Search Results
Found 1 results
510(k) Data Aggregation
(248 days)
For In Vitro Diagnostic Use
FullFocus is a software intended for viewing and management of digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. It is an aid to the pathologist to review, interpret and manage digital images of pathology slides for primary diagnosis. FullFocus is not intended for use with frozen sections, cytology, or non-FFPE hematopathology specimens.
It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the quality of the images obtained and, where necessary, use conventional light microscopy review when making a diagnostic decision. FullFocus is intended to be used with the interoperable components specified in the below Table.
Table: Interoperable components of FullFocus
| Scanner Hardware | Scanner Output file format | Interoperable Displays |
|---|---|---|
| Leica Aperio GT 450 DX scanner | DICOM, SVS | Dell UP3017Dell U3023E |
| Hamamatsu NanoZoomer S360MD Slide Scanner | NDPI | Dell U3223QEJVC-Kenwood JD-C240BN01A |
FullFocus, version 2.29, is a web-based software-only device that facilitates the viewing and navigating of digitized pathology images of slides prepared from FFPE-tissue specimens acquired from FDA cleared digital pathology scanners on FDA cleared displays. FullFocus renders these digitized pathology images for review, management and navigation for pathology primary diagnosis.
Image acquisition is performed using the intended scanner (s), with the operator conducting quality control on the digital WSI images according to the scanner's instructions for use and lab specifications to determine if re-scans are needed. Please see the Intended Use section and below tables for specifics on scanners and respective displays for clinical use.
Once a whole slide image is acquired using the intended scanner and becomes available in the scanner's database file system, a separate medical image communications software (not part of the device), automatically uploads the image and corresponding metadata to persistent cloud storage. Integrity checks are performed during the upload to ensure data accuracy.
The subject device enables the reading pathologist to open a patient case, view the images, and perform actions such as zooming, panning, measuring distances and annotating images as needed. After reviewing all images for a case, the pathologist will render a diagnosis.
FullFocus operates with and is validated for use with the FDA cleared components specified in the tables below:
| Scanner Hardware | Scanner Output file format | Interoperable Displays |
|---|---|---|
| Leica Aperio GT 450 DX scanner | DICOM, SVS | Dell UP3017Dell U3023E |
| Hamamatsu NanoZoomer S360MD Slide Scanner | NDPI | Dell U3223QEJVC-Kenwood JD-C240BN01A |
Table 1: Interoperable Components Intended for Use with FullFocus
FullFocus version 2.29 was not validated for the use with images generated with Philips Ultra Fast Scanner.
Table 2: Computer Environment/System Requirements for during the use of FullFocus
| Environment | Component | Minimum Requirements |
|---|---|---|
| Hardware | Processor | 1 CPU, 2 cores, 1.6GHz |
| Memory | 4 GB RAM | |
| Network | Bandwidth of 10Mbps | |
| Software | Operating System | • Windows• macOS |
| Browser | • Google Chrome (129.0.6668.90 or higher)• Microsoft Edge (129.0.2792.79 or higher) |
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion | Reported Device Performance |
|---|---|
| Pixel-wise comparison: The 95th percentile of pixel-wise color differences in any image pair across all required screenshots must be less than 3.0 ΔE00 when compared to comparator (predicate device's Image Review Manipulation Software - IRMS) for identical image reproduction. This indicates visual adequacy for human readers. | The 95th percentile of pixel-wise differences between FullFocus and the comparators were less than 3 CIEDE2000, indicating that their output images can be considered to be pixel-wise identical. FullFocus has been found to visually adequately reproduce digital pathology images to human readers with respect to its intended use. |
| Turnaround time (Case selection): It should not take longer than 10 seconds until the image is fully loaded when selecting a case. | System requirements fulfilled: Not longer than 10 seconds until the image is fully loaded. |
| Turnaround time (Panning/Zooming): It shall not take longer than 7 seconds until the image is fully loaded when panning and zooming the image. | System requirements fulfilled: Not longer than 7 seconds until the image is fully loaded. |
| Measurement Accuracy (Straight Line): The 1mm measured line should match the reference value exactly 1mm ± 0mm. | All straight-line measurements compared to the reference were exactly 1mm, with no error. |
| Measurement Accuracy (Area): The measured area must match the reference area exactly 0.2 x 0.2 mm for a total of 0.04 mm² ± 0 mm². | All area measurements compared to the reference value were exactly 0.04mm², with no error. |
| Measurement Accuracy (Scalebar): 2mm scalebar is accurate. | All Tests Passed. |
| Human Factors Testing: (Implied from previous clearance) Safe and effective use by representative users for critical user tasks and use scenarios. | Human factors study designed around critical user tasks and use scenarios performed by representative users were conducted for previously cleared FullFocus, version 1.2.1, in K201005, per FDA guidance “Applying Human Factors and Usability Engineering to Medical Devices (2016)". Human factors validation testing is not necessary as the user interface hasn't changed. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Pixel-wise Comparison: 30 formalin-fixed paraffin-embedded (FFPE) tissue glass slides, representing a range of human anatomical sites.
