(84 days)
The Netra™ Workstation System and NetraMD™ Software is intended for viewing and manipulation of high quality MRI, CT, Ultrasound and X-ray electronic images as an aid in diagnosis for the trained medical practitioner.
The Netra™ Workstation System and NetraMD™ Software is a Medical Image Processing System and digital image communications system for use by the trained medical practitioner. The Netral Image Processing System receives electronic information from medical imaging devices and manipulates that data for purposes of visualization, communication, archiving, characterization, comparison to other images and image enhancement. It is similar in design to other such digital image communications system devices. It has microprocessor PC computer controlled solid state digital data and video receiving and transmission electronics and accessories.
The provided text describes a 510(k) submission for the Netra™ Workstation System and NetraMD™ Software, claiming substantial equivalence to a predicate device. However, it does not contain a detailed study with acceptance criteria and reported device performance in the manner typically required for a modern AI/ML device.
Here's an analysis based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Acceptance Criteria (from text) | Reported Device Performance (from text) |
|---|---|---|
| Standards Compliance | - ACR/NEMA Digital Imaging and Communications in Medicine (DICOM) Standard, Version 3.0. | "the system met the standard's and requirements" |
| - ACC/NEMA DICOM 3.0 Digital Interchange for Standard for Cardiology (DISC95-96) | "the system met the standard's and requirements" | |
| - FDA, CDRH, ODE, August 29, 1991, Reviewer Guidance for Computer Controlled Medical Devices Undergoing 510(k) Review. | "The device and its development process also comply with the FDA... Reviewer Guidance" | |
| Design Specifications | Netra™ design specifications | "consistently performed within its design parameters" |
| Equivalence to Predicate | "no significant change in design, materials, energy source or other technological characteristics when compared to the predicate device" | "equivalently to the predicate device" |
| "minor configuration differences... do not alter the intended use or affect the safety and effectiveness of the NetraMD™ Software" when used as labeled | "minor configuration differences... do not alter the intended use or affect the safety and effectiveness of the NetraMD™ Software and NETRA™ Imaging Workstation system when used as labeled." |
Explanation: The document focuses on demonstrating substantial equivalence to an existing predicate device rather than undergoing a new, comprehensive clinical performance study with specific quantitative acceptance criteria for diagnostic accuracy (e.g., sensitivity, specificity, AUC). The "acceptance criteria" here are primarily about regulatory compliance, functional specifications, and maintaining the same safety and effectiveness as the predicate.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not specified. The document states "Performance tests were conducted by testing the system to the above standards and to the Netra™ design specifications." This suggests functional and technical testing, but there's no mention of a "test set" of medical images for diagnostic performance evaluation.
- Data Provenance: Not specified.
3. Number of Experts Used to Establish Ground Truth and Qualifications
- Number of Experts: Not applicable/not specified. The testing described is against technical standards and design specifications, not against established ground truth for diagnostic accuracy based on expert consensus.
- Qualifications of Experts: Not applicable/not specified.
4. Adjudication Method for the Test Set
- Adjudication method: Not applicable/not specified. No diagnostic "test set" requiring adjudication is mentioned.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done
- MRMC Study: No, an MRMC comparative effectiveness study was not done. The submission relies on demonstrating substantial equivalence to a predicate device based on technological characteristics and functional performance, not on direct comparison of human reader performance with or without the device.
- Effect size improvement: Not applicable, as no MRMC study was performed.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: No, a standalone performance study in the modern sense