(159 days)
MEDImage will be used to acquire, display, process, archive, retrieve, and transmit diagnostic radiological images and information about these images in a single user or network environment. Typical users of MEDImage are trained medical professionals.
MEDImage is a software package designed to acquire analogue and digital images from any modality, store and archive these images together with patient information on hard disk and/or on long-term media such as standard optical disks; search for and retrieve these images for re-consultation, processing and/or transmission. MEDImage utilizes industry standard equipment.
This document is a 510(k) summary for the VEPRO MEDImage Picture Archiving and Communications System (PACS). It primarily focuses on establishing substantial equivalence to a predicate device (Siemens PACS/I-A (K880690)) rather than providing detailed acceptance criteria and a study report with performance metrics for the MEDImage device itself.
Based on the provided text, there is no specific information describing acceptance criteria or a dedicated study proving the device meets performance criteria in the way a modern medical device submission typically would for a novel algorithm.
Here's a breakdown of why and what information is available:
There is no table of acceptance criteria and reported device performance because the submission's focus is on substantial equivalence to an existing PACS system and its functionality as a Class I device (which does not require a demonstration of clinical performance that relies on outcome or diagnostic accuracy measurements).
The document states:
- "MEDimage is a software package designed to acquire analogue and digital images from any modality, store and archive these images together with patient information on hard disk and/or on long-term media such as standard optical disks; search for and retrieve these images for re-consultation, processing and/or transmission. MEDImage utilizes industry standard equipment."
- "MEDImage will be used to acquire, display, process, archive, retrieve, and transmit diagnostic radiological images and information about these images in a single user or network environment."
These descriptions define the functionality and intended use of the device, implying that its performance is measured by its ability to reliably perform these functions, which would have been demonstrated through system testing and validation, but not explicitly summarized here with specific metrics.
Here's a summary of the requested information based on the document:
1. A table of acceptance criteria and the reported device performance:
- Not provided. The submission focuses on substantial equivalence based on functionality and intended use aligning with a predicate device, rather than specific performance metrics against pre-defined acceptance criteria for diagnostic accuracy or algorithmic performance.
2. Sample size used for the test set and the data provenance:
- Not applicable/Not provided. This type of information would be relevant for a device performing automated analysis or diagnosis, which MEDImage is not presented as. The document does not describe a "test set" for evaluating algorithmic performance on images.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience):
- Not applicable/Not provided. This information is typically relevant for studies evaluating the diagnostic accuracy or classification performance of an algorithm. MEDImage is a PACS system, and its performance is not assessed in this manner in this submission. The document states, "Evaluation of the output is performed by health care professionals and provides adequate opportunity for competent human intervention," indicating human oversight.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not applicable/Not provided. As there's no mention of a test set for diagnostic performance, there's 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, an MRMC study was not done. This document pertains to a Picture Archiving and Communications System (PACS), not an AI-assisted diagnostic tool. Therefore, a study on human reader improvement with AI assistance is not described or relevant for this submission.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Not applicable/Not provided. This device is a PACS, which is fundamentally a human-in-the-loop system for image management and display, not a standalone diagnostic algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not applicable/Not provided. Ground truth is not discussed in the context of diagnostic accuracy, as this is not an AI diagnostic algorithm.
8. The sample size for the training set:
- Not applicable/Not provided. This device is a software package for managing images, not a machine learning model that requires a training set.
9. How the ground truth for the training set was established:
- Not applicable/Not provided. As there is no training set for a machine learning model, ground truth establishment is not relevant in this context.
In summary:
This 510(k) submission for VEPRO MEDImage focuses on demonstrating substantial equivalence to a predicate PACS device (Siemens PACS/I-A (K880690)) based on its intended use and functional capabilities (acquiring, displaying, processing, archiving, retrieving, and transmitting images). It does not present specific acceptance criteria or performance study results related to diagnostic accuracy, as would be expected for an AI-powered diagnostic algorithm. The device is classified as Class I, meaning it is subject to general controls and FDA believes it poses a low risk, with "adequate opportunity for competent human intervention."
§ 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).