(20 days)
OmniVision is intended to be used for the acquisition, storage, communication and viewing of medical Images.OmniVision receives images from imaging modalities via DICOM or imported directly. It archives and displays these images for the use of medical specialists who are qualified to operate radiological equipment and to record and diagnose medical images.
It provides the user with a range of tools to assist them in viewing the images, such as zoom, filters and measurements, and with facilities to exchange images with other specialists.
OmniVision is not intended for the acquisition of mammographic image data.
OmniVision is a Picture Archiving and Communications System (PACS), as is the predicate Device dicomPACS. All of them have been developed to acquire, store, communicate, display and process medical images. They offer features (e.g. window leveling, zoom, measurements, annotations etc.) routinely used by medical professionals, such as radiologists and orthopaedists, and required of all PACS solutions.
OmniVision has a modular system architecture, It consists of the basic application viewer for image viewing and processing, image storage and communication, and a number of other modules for database management, image acquisition, printing etc.
OmniVision conforms to the DICOM (Digital Image and Communications in Medicine) standard.
The provided text describes the OmniVision Picture Archiving and Communications System (PACS) and its substantial equivalence to the predicate device, dicomPACS. However, it does not explicitly detail specific acceptance criteria in a quantitative manner or describe a study that involves performance metrics such as accuracy, sensitivity, or specificity.
The document primarily focuses on demonstrating that OmniVision provides comparable functionality, technological characteristics, and intended use as its predicate device to prove substantial equivalence for regulatory clearance. It confirms that the device has been tested according to the specifications documented in this notification and conforms to the DICOM standard.
Therefore, based solely on the provided text, the answer will reflect the absence of such detailed information.
Here's an analysis based on the provided input:
1. Table of acceptance criteria and the reported device performance
The provided document does not explicitly state quantitative acceptance criteria (e.g., minimum accuracy, sensitivity, or specificity) or the direct results of a performance study against such criteria. The document claims "substantial equivalence" to the predicate device, dicomPACS, based on functional and technological comparisons.
Instead, the comparison table focuses on functional similarities between OmniVision and dicomPACS:
| Feature/Characteristic | OmniVision Performance (as claimed by the document) | Predicate Device (dicomPACS) | Acceptance Criteria (Implicitly: Similarity to Predicate) |
|---|---|---|---|
| System Architecture | Server & Client, Web-based versions, local servers & remote archiving | Server & Client, Web-based versions, local servers & remote archiving | Similarity |
| Operating System | Window XP | Window XP | Similarity |
| Hardware | HP, Dell, IBM | HP, Dell, IBM | Similarity |
| System failure Alert | Available | Available | Similarity |
| DICOM Worklist | Yes | Yes | Similarity |
| DICOM Storage | Yes | Yes | Similarity |
| DICOM Printer | Yes | Yes | Similarity |
| Image Acquisition | DICOM radiology systems, Digital film scanner, Other imaging modalities | DICOM radiology systems, Digital film scanner, Other imaging modalities | Similarity |
| Rotation | Yes | Yes | Similarity |
| Invert | Yes | Yes | Similarity |
| Zoom In/Out | Yes | Yes | Similarity |
| W/L Adjustment | Yes | Yes | Similarity |
| Pan Image | Yes | Yes | Similarity |
| Flipping | Yes | Yes | Similarity |
| Image Crop | Yes | No | Enhancement (OmniVision has this, predicate does not) |
| Secondary Processing | Organ Specific Type | Organ specific type | Similarity |
| Length Measurement | Yes | Yes | Similarity |
| Angle Measurement | Yes | Yes | Similarity |
| Multiple Length Measurement | Yes | Yes | Similarity |
| Storage Backup method | CD/DVD, Flash Drive, URL | CD/DVD, Flash Drive | Improvement (OmniVision adds URL) |
| Export Format | DICOM, BMP | DICOM, TIFF, BMP, JPEG, PNG | Difference (OmniVision exports fewer formats) |
| Support | 24/7 customer support for application software | 24/7 customer support for application software | Similarity |
| Training | On/off site available | On/off site available | Similarity |
The "acceptance criteria" here appear to be primarily functional equivalence and adherence to DICOM standards, rather than specific performance metrics like diagnostic accuracy. The study described is essentially a comparison study against a predicate device.
2. Sample size used for the test set and the data provenance
The document does not specify a sample size for any test set or the provenance (e.g., country of origin, retrospective/prospective) of any data used for performance evaluation that would typically be described in clinical validation studies. The testing mentioned refers to conformity with DICOM standards and specifications in the notification, not independent clinical performance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. The document does not describe a study involving expert-established ground truth for a test set. The device is a PACS system for image handling and viewing, not a diagnostic AI tool that generates a finding requiring ground truth for validation. The premise is that "medical specialists who are qualified to operate radiological equipment and to record and diagnose medical images" will use the system, implying human experts will interpret the images.
4. Adjudication method for the test set
Not applicable, as no described test set required adjudication for ground truth.
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
There is no mention of an MRMC comparative effectiveness study or any study evaluating human reader improvement with or without AI assistance. OmniVision is described as a PACS system providing tools like zoom, filters, and measurements, which are standard functionalities, not an AI-driven diagnostic assistance tool in the context of an MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. OmniVision is a PACS system intended for human-in-the-loop use by medical specialists. It is not an algorithm designed to provide standalone diagnostic output.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
Not applicable, as no described study involved establishing ground truth for diagnostic accuracy.
8. The sample size for the training set
Not applicable. OmniVision is a PACS system, not an AI algorithm that undergoes "training" in the machine learning sense with a dataset.
9. How the ground truth for the training set was established
Not applicable, as there is no training set mentioned for an AI algorithm.
§ 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).