(80 days)
IB Clinic v1.0 (Clinic) is a post-processing software toolkit designed to be integrated into existing medical image visualization applications running on standard computer hardware. Clinic accepts relevant DICOM image sets, such as dynamic perfusion and diffusion image sets. Clinic generates various perfusion- and diffusion-related parameters, standardized image sets, and image intensity differences. The results are saved to a DICOM image file and may be further visualized on an imaging workstation.
Clinic is designed to aid trained physicians in advanced image assessment, treatment consideration, and monitoring of therapeutic response. The information provided by Clinic should not be used in isolation when making patient management decisions.
Dynamic Perfusion Analysis - Generates parametric perfusion maps used for visualization of temporal variations in dynamic datasets, showing changes in image intensity over time. These maps may aid in the assessment of the extent and type of perfusion, blood volume and vascular permeability changes.
Dynamic Diffusion Analysis - Generates apparent diffusion coefficient maps used for the visualization of apparent water movement in soft tissue throughout the body on both voxel-by-voxel and sub-voxel bases. These images may aid in the assessment of the extent of diffusion in tissue.
Image Comparison - Generates co-registered image sets. Generates standardized image sets calibrated to an arbitrary scale to facilitate comparisons between independent image sets. Generates voxel-by-voxel maps of the image intensity differences between image sets acquired at different times. Facilitates selection and DICOM export of user-selected regions of interest (ROIs) These processes may enable easier identification of image intensity differences between images and easier selection and processing of ROIs.
Clinic is a platform independent image processing library which consists of a set of code modules which run on standard computer hardware that computes a variety of numerical analyses, image parameter maps, and other image manipulations based on DICOM images captured via MR and CT modalities. These actions include:
- Retrieval of MR and CT DICOM image studies from PACS and/or OS-. based file storage.
- Computation of parameter maps for: .
- DSC perfusion (based on MR and CT studies) O
- o ADC diffusion (based on MR studies)
- Image manipulations (of MR and CT studies): .
- Registration of images generated at different time points o
- Standardized scaling of image intensities O
- o Comparison of registered and/or standardized images
- Region of Interest (ROI) selection o
- Generation of ROI datasets in DICOM formats O
- Output of the above maps in DICOM format for export to PACS and/or OS . file storage
- . Generation of reports summarizing the computations performed
The IB Clinic code library can be used within standalone FDA cleared applications or can be "plugged in" and launched from within other FDA cleared applications such as Aycan's OsiriX PRO workstation. They are intended for distribution both in combination and in modular form, with functional subsets geared toward specific types of image analysis and marketed with corresponding names, including IB Neuro, IB Diffusion, and IB Delta Suite.
Here's an analysis of the provided text regarding the acceptance criteria and study information for the IB Clinic v1.0 device:
1. Table of Acceptance Criteria and Reported Device Performance:
Based on the provided text, there are no explicit, quantitative acceptance criteria or numerical performance metrics for the IB Clinic v1.0 device. The submission focuses on demonstrating substantial equivalence to predicate devices, rather than meeting specific performance thresholds. The text describes the functionalities of the device but does not quantify their accuracy, precision, or efficiency.
| Acceptance Criteria (Not Explicitly Stated) | Reported Device Performance |
|---|---|
| Implicit Criteria: | |
| - Ability to retrieve MR and CT DICOM images | Yes, device performs this. |
| - Ability to compute DSC perfusion maps | Yes, device performs this. |
| - Ability to compute ADC diffusion maps | Yes, device performs this. |
| - Ability to register images | Yes, device performs this. |
| - Ability to standardize image intensities | Yes, device performs this. |
| - Ability to compare images | Yes, device performs this. |
| - Ability to select Regions of Interest (ROIs) | Yes, device performs this. |
| - Ability to generate ROI datasets in DICOM | Yes, device performs this. |
| - Ability to output maps in DICOM format | Yes, device performs this. |
| - Ability to generate reports | Yes, device performs this. |
| - Substantial equivalence to predicate devices in intended use and performance characteristics. | Confirmed by FDA clearance. |
2. Sample Size for Test Set and Data Provenance:
The document does not specify a sample size for a test set or the provenance of any data. The submission relies on non-clinical tests (quality assurance measures) and a comparison to predicate devices, rather than a clinical trial with a defined test set.
3. Number of Experts and Qualifications for Ground Truth (Test Set):
Not applicable. No clinical test set with expert-established ground truth is mentioned in the document.
4. Adjudication Method for Test Set:
Not applicable. As there is no described clinical test set, there is no mention of an adjudication method.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
No. The document explicitly states: "Discussion of Clinical Tests Performed: N/A". This indicates that no MRMC or any other clinical effectiveness study involving human readers or AI assistance was conducted or reported in this submission.
6. Standalone Performance Study (Algorithm Only):
No. The document states "N/A" for clinical tests. While the device is a "post-processing software toolkit" and "platform independent image processing library," the submission does not present any standalone performance metrics or studies directly demonstrating the algorithm's accuracy or efficacy on a dataset. The validation described is primarily related to software development processes and comparison to predicate devices.
7. Type of Ground Truth Used:
Not explicitly stated for any performance evaluation. The "ground truth" for the device's functionality appears to be derived from the inherent mathematical and algorithmic correctness of the image processing operations it performs, as verified through "Performance testing (verification)" and "Product software validation" (listed under non-clinical tests). There's no mention of a clinical ground truth like pathology or outcomes data to assess the accuracy of the generated perfusion/diffusion maps.
8. Sample Size for Training Set:
Not applicable. As this is a software toolkit for image processing, not a machine learning model that typically requires a training set, no training set size is mentioned. The device computes parameters based on established physical models (e.g., perfusion, diffusion) rather than learning from data.
9. How Ground Truth for Training Set Was Established:
Not applicable. See point 8.
§ 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).