(342 days)
Dynamika Version 5.0 is an image processing software package to be used by trained medical professionals with a level of medical expertise (including physicians, radiology technicians). The software runs on a standard offthe-shelf workstation and can be used to perform image viewing, processing and analysis of medical images. Data and images are acquired through DICOM compliant imaging devices and modalities.
Dynamika Version 5.0 provides both viewing and analysis capabilities of dynamic imaging datasets acquired with MRI.
Dynamika Version 5.0 is used for the visualization, analysis and reporting of dynamic MRI data, showing the properties of changes in contrast over time.
The package may be used to calculate permeability parameters related to the leakage of injected contrast material from intravascular to extracellular space. Parametric maps may be overlaid onto the original image for interpretation.
Dynamika Version 5.0 is intended to be used within hospitals and medical clinics. It is licensed and not intended for general public use.
Dynamika Version 5.0 is a software package for viewing, analysis and processing of medical images from MRI. The software is compliant with the DICOM standard and is suitable for running on Windows, Macintosh or Linux operating systems.
Dynamika Version 5.0 allows the display, analysis and post-processing of medical images.
These images, when interpreted by a trained physician, may yield clinically useful information.
The software provides a range of basic image processing and manipulation functions, in addition to comprehensive dynamic image processing and display.
The main features of the software are:
-
- Image Loading and Saving.
-
- Image Viewing.
-
- Image Manipulation.
-
- Image Analysis.
-
- Imaging Processing and Generation of Parametric Maps.
- Permeability Post-processing. 6.
-
- Reporting of User-Selected Findings and Assessment.
- Communication and Storage of Results (DICOM import/export, 8. query/retrieve and study storage).
Dynamika Version 5.0 is designed for medical imaging professionals with expertise in interpreting medical MRI images. Dynamika Version 5.0 can also be used to view multi-modality, digital images including ultrasound and mammography images. However, the software package is not intended for primary interpretation of digital mammography images.
The document provides a comparison table between the Dynamika Version 5.0 device and its predicate device, Olea Sphere Version 2.3, to demonstrate substantial equivalence, rather than detailing specific acceptance criteria and a study to prove they are met. The information provided is more aligned with demonstrating that the new device has similar characteristics and performs comparably to a legally marketed device.
Based on the provided text, a direct table of acceptance criteria and reported device performance of Dynamika Version 5.0 against defined metrics is not explicitly stated. Instead, the document focuses on comparison to a predicate device for regulatory clearance.
However, I can extract the closest information to what you've requested from the "Summary Table of Key Areas of Demonstration of Substantial Equivalence between the New Device and Legally Marketed Predicate Devices."
Here's an interpretation based on the document's content:
1. A table of acceptance criteria and the reported device performance
The document does not present "acceptance criteria" in the traditional sense of metrics like sensitivity, specificity, or quantitative thresholds for the device's performance. Instead, it demonstrates that the device's features and performance characteristics are substantially equivalent to a predicate device.
Table: Comparison of Dynamika Version 5.0 to Predicate Device (Olea Sphere Version 2.3)
| Feature or Specification of the Device | Dynamika Version 5.0 (Target Device) | Predicate Device (Olea Sphere Version 2.3) |
|---|---|---|
| Intended Use – General Purpose | Image processing software package to be used by trained medical professionals (physicians, radiographers, radiology technicians) for viewing, processing, and analysis of medical images acquired through DICOM compliant devices. Provides viewing and analysis capabilities of dynamic imaging datasets acquired with MRI. Used for visualization, analysis, and reporting of dynamic MRI data, showing changes in contrast over time. May calculate permeability parameters related to contrast leakage (intravascular to extracellular space) with parametric maps overlaid for interpretation. Intended for use in hospitals and medical clinics, not for general public use. | Image processing software package to be used by trained professionals (physicians, medical technicians) for viewing, processing, and analysis of medical images acquired through DICOM compliant devices. Provides viewing and analysis capabilities of functional and dynamic imaging datasets acquired with MRI or other relevant modalities, including a Diffusion Weighted MRI (DWI)/Fibre Tracking Module and a Dynamic Analysis Module (dynamic contrast imaging data for MRI and CT). Visualization and analysis of dynamic imaging data, showing changes in contrast over time. Includes modules for Perfusion and Permeability (calculation of parameters related to tissue flow/perfusion and tissue blood volume; calculation of parameters related to leakage of injected contrast material from intravascular to extracellular space). Intended for use in hospitals and medical clinics, not for general public use. When interpreted by a skilled physician, provides information that may be used for screening, diagnosis, and interventional planning. Patient management decisions should not be based solely on results. The DWI/Fiber Tracking Module is designed to track white matter within the brain and the nervous system. |
