(60 days)
The iCAD Breast Interventional Planning Software supports the use of interventional breast coils and MR stereotactic localization devices to perform magnetic resonance (MR) guided breast interventional procedures. Using information from MR images regarding the coordinates of a user-specified region of interest, and fiducial coordinates. the software provides an automatic calculation of the location and depth of the targeted region of interest, such as a lesion or suspected lesion relative to the interventional device.
The iCAD Breast Interventional Planning Software (BIPS) is intended to extract certain image information and display them to a user. The software allows the user to select a target lesion in the breast as well as fiducial markers, and get accurate information about the optimal positioning of the biopsy needle or other interventional device, including visualization of the appropriate position, distances and other applicable settings. iCAD's BIPS is a software tool, which can assist the radiologist in planning and performing MRI guidance of percutaneous breast biopsies and other interventional procedures. When interpreted by a skilled physician, this device provides information that may be useful in interventional planning and monitoring.
The BIPS is a DICOM 3.0 compliant post-processing software package for viewing magnetic resonance imaging (MRI) data sets and supporting interventional breast coils and MR stereotactic localization devices when performing MRI-guided breast interventional procedures.
The provided document, K090223, primarily serves as a 510(k) summary for the iCAD Breast Interventional Planning Software. It establishes substantial equivalence to predicate devices and outlines the device's intended use and technological characteristics.
Crucially, this document does not include detailed information about specific acceptance criteria, a standalone performance study with metrics, or an MRMC comparative effectiveness study. The regulatory submission focuses on demonstrating equivalence to previously cleared devices rather than presenting novel performance data against predefined criteria.
Therefore, many of the requested items cannot be extracted directly from this document. However, I can provide the information that is available and highlight what is missing.
1. Table of Acceptance Criteria and Reported Device Performance
This information is not provided in the document. The 510(k) summary states that "Test data was supplied that met the requirements of the Software Test Plan and Software Unit Test Plan," but it does not specify what those requirements (acceptance criteria) were or what the actual test data showed in terms of quantitative performance (e.g., accuracy of calculations, efficiency gains, etc.).
2. Sample Size Used for the Test Set and Data Provenance
This information is not provided in the document. The document mentions "Test data was supplied," but it does not specify the size of the test set or the origin of the data (e.g., country, retrospective/prospective).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
This information is not provided in the document. The document refers to the device assisting a "skilled physician" but does not detail any expert involvement in establishing ground truth for testing.
4. Adjudication Method for the Test Set
This information is not provided in the document.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and the effect size of how much human readers improve with AI vs without AI assistance
This information is not provided in the document. The regulatory submission primarily focuses on the device's technical equivalence and functionality rather than comparative effectiveness studies with human readers.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
A standalone performance study with specific metrics is not explicitly described in the document. The submission states that testing was done to meet software test plan requirements, implying some form of standalone validation of the software's calculations and features, but no detailed performance report is included.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
This information is not provided in the document for any testing.
8. The Sample Size for the Training Set
This information is not provided in the document. Given the description focusing on calculations based on user-selected points and fiducial markers, it's possible the software relies on deterministic algorithms rather than a machine learning model that would require a "training set" in the conventional sense. If machine learning was used, the training set size is not disclosed.
9. How the Ground Truth for the Training Set was Established
This information is not provided in the document. (Please see point 8 regarding the potential absence of a traditional "training set.")
Summary of Device and Regulatory Context (Based on Provided Document):
- Device Name: iCAD Breast Interventional Planning Software (BIPS)
- Purpose: Assists radiologists in planning and performing MRI-guided percutaneous breast biopsies and other interventional procedures. It extracts image information, allows users to select target lesions and fiducial markers, and calculates optimal positioning (location and depth) for interventional devices.
- Regulatory Path: 510(k) Premarket Notification (K090223).
- Predicate Devices: CADstream™ Version 4.0 (Confirma, Inc.), DynaCAD™ V1.0 (MRI Devices Corporation), MICS Intervention Aid (Machnet BV).
- Basis for Clearance: Substantial equivalence to these predicate devices, based on same intended use, principles of operation, and characteristics, with differences primarily in visual interface design that do not raise new questions of safety or efficacy.
- Safety and Effectiveness Concerns Addressed: Risk management via risk analysis, controls through software development, verification, and validation testing.
- Performance Data Mentioned: "Test data was supplied that met the requirements of the Software Test Plan and Software Unit Test Plan." This indicates internal validation, but the details of the performance are not public in this filing.
§ 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).