(66 days)
PERFSCAPE allows the post-processing and display of dynamically acquired Magnetic Resonance datasets to evaluate image intensity variations over time. PERFSCAPE retrieves and accepts data from existing MRI systems. Based on these data, PERFSCAPE performs quality control checks, displays Diffusion Weighted Images and generates parametric perfusion maps such as Relative Cerebral Blood Volume (rCBV), Relative Cerebral Blood Flow (rCBF), Relative Mean Transit Time (rMTT), Time to Peak (TTP) and Impulse Response Time to Peak (TMAX). These images when interpreted by a trained physician may yield information useful in clinical applications.
PERFSCAPE is a software application designed to analyze dynamically acquired datasets. Using well-established algorithms, parametric perfusion maps can be generated such as Relative Cerebral Blood Volume (rCBV), Relative Cerebral Blood Flow (CBF), Relative Mean Transit Time (MTT), Time to Peak (TTP) and impulse response time to peak (TMAX). The system includes critical features such as:
- Enables rapid creation of a complete array of critical perfusion . parameter maps of rCBV, rCBF, rMTT, TTP, TMAX;
- Automated brain mask generation: .
- View dynamic signal time course on a per-voxel basis; .
- . Interactive Arterial Input Function (AIF) selection:
- Export computed perfusion map to the NEUROSCAPE PACS system. .
PERFSCAPE also allows the user to view the computed perfusion maps using the NEUROSCAPE software. NEUROSCAPE displays the original study series for FLAIR, ADC, B0 and B1000 and PERFSCAPE computed series for TTP, CBV, CBF, MTT and TMAX.
The PERFSCAPE device is a software application intended for the post-processing and display of dynamically acquired Magnetic Resonance datasets to evaluate image intensity variations over time. It retrieves data from existing MRI systems to perform quality control checks, display Diffusion Weighted Images, and generate parametric perfusion maps (rCBV, rCBF, rMTT, TTP, TMAX). These images, when interpreted by a trained physician, are intended to provide information useful in clinical applications.
The provided document does not explicitly state specific quantitative acceptance criteria for the device's performance in terms of accuracy, sensitivity, or specificity for a particular clinical task. Instead, the focus of the 510(k) submission and the "Testing" section is on demonstrating substantial equivalence to a predicate device and confirming the software's functionality and reliability.
However, based on the provided text, we can infer the primary "acceptance criterion" as functional equivalence and reliability with the predicate device for its intended use as a post-processing and display tool for MR perfusion images.
Here's an analysis of the provided information:
1. Table of Acceptance Criteria and Reported Device Performance
As no explicit quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds) are stated in the document, this table will reflect the inferred criteria of functional equivalence and software reliability.
| Acceptance Criterion (Inferred from submission) | Reported Device Performance |
|---|---|
| Functional Equivalence to Predicate Device (IB Neuro™ 1.0, K080762) | "Based on the comparison of intended use and technological characteristics, the PERFSCAPE system is substantially equivalent to the IB Neuro™ 1.0 device manufactured by Imaging Biometrics, LLC (K080762)." |
| Reliable Post-processing and Display of MR perfusion images | "OLEA Medical has conducted extensive validation testing of the PERFSCAPE system, as a software that is capable of providing reliable postprocessing and display of magnetic resonance perfusion images for instantaneous multi-parametric analysis." |
| Generation of specified parametric perfusion maps (rCBV, rCBF, rMTT, TTP, TMAX) | "Enables rapid creation of a complete array of critical perfusion parameter maps of rCBV, rCBF, rMTT, TTP, TMAX." "PERFSCAPE analyzes dynamically acquired MR datasets and generates parametric maps of the brain." |
| Automated brain mask generation | "Automated brain mask generation." "It also allows generating, manually or automatically, a brain mask to remove non-brain voxels." |
| Interactive Arterial Input Function (AIF) selection and filtering | "Interactive Arterial Input Function (AIF) selection." "PERFSCAPE allows interactive and multiple selections of arterial input functions and displays map results of the selected slice in real time. The selected AIF can be manually filtered before the beginning of the signal of interest and after the beginning of the recirculation." |
| Viewing dynamic signal time course | "View dynamic signal time course on a per-voxel basis." |
| Export computed perfusion maps to NEUROSCAPE PACS system | "Export computed perfusion map to the NEUROSCAPE PACS system." "PERFSCAPE allows creating a NEUROSCAPE study with computed perfusion maps and with imported diffusion map." |
