(9 days)
MIStar is a software package that provides manipulation, visualization and processing of medical images in a diagnostic imaging setting. It allows transfer of DICOM 3.0 images over a medical imaging network, and can receive digital images and data from various sources (including but not limited to CT, MR, NM, and PT).
MIStar supports the analysis of dynamic CT and MR images acquired during and after the injection of a compact bolus of contrast media. It allows visual inspection of time intensity curves and calculation of parametric parameters (i.e., area under curve, time to peak, maximum slope of enhancement, etc). It also calculates various blood perfusion related parameters such as blood flow (BF), blood volume (BV), mean transit time (MTT) and capillary permeability from dynamic CT images. This software provides supplemental information to those images extracted from CT and MR temporal datasets and will aid in the assessment of the extent and type of perfusion, blood volume and capillary permeability changes related but not limited to stroke or tumor angiogenesis and be helpful in therapy monitoring.
MIStar is intended to be used by trained medical professionals, including but not limited to licensed radiologists, technologists and clinicians, and for the rendering clinical diagnosis.
MIStar is a software package, which runs on an Intel-based PC platform. It allows manipulation, visualization and processing of medical images acquired with various clinical scanners and stored in DICOM and for other proprietary formats. MIStar allows transfer of DICOM 3.0 images over a medical imaging network.
MIStar also provides post-processing of dynamic CT and MR images acquired during and after the injection of a compact bolus of contrast media, where the contrast media acts as a pure intravascular tracer. It allows visual inspection of time intensity curves and calculation of parameters (i.e., area under curve, time to peak, maximum slope of enhancement, etc). It also allows calculation of various perfusion related parameters (i.e. regional blood flow, regional blood volume, mean transit time and capillary permeability) from dynamic CT data. The results are displayed in a user-friendly graphic format as parametric images that provide supplementary information for diagnosis purposes.
The provided document does not contain specific acceptance criteria or a study demonstrating the device meets such criteria.
The document K043350 is a 510(k) premarket notification for the MIStar device, which is a software package for manipulating, visualizing, and processing medical images, particularly for analyzing dynamic CT and MR images to calculate perfusion-related parameters.
Here's what can be inferred from the provided text, and what information is missing:
1. Table of Acceptance Criteria and Reported Device Performance:
- Acceptance Criteria: Not specified in the document. The submission focuses on demonstrating substantial equivalence to predicate devices rather than meeting predefined performance acceptance criteria.
- Reported Device Performance: Not explicitly stated as a table of performance metrics. The document mentions that the algorithms used are "similar to" predicate devices, but no quantitative performance data (e.g., accuracy, sensitivity, specificity for perfusion parameter calculation) is provided.
2. Sample Size Used for the Test Set and Data Provenance:
- Test Set Sample Size: Not mentioned. No specific test set for evaluating the device's performance is described.
- Data Provenance: Not mentioned.
3. Number of Experts Used to Establish Ground Truth and Qualifications:
- Number of Experts: Not mentioned.
- Qualifications of Experts: Not mentioned.
- Ground Truth Establishment: No information on how ground truth would be established for any performance evaluation.
4. Adjudication Method:
- Adjudication Method: Not mentioned, as no study involving expert interpretation or adjudication is described.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- MRMC Study: No MRMC comparative effectiveness study is mentioned. The document primarily focuses on establishing substantial equivalence based on functional similarity to predicate devices. There is no information about human readers improving with or without AI assistance, as the device itself is a post-processing tool.
6. Standalone (Algorithm Only) Performance Study:
- Standalone Study: No standalone performance study is mentioned. The document states that the software "requires the intervention of a physician in setting necessary parameters and in assessing resultant images," implying it's not a fully standalone diagnostic algorithm. While it performs calculations, there's no study to evaluate the accuracy of these calculations against a gold standard.
7. Type of Ground Truth Used:
- Type of Ground Truth: Not mentioned. No ground truth is described for any performance evaluation.
8. Sample Size for the Training Set:
- Training Set Sample Size: Not applicable/mentioned. The document describes the software development process as including "verification and validation according to the procedures described in the Software Information section: Software Development Process," but details about training data for any machine learning components (if present, which is not explicitly stated in detail for the core algorithms) are absent. This device predates widespread AI/ML regulatory frameworks.
9. How Ground Truth for the Training Set Was Established:
- Ground Truth for Training Set: Not applicable/mentioned.
Summary of what the document does provide regarding "proof" of meeting criteria:
The "study" presented is a 510(k) Premarket Notification whose primary goal is to demonstrate substantial equivalence to legally marketed predicate devices, not to meet specific quantitative performance acceptance criteria with detailed clinical study data as might be expected today for an AI/ML device.
- Comparison with Predicate Devices: The document argues that MIStar is substantially equivalent to:
- Basis for Equivalence:
- Functional Similarity: MIStar provides digital image processing, measurement capabilities, and DICOM communication, similar to the predicate devices.
- Algorithm Similarity: It states that "The algorithms used to calculate parametric parameters are similar to CT perfusion2 and Functool."
- Intended Use: The indications for use are aligned with the capabilities of the predicate devices for image manipulation, visualization, processing, and calculation of perfusion-related parameters.
- Safety: It asserts that the use of MIStar "does not result in any additional potential hazards when compared to predicate devices."
- Software Development and Testing: The document generally states that the "software package was designed, developed, verified and validated according to the procedures described in the Software Information section: Software Development Process." However, these are general assertions of good practice rather than a description of a specific performance study.
In essence, the "proof" described is the regulatory argument for substantial equivalence based on functional and algorithmic similarity to existing cleared devices, rather than a detailed performance study against predefined acceptance criteria for the output of its advanced features (like perfusion parameter calculations).
§ 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).