(63 days)
READY View is an image analysis software that allows the user to process dynamic or functional volumetric data and to generate maps that display changes in image intensity over time, echo time, b-value (Diffusion imaging) and frequency (Spectroscopy). The combination of acquired images, reconstructed images, calculated parametric images, tissue segmentation, annotations and measurement performed by the clinician allows multi-parametric analysis and may provide clinically relevant information for diagnosis.
READY View is a suite of applications developed to improve multiparametric exams by enabling the analysis of MR generated data sets containing multiple images for each scan location. The MR data sets may be any of the following:
- A time series
- A diffusion weighted scan
- A diffusion tensor scan
- A variable echo imaging
- A blood oxygen level dependent imaging
- Spectroscopy (Single voxel and 2D or 3D CSI)
The READY View platform provides a combination of protocols, applications and tools that enables a fast, easy and quantified analysis of the multiple data sets.
Brain View is a post processing image analysis software package that provides advanced techniques to aid in the diganosis of neurological and oncological diseases. Brain View is an option with the READY View platform and offers two advanced protocols: - FiberTrak
- Arterial Spin Labeling (ASL)
READY View along with Brain View option is available on the Advantage Workstation (AW) and Advantage Workstation Server Gen 2, for viewing and processing Magnetic Resonance images.
Here's an analysis of the acceptance criteria and the study information for the GE Healthcare READY View device, based on the provided text.
Based on the provided document, the GE Healthcare READY View device did not require clinical studies to support substantial equivalence. This means that specific acceptance criteria typically associated with clinical performance metrics (like sensitivity, specificity, accuracy, etc.) and a study to prove they were met are not detailed.
Instead, the submission focuses on non-clinical tests to demonstrate its safety, effectiveness, and substantial equivalence to a predicate device.
Here's the breakdown of the requested information, drawing from what's available in the document:
1. A table of acceptance criteria and the reported device performance
Since a clinical study with performance metrics wasn't conducted, the acceptance criteria and performance are based on successful completion of non-clinical tests and demonstration of equivalence to the predicate device.
| Acceptance Criteria Category | Specific Criteria (Implicitly Met) | Reported Device Performance/Conclusion |
|---|---|---|
| Non-Clinical Testing | - Risk Analysis conducted | - Risk Analysis complete |
| - Requirements Reviews conducted | - Requirements Reviews complete | |
| - Design Reviews conducted | - Design Reviews complete | |
| - Performance testing (Verification) completed successfully | - Performance testing (Verification) complete and successful | |
| - Safety testing (Verification) completed successfully | - Safety testing (Verification) complete and successful | |
| - Simulated use testing (Validation) completed successfully | - Simulated use testing (Validation) complete and successful | |
| Substantial Equivalence | - Device is as safe, as effective, and performance is substantially equivalent to predicate devices (FuncTool K960265 and Volume Viewer Plus K041521). | - "GE Healthcare considers READY View to be as safe, as effective, and performance is substantially equivalent to the predicate devices." The FDA concurred with this determination, stating, "We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent... You may, therefore, market the device." This implies all equivalence criteria (e.g., similar indications for use, technological characteristics, and performance based on non-clinical testing) were deemed met. The document also states, "The READY View software employs the same algorithm technology as its predicate device FuncTool (K960265)." |
2. Sample size used for the test set and the data provenance
- Sample size for the test set: Not applicable, as no clinical efficacy study with a distinct "test set" of patient data (in the sense of a clinical trial) was performed for this submission. The "test set" for the non-clinical performance and safety testing would have been internal engineering and software validation tests, not patient imaging data reported in the submission in detail.
- Data provenance: Not applicable for a clinical test set. The document refers to "MR functional data of the human body acquired from a MR Scanner" for processing by the device, covering targeted anatomies like "Brain, Breast, Prostate, and Liver." However, the origin of specific data used for validation is not specified as it was not a clinical efficacy study.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not applicable. There was no clinical study involving expert consensus on patient cases for ground truth, as the submission relies on substantial equivalence and non-clinical testing.
4. Adjudication method for the test set
- Not applicable. No clinical study with a test set requiring adjudication was performed.
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. The document explicitly states: "The subject of this premarket submission, READY View, did not require clinical studies to support substantial equivalence." Therefore, no MRMC study or AI-assisted reader performance evaluation was conducted or reported.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, in essence. The "Performance testing (Verification)" and "Simulated use testing (Validation)" described are essentially demonstrations of the algorithm's functionality and performance as a software product. While not described as an "AI algorithm," it's a software application performing image analysis without human intervention during its processing steps. The output of the software (calculated parametric images, graphs, etc.) is then used by a clinician. The focus here is on the software's ability to process data and generate accurate representations, mirroring the algorithms of its predicate devices.
7. The type of ground truth used
- For the non-clinical verification and validation activities, the "ground truth" would have been established by engineering specifications, software design documents, and expected outputs based on known input data. For example, if a function calculates a specific parameter, the ground truth would be the mathematically correct calculation of that parameter given predefined input values. The comparison against predicate devices also serves as a form of "ground truth" for functionality and expected output.
8. The sample size for the training set
- Not applicable directly. READY View is not presented as a machine learning/AI model that requires a distinct "training set" in the modern sense. It's an image analysis software employing established algorithms, explicitly stated to use "the same algorithm technology as its predicate device FuncTool (K960265)." Therefore, there's no mention of a training set size.
9. How the ground truth for the training set was established
- Not applicable, as a discrete "training set" for a machine learning model was not used. The algorithms are based on established scientific principles for processing MR functional data, similar to the predicate device.
§ 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).