| Compatibility with DICOM standard and multi-platform OS | "PERFSCAPE is compliant with the DICOM standard allowing the system to visualize medical images. The system is a multi-platform software running on any Windows, Mac and Linux operating systems." |
| Safety and Effectiveness (no new issues) | "The PERFSCAPE device raises no new safety or effectiveness issues." |
| Quality Control Checks and Display of Diffusion Weighted Images | "PERFSCAPE performs quality control checks, displays Diffusion Weighted Images..." |
| Stress testing of components | "All of the different components of the PERFSCAPE software have been stress tested to ensure that the system as a whole provides all the capabilities necessary to operate safely and effectively." |
2. Sample size used for the test set and the data provenance
The document states, "OLEA Medical has conducted extensive validation testing of the PERFSCAPE system..." but does not specify the sample size of the test set (number of cases/patients) or the data provenance (e.g., country of origin, retrospective or prospective). The testing is described as focused on the software's functional capabilities and reliability rather than a diagnostic performance study on a patient cohort.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not mention the use of experts to establish ground truth for a test set, nor does it describe any such ground truth establishment process. The testing appears to be centered on software validation rather than clinical diagnostic accuracy against a ground truth.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
As there's no mention of a test set with ground truth established by experts, there is no adjudication method 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 MRMC comparative effectiveness study is mentioned in the provided text. The device is a post-processing tool, and its submission focuses on substantial equivalence based on technical characteristics and intended use, not on reader performance improvement in a clinical setting.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
The document describes the device as performing post-processing and displaying parametric maps, which are then "interpreted by a trained physician." This implies it is an algorithm-only (standalone) component that assists human interpretation rather than a system that provides a final diagnostic output. The validation described is of the software's ability to generate these maps and its functionality, which is a standalone performance aspect. However, it's not a standalone diagnostic performance in the sense of providing a definitive diagnosis without human oversight.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
No specific type of ground truth is mentioned for the validation of the PERFSCAPE system, as the testing described focuses on software functionality, reliability, and substantial equivalence, not the diagnostic accuracy of the generated maps against external clinical truth. The "ground truth" for the software's performance seems to be its ability to correctly generate the specified parametric maps based on established algorithms and display them reliably.
8. The sample size for the training set
The document does not provide any information regarding a training set sample size. This is common for devices of this nature (post-processing software using established algorithms), as explicit "training" in the context of machine learning (where training set sizes are critical) might not be applicable or explicitly called out if the algorithms are deterministic and well-established.
9. How the ground truth for the training set was established
Since no training set is described or implied in the context of machine learning, there is no information on how ground truth for a training set was established. The device "Using well-established algorithms" suggests that the underlying principles are known and validated, rather than learned from a labeled training set in a machine learning context.
§ 892.1000 Magnetic resonance diagnostic device.
(a)
Identification. A magnetic resonance diagnostic device is intended for general diagnostic use to present images which reflect the spatial distribution and/or magnetic resonance spectra which reflect frequency and distribution of nuclei exhibiting nuclear magnetic resonance. Other physical parameters derived from the images and/or spectra may also be produced. The device includes hydrogen-1 (proton) imaging, sodium-23 imaging, hydrogen-1 spectroscopy, phosphorus-31 spectroscopy, and chemical shift imaging (preserving simultaneous frequency and spatial information).(b)
Classification. Class II (special controls). A magnetic resonance imaging disposable kit intended for use with a magnetic resonance diagnostic device only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.