(22 days)
QLAB Quantification Software is a software application package. It is designed to view and quantify image data acquired on Philips Healthcare ultrasound products.
The QLAB software application is available either as a stand-alone product that can function on a standard PC, a dedicated workstation, and on-board Philips' ultrasound systems. It can be used for the on-line and off-line review and quantification of ultrasound studies. QLAB Quantification software now includes two new plug-in applications: Fetal Heart Navigator (FHN) and Vascular Plaque Quantification (VPO).
The QLAB Quantification Software with Fetal Heart Navigator (FHN) and Vascular Plaque Quantification (VPQ) plug-ins does not contain details about acceptance criteria in the provided documentation, nor does it explicitly state a study that proves the device meets specific performance acceptance criteria. The document states that the QLAB Quantification software with VPO and FHN "did not require clinical studies to support substantial equivalence."
However, based on the non-clinical performance data section, some aspects of the device's validation can be inferred:
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria Category | Specific Criteria (Inferred from text) | Reported Device Performance (Inferred from text) |
|---|---|---|
| Software Design & Development | Adherence to Philips verification and validation processes. | Quality assurance measures applied, including: Risk Analysis, Product Specifications, Design Reviews, Verification & Validation. |
| Safety and Effectiveness | Device is safe and effective and introduces no new risks. | Verification and validation testing concluded that FHN and VPQ are safe and effective and introduced no new risks. |
| Intended Use | Ability to view and quantify image data acquired on Philips Healthcare ultrasound products. | QLAB Quantification Software is designed for this purpose. |
| FHN Functionality | Semi-automated alignment of fetal heart from 4D acquisition; protocol for standard views to reveal common fetal heart anomalies; visualization for standard views. | FHN provides semi-automated alignment and a protocol for standard views. It does not produce quantitative data or measurements. |
| VPQ Functionality | Protocol-driven tools for semi-automated analysis of carotid artery plaques; clinical results include location of max reduction, percentage of stenosis, and plaque volume. | VPQ provides protocol-driven tools for semi-automated analysis, and reports maximum reduction site, percentage of stenosis, and plaque volume. |
| Risk Management | Identification and control of potential design hazards. | A risk assessment was completed, and appropriate steps were taken to control identified risks. |
2. Sample size used for the test set and the data provenance:
- Sample Size: Not specified.
- Data Provenance: Not specified. The document only mentions "on-line and off-line review and quantification of ultrasound studies."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided. The document states that "QLAB Quantification software with VPO and FHN did not require clinical studies to support substantial equivalence." Therefore, expert-established ground truth for a test set, as would be typical for a clinical study, is not detailed.
4. Adjudication method for the test set:
- This information is not provided. As clinical studies were not required, a formal adjudication method for a test set is not described.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No, an MRMC comparative effectiveness study was not done. The document explicitly states that "QLAB Quantification software with VPO and FHN did not require clinical studies to support substantial equivalence." The FHN features are described as tools to guide users, and the VPQ as providing protocol-driven tools for analysis, implying assistance, but no comparative effectiveness study with human readers is reported.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- The FHN and VPQ plug-ins are described as "semi-automated" tools, suggesting a human-in-the-loop component. The document does not describe a standalone algorithm-only performance study.
7. The type of ground truth used:
- The document does not detail specific, independent ground truth used. The validation was based on internal Philips verification and validation processes and quality assurance measures, rather than a comparison to an external and independent "ground truth" such as pathology or outcomes data from clinical studies.
8. The sample size for the training set:
- Not specified. The document does not provide details about a training set for the algorithms within FHN or VPQ.
9. How the ground truth for the training set was established:
- Not specified. Given the lack of information on a training set, the method for establishing its ground truth is also not mentioned.
Summary of Device Validation Approach:
The provided information indicates that the QLAB Quantification Software with FHN and VPQ was cleared through a 510(k) pathway by demonstrating substantial equivalence to predicate devices, and internal "verification and validation processes" were deemed sufficient. This means that a comprehensive clinical study with specific acceptance criteria, external test sets, expert ground truth, or MRMC studies was not required for its market clearance. The focus was on ensuring the software functioned as intended and did not introduce new risks, aligning with established internal product development and quality assurance procedures.
§ 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).