- Sample Size for Turnaround Time & Measurements: Not explicitly stated as a number of distinct cases or images beyond the 30 slides used for pixel-wise comparison. For measurements, a "1 Calibration Slide" was used per test.
- Data Provenance: The text does not explicitly state the country of origin. The slides are described as "representing a range of human anatomical sites," implying a diverse set of real-world pathology samples. It is a retrospective study as it states "30 formalin-fixed paraffin-embedded (FFPE) tissue glass slides... were scanned".
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Pixel-wise Comparison: "For each WSI, three regions of interest (ROIs) were identified to highlight relevant pathological features, as verified by a pathologist."
- Number of Experts: At least one pathologist.
- Qualifications: "A pathologist" (specific qualifications like years of experience are not provided).
- Measurements: No expert was explicitly mentioned for establishing ground truth for measurements; it relies on a "test image containing objects with known sizes" (calibration slide) and "reference value."
4. Adjudication Method for the Test Set
- The text does not mention an explicit adjudication method (like 2+1 or 3+1 consensus) for the pixel-wise comparison or measurement accuracy. For the pixel-wise comparison, ROIs were "verified by a pathologist," suggesting a single-expert verification rather than a consensus process.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- No, an MRMC comparative effectiveness study was not done in this context. The study focused on demonstrating identical image reproduction (pixel-wise comparison) and technical performance (turnaround time, measurement accuracy) of the FullFocus viewer against predicate devices' viewing components. It did not directly assess the improvement in human reader performance (e.g., diagnostic accuracy or efficiency) with or without AI assistance. The device is a "viewer and management software," not an AI diagnostic aid in the sense of providing specific findings or interpretations.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
- Yes, a standalone "algorithm only" performance was effectively done for the technical aspects. The pixel-wise comparison directly compares the image rendering of FullFocus with the predicate viewer's rendering without human intervention in the comparison process itself (though a pathologist verified ROIs). Similarly, turnaround times and measurement accuracy are intrinsic technical performances of the software.
7. The Type of Ground Truth Used
- Pixel-wise Comparison: The ground truth for this test was the digital image data as rendered by the predicate device's IRMS. The goal was to show that FullFocus reproduces the same image data. The "relevant pathological features" within ROIs were "verified by a pathologist" which served as a reference for what areas to test, not necessarily a diagnostic ground truth for the device's output.
- Measurements: The ground truth was based on known physical dimensions within a calibration slide and corresponding "reference values."
8. The Sample Size for the Training Set
- The provided text does not mention a training set. This is expected because FullFocus is a viewer and management software for digital pathology images, not an AI or machine learning algorithm that is "trained" on data to make predictions or assist in diagnosis directly. Its core function is to display existing image data accurately and efficiently.
9. How the Ground Truth for the Training Set Was Established
- As no training set is mentioned (since it's a viewer software), this question is not applicable based on the provided text.
Ask a specific question about this device
Page 1 of 1