| Principles of Operation | Image processing software package to allow viewing and analysis of dynamic MRI scans (DICOM files), providing measurements and statistics associated with contrast agent use in MRI, and analyzing signal intensity changes over time in different tissues. Corrects for patient motion and creates subtractions and multiplanar formats. Dynamic analysis functionality for visualization and analysis of dynamic imaging (contrast changes over time), including dedicated analysis methods and visualization tools for dynamic contrast-enhanced imaging data (DCE-MRI) to calculate functional parameters related to tissue perfusion and tissue blood volume (permeability) of injected contrast material. | Comprehensive functionality for dynamic image analysis and visualization where signal changes over time are analyzed to determine various modality-dependent functional parameters. Provides viewing and analysis capabilities of functional and dynamic imaging datasets acquired with MRI or other relevant modalities, including DWI/Fiber Tracking and Dynamic Analysis. Modules include DWI/Fibre Tracking (visualizing local water diffusion properties, fiber tracking for white matter structure) and Dynamic Analysis (visualization and analysis of dynamic imaging for contrast changes over time, including Perfusion and Permeability modules). |
| Environment of Use | Within hospitals and medical clinics. Licensed, not for general public use. | Within hospitals and medical clinics. Licensed, not for general public use. |
| Limitations of Use | Not intended for primary interpretation of mammography images. | Not intended for primary interpretation of mammography images. |
| Performance Characteristics: Image Analysis | Supports qualitative and quantitative analysis of certain features in an image or set: Region of interest (ROI) analysis; Segmentation of volumes of interest via region growing method and manual delineation; Image subtraction; Patient Motion Correction. | Supports qualitative and quantitative analysis of certain features in an image or set: Volume of interest (VOI) analysis; Segmentation of volumes of interest via region growing method, manual delineation, and region-based volume segmentation; Histogram normalization; Image subtraction; Patient Motion Correction. |
| Performance Characteristics: Permeability | State-of-the-art kinetic modeling with vascular deconvolution algorithm. Parametric Map Generation: Maximum Enhancement (ME), Time of Onset of Enhancement (Tonset), Initial Rate of Enhancement (IRE), Time to Peak Enhancement (TTP), Time of Washout (Twashout), Initial Rate of Washout (IRW), Area under the curve (AUC). Kinetic modeling with quantitative pixel-by-pixel analysis. Generation of permeability maps using signal conversion based on relative signal enhancement: Initial area under the Gd concentration curve (iAUGC60), Ktrans, Ve, Vp. T1-mapping allows loading additional MRI sequences for signal conversion into concentration values. | State-of-the-art kinetic modeling with vascular deconvolution algorithm. Generation of permeability maps using signal conversion based on relative signal enhancement or T1 mapping: AUC, Peak enhancement (PEAK), Initial up-slope (Washin), Down slope (Washout), Time to Peak enhancement (TTP), Peak Percentage Enhancement (PEAK_ENHANCEMENT), Relative washout (CURVE_WASHOUT), Signal Enhancement Ratio (SER). Ktrans, Kep, Ve, Vp, T10. T1-mapping allows loading additional MRI sequences for signal conversion into concentration values. Permeability Algorithms: (T1 mapping) Estimation of pre-contrast T1 map from additional MR sequences. |
| Voluntary Standards | Yes, DICOM Compliant. | Yes, DICOM Compliant. |
| Reporting | User customized reporting. DEMRIQ parameters. | User customized reporting. |
Study to prove device meets acceptance criteria:
The document describes "extensive verification and validation testing" conducted for the Dynamika Version 5.0 system. This included:
- Product Risk Assessment.
- Software verification and validation testing, covering algorithm (unit) level testing, integration, and system functional testing.
The document states that the testing ensured the system "provides the capabilities to operate safely and effectively according to its intended use." It also notes compliance with the FDA recommended voluntary NEMA DICOM safety standard for PACS.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document does not provide details on the sample size used for any test set or the provenance of data. It only broadly mentions "extensive verification and validation testing."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
The document does not provide any information about experts used to establish ground truth or their qualifications. Since no clinical testing was performed (see point 5), it's unlikely that expert-adjudicated ground truth for clinical performance was established.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
The document does not specify any adjudication method.
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 clinical testing or MRMC study was done. The document explicitly states: "No clinical testing was used to demonstrate substantial equivalence between Dynamika Version 5.0 and the predicate device (Olea Sphere Version 2.3) as these types of devices have been on the market for many years with proven safety and efficacy of use. Therefore, the non-clinical testing detailed within the submission supports the substantial equivalence of this device." This implies no human-in-the-loop performance studies or effect size measurements were conducted.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document mentions "algorithm (unit) level testing" as part of software verification and validation. While this implies standalone testing of the algorithm components, it does not provide specific performance metrics or a detailed study description for such testing. The focus of the submission is substantial equivalence to a predicate PACS device, rather than a novel AI algorithm requiring standalone diagnostic performance validation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the non-clinical testing, the "ground truth" would likely be based on engineering specifications and expected software behavior, verified through unit, integration, and system functional testing. Given the context of PACS and image processing, it would involve confirming that calculations are correct, images are displayed accurately, and features function as designed against known inputs, rather than clinical ground truth from pathology or expert consensus.
8. The sample size for the training set
The document does not mention any training set or its sample size. This is consistent with the device being an image processing software (PACS) rather than a machine learning or AI diagnostic aid that typically requires a training set.
9. How the ground truth for the training set was established
As no training set is mentioned, this question is not applicable.
§ 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).