Search Results
Found 1 results
510(k) Data Aggregation
(269 days)
JelloX Biotech Inc.
For In Vitro Diagnostic Use
MetaLite DX Digital Pathology Software is a software only device intended for viewing and management of digital images of scanned surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue for the purposes of pathology primary diagnosis. It is an aid to the pathologist to review, interpret and manage digital images of pathology slides.
MetaLite DX Digital Pathology Software is not intended for use with frozen section, 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. MetaLite DX Digital Pathology Software is intended for use with Philips Ultra Fast Scanner and the Barco MDPC-8127 display.
MetaLite DX Digital Pathology Software, Model MLDXUS, version 1.2.1 is software designed for viewing digital pathology images of glass slides from the Philips IntelliSite Pathology Solution Ultra-Fast Scanner (PIPS-UFS), version 1.8.4 on Barco MDPC-8127 display.
MetaLite DX Digital Pathology Software is operated as follows:
Before scanning the slide on the PIPS-UFS, the technician performs quality control on the tissue of interest. The images captured by the PIPS-UFS are compressed using Philips' proprietary iSyntax format and are transmitted to the Philips Image Management System (IMS).
(1) After the Whole Slide Images (WSIs) are successfully, acquired by using PIPS-UFS, the WSIs are stored in the Local file system. A qualified pathologist will upload compatible iSyntax format digital pathology images, and the software will load them to the "Main Viewer" area of the graphical interface for the pathologist to view.
(2) Once properly loaded, the pathologist will use the inherent features of the device (including tools that allow for adjusting the position and viewing angle of the image, measuring lengths between two coordinates, and adding annotations to specific regional areas).
(3) After viewing all images for a patient (case), the pathologist will make a diagnosis. The diagnosis will be documented in another system, e.g., a Laboratory Information System (LIS).
The software has various features such as zoom-in and zoom-out functions, scale display, thumbnail view, measurement function, annotation function, and panning function to help pathologists interpret, diagnose and manage digital whole slide images. The MetaLite DX Digital Pathology Software is validated for use with the components specified the tables below.
Let's break down the acceptance criteria and the study proving the device meets them based on the provided text.
Based on the provided text, the "MetaLite DX Digital Pathology Software" (MLDXUS) is a software-only device intended for viewing and managing digital images of scanned surgical pathology slides for primary diagnosis. The performance testing section describes the studies conducted to demonstrate its safety and effectiveness.
Here's the information organized as requested:
1. Table of Acceptance Criteria and Reported Device Performance
| Test | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Pixel-wise comparison | The output images of the MetaLite DX Digital Pathology Software should be visually identical to those produced by the predicate device (PIPS IMS) for the same file. | The 95th percentile of pixel-wise differences between MetaLite DX Digital Pathology Software and PIPS IMS was less than 3 CIEDE2000, indicating that their output images are pixel-wise identical and visually adequate. |
| Turnaround time | Opening, panning, and zooming an image should be within an adequate timeframe for intended use (implicitly, within 5 seconds based on the outcome). | The turnaround time for opening, panning, and zooming an image is within 5 seconds. This was determined and found to be adequate for the intended use. |
| Measurements | The software should perform accurate measurements. | Measurement accuracy was verified using a scanned image of a calibration scale slide. MetaLite DX Digital Pathology Software was found to perform accurate measurements with respect to its intended use. (Note: Predicate device also measures area, but this device only explicitly states distance measurement in the comparison table, although the performance statement is general for "measurements"). |
| Usability testing | The device should be safe and effective for its intended users, uses, and use environments. | Conducted per FDA guidance "Applying Human Factors and Usability Engineering to Medical Devices (2016)". The test result demonstrated that the subject device has been found to be safe and effective for the intended users, uses, and use environments. |
2. Sample Size Used for the Test Set and Data Provenance
The document does not specify the sample size for the test sets used in the pixel-wise comparison, turnaround time, measurement accuracy, or usability testing.
The document does not specify the provenance of the data (e.g., country of origin, retrospective or prospective). It only states that the images used were "iSyntax file generated from UFS 1.8.4," which refers to the Philips Ultra Fast Scanner, a compatible component.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not explicitly state the number of experts used or their specific qualifications for establishing ground truth for any of the performance tests.
- For the pixel-wise comparison, the ground truth seems to be the output of the predicate device (PIPS IMS) for the same initial image file, rather than expert judgment on clinical images.
- For turnaround time and measurements, the ground truth would be objectively measurable (time, known distances on a calibration slide).
- For usability testing, ground truth typically involves observing user interactions and identifying errors or difficulties, rather than a clinical ground truth established by experts.
4. Adjudication Method for the Test Set
The document does not describe any adjudication method (e.g., 2+1, 3+1, none) for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly conducted for the MetaLite DX Digital Pathology Software as described in this document. The studies performed focus on technical performance (pixel comparison, speed, measurement accuracy) and usability of the software as a viewing and management tool, not on its impact on human reader diagnostic accuracy or efficiency with and without AI assistance. The device is purely a viewer/manager and does not incorporate AI for diagnosis.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
The studies described are primarily standalone in the sense that they evaluate the software's technical performance attributes (pixel reproduction, speed, measurement accuracy) independent of a pathologist's diagnostic performance. The usability test involved human interaction but assessed the usability of the software interface, not the diagnostic accuracy of the human using it. The device itself is described as "software only" and an "aid to the pathologist," rather than an AI diagnostic algorithm.
7. Type of Ground Truth Used
- Pixel-wise comparison: The ground truth appears to be the output of a reference system (PIPS IMS) for the same iSyntax file. This is a technical ground truth based on image fidelity.
- Turnaround time: The ground truth is objective measurement of time.
- Measurements: The ground truth is objective, known distances on a calibration scale slide.
- Usability testing: The ground truth is based on observed user interactions, identification of use errors, and compliance with human factors principles, as guided by FDA guidelines.
There is no mention of clinical ground truth (e.g., expert consensus on pathology diagnoses, or outcomes data) being used for these particular performance tests, as the device is not a diagnostic AI algorithm.
8. Sample Size for the Training Set
The document does not provide any information regarding a training set size. This is consistent with the device being a viewer and manager of digital images, not an AI algorithm that requires a training set for model development.
9. How the Ground Truth for the Training Set Was Established
As no training set is described for this type of device, this information is not applicable and not provided in the document.
Ask a specific question about this device
Page 1 of 1