(34 days)
The QBrain software has been developed for the objective and reproducible analysis of MR images of the brain. It performs quantitative analysis of MR brain images based on automatic segmentation. More specifically, it quantifies the volumes of intracranial cavities, areas that contain cerebrospinal fluid (CSF), and white matter hyperintensities (lesions). These parameters should only be used by trained medical professionals in clinical practice and to reach conclusions in clinical trials.
The QBrain software has been developped for the onalyses on MR brain images of based on automatic segmentation. More specifically, it quantifies the volumes of based on automatic segmentation: more openiture, more openiture (CSF), and white matter hyperintensities (lesions).
The provided text (K050703) describes the QBrain software, which performs automatic quantitative analysis of MR brain images, specifically quantifying the volumes of intracranial cavities, cerebrospinal fluid (CSF), and white matter hyperintensities (lesions).
However, the provided document does not contain information regarding traditional acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds) or a formal study designed to demonstrate performance against such criteria.
Instead, the submission emphasizes substantial equivalence to an existing predicate device (IQuantify workstation software, K011196). The "Summary of Safety and Effectiveness" primarily focuses on the device description, intended use, and a declaration of safety based on internal development, risk analysis, and validation tests. There is no detailed study methodology, test set characteristics, or a table of acceptance criteria with reported performance.
Therefore, I cannot fulfill the request for a table of acceptance criteria and reported performance, sample sizes used, number of experts, adjudication methods, MRMC study details, or standalone performance. The document only implicitly "proves" acceptance by asserting substantial equivalence and stating that "validation and validation tests" were performed, but without detailing their scope or results.
Here's a breakdown of what can be extracted from the provided text based on your questions, with the understanding that robust study details are absent:
1. A table of acceptance criteria and the reported device performance:
- Acceptance Criteria: Not explicitly stated in terms of performance metrics (e.g., accuracy thresholds, sensitivity, specificity). The primary "acceptance" mechanism implied is demonstrating substantial equivalence to a predicate device.
- Reported Device Performance: No specific performance metrics (e.g., percentages, F1 scores, absolute error) are reported in the document.
2. Sample size used for the test set and the data provenance:
- Sample Size (Test Set): Not specified.
- Data Provenance: Not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not specified, as no formal ground truth establishment for a test set is detailed.
- Qualifications of Experts: Not specified.
4. Adjudication method for the test set:
- Adjudication Method: Not specified.
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:
- MRMC Study: Not mentioned or described. The document states a primary use is "quantitative values support the diagnostic and/or therapy response" and "should only be used by trained medical professionals in clinical trials," but does not present a study comparing human performance with and without AI assistance.
- Effect Size: Not applicable, as no MRMC study is described.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Standalone Study: No specific standalone performance study is described or reported with metrics. The device's function is "automatic segmentation," implying standalone capability, but its performance is not quantified.
7. The type of ground truth used:
- Type of Ground Truth: Not specified in detail for any study. The document mentions "mask data, generated by automatic segmentation and/or manual editing" as input for results, but does not clarify how a "ground truth" for evaluating the system's accuracy was established.
8. The sample size for the training set:
- Sample Size (Training Set): Not specified.
9. How the ground truth for the training set was established:
- Ground Truth Establishment (Training Set): Not specified.
Summary based on available information:
The K050703 submission for QBrain primarily relies on demonstrating substantial equivalence to a predicate device (IQuantify workstation software, K011196) rather than providing detailed performance studies with quantitative acceptance criteria, test sets, and ground truth methodologies. The document emphasizes the device's functionality (automatic quantification of brain structures) and its intended use by trained medical professionals in clinical trials, but it lacks the specific data points requested in your prompt regarding detailed study designs and outcomes.
§ 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).