clinical diagnosis purposes of patients with suspected heart disease.

Device Description

2D Cardiac Performance Analysis MR (=2D CPA MR) is a clinical application package for high performance PC platforms based on Microsoft® Windows® operating system standards. 2D CPA MR is a software for the analysis, storage and retrieval of digitized magnetic resonance (MR) images.
The data can be acquired by cardiac MR machines. The digital 2D data can be used for comprehensive functional assessment of the myocardial function.
2D CPA MR is designed to run with a TomTec Data Management Platform (Image-Arena™, their derivatives or any other platform that provides and supports the Generic CAP Interface. The Generic CAP Interface is used to connect clinical application packages (=CAPs) to platforms to exchange digital medical data.
The TomTec Data Management Platform enhances the workflow by providing the database, import, export and other advanced high-level research functionalities.
2D CPA MR is designed for the 2-dimensional functional analysis of myocardial deformation. Based on two dimensional datasets a feature tracking algorithm supports the calculation of a 2D contour model that represents the endocardial and epicardial border. From these contours the corresponding velocities, displacement and strain can be derived.

AI/ML Overview

Here's an analysis of the acceptance criteria and study information for the 2D Cardiac Performance Analysis MR 1.0 device, based on the provided text:

1. Acceptance Criteria and Reported Device Performance

The provided 510(k) summary does not explicitly state quantitative acceptance criteria (e.g., specific accuracy thresholds, sensitivity, or specificity values). Instead, the acceptance criteria appear to be qualitative, focusing on equivalence to predicate devices and confirmation through internal testing and literature review.

Acceptance Criteria (Implicit from the document):

  • Safety and Effectiveness: The device must be as safe and effective as the predicate devices.
  • Performance Equivalence: The device must perform as well as or better than the predicate devices regarding myocardial function analysis (displacement, velocity, strain, strain rate).
  • Clinical Acceptance: The overall product concept must be clinically accepted.
  • Risk-Benefit Assessment: The benefit of using the device must be superior to the risk (with risk being low).
  • Published Data Relevance: Published data must be relevant and applicable to the device characteristics and intended medical procedure.
  • Claim Substantiation: Claims made in the device labeling must be substantiated by clinical data.
  • Software Verification: All software requirements are tested and meet required pass/fail criteria.

Reported Device Performance:

Acceptance Criteria (Implicit)Reported Device Performance
As safe and effective as predicate devices."The conclusion states that: ... The overall product concept was clinically accepted and the clinical test results support the conclusion that the Subject Device is as safe as effective, and performs as well as the Predicate Devices."
"Test results support the conclusion, that the Subject Device is as safe as effective, and performs as well as or better than the Predicate Devices."
Performs as well as or better than predicate devices regarding myocardial function analysis."The Subject Device provides measurements to analyze the myocardial function on cardiac magnetic resonance images like Predicate Device 1 (K090461) and Predicate Device 2 (K100352)."
"The tracking technology of the Subject Device is sensitive enough to track the grey value patterns of regular MRI, thus eliminating the need of additional acquisition of tagged images, which are usually the basis for Predicate Device 2 (K100352)."
"The tracking of the Subject Device delivers contours of different regions of the myocardium like in Predicate Device 1 (K090461) and Predicate Device 2 (K100352)."
"Based on the tracking results regional measurements like strain can be derived like in Predicate Device 1 (K090461) and Predicate Device 2 (K100352)."
"The 2D feature tracking method based on 2D MR image data is already published. The use is as accurate as standard procedures such as HARP (for MR) or 2D speckle tracking (for echo) and it is feasible for clinical practice."
Overall product concept is clinically accepted."The overall product concept was clinically accepted and the clinical test results support the conclusion that the Subject Device is as safe as effective, and performs as well as the Predicate Devices."
Benefits superior to risks."The Risk-Benefit Assessment shows that the benefit is superior to the risk (whereas the risk is low)."
Published data is relevant and applicable."The clinical evaluation shows that the published data are relevant and applicable to the relevant characteristics of the device under assessment and the medical procedure for which the device is intended."
Claims made in device labeling are substantiated."The claims made in the device labelling are substantiated by the clinical data."
All software requirements are tested and meet required pass/fail criteria (Non-clinical performance)."Test results meet the required pass/fail criteria."
"All software requirements are tested or otherwise verified."

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

The document refers to "clinical performance data testing" and a "clinical evaluation following the literature route." However, it does not specify a sample size for a dedicated test set in the traditional sense of a clinical trial. Instead, it relies on a review of published literature and a comparison to predicate devices.

  • Sample Size: Not specified for a dedicated test set. The clinical evaluation was based on a "literature route."
  • Data Provenance: Not explicitly stated (e.g., country of origin). The data provenance is implied to be from published literature. The study is retrospective in the sense that it reviews existing published data.

3. Number of Experts and Qualifications for Ground Truth

The document does not specify the number or qualifications of experts used to establish ground truth for a test set. Since the clinical evaluation relied on a literature review, the "ground truth" would implicitly come from the studies and methods described in the published literature, which would have their own expert-derived ground truths.

4. Adjudication Method for the Test Set

As there is no described dedicated "test set" with expert review for adjudication, no adjudication method is mentioned or applicable in the context of this 510(k) summary.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study is described that measures how much human readers improve with AI vs. without AI assistance. The submission focuses on the standalone performance of the device and its comparability to predicate devices and established techniques, not on human-in-the-loop performance.

6. Standalone (Algorithm Only) Performance Study

Yes, a standalone performance assessment was done. The document states:

  • "The 2D feature tracking method based on 2D MR image data is already published. The use is as accurate as standard procedures such as HARP (for MR) or 2D speckle tracking (for echo) and it is feasible for clinical practice."
  • This implies that the algorithm's performance (its accuracy) was evaluated against established "standard procedures" (like HARP for MR) in published literature. While no specific study details are given within this document, the reliance on a "literature route" for clinical evaluation suggests that earlier standalone performance studies of this 2D feature tracking method were reviewed and deemed acceptable.

7. Type of Ground Truth Used

The type of ground truth is indirectly pathology or expert consensus, derived from the "standard procedures" used in the referenced literature. The document notes that the device is "as accurate as standard procedures such as HARP (for MR)." The ground truth for these standard procedures typically comes from:

  • Expert Consensus/Manual Contours: For imaging-based measurements, manual contouring by expert clinicians is often the gold standard. The device itself requires a manually drawn contour as a prerequisite for its calculations.
  • Pathology/Outcomes Data: While not directly mentioned for the device's validation, the "diagnostic purposes of patients with suspected heart disease" implies that, ultimately, the clinical utility of the measurements would relate to patient outcomes or confirmed pathology.

8. Sample Size for the Training Set

The document does not specify a sample size for any training set. Given that the core technology (2D feature tracking) is described as "already published," it's highly probable that such a method would have been developed and trained using various datasets. However, these details are not provided in this 510(k) summary.

9. How Ground Truth for the Training Set Was Established

Since no training set is described, the method for establishing its ground truth is also not provided in this document.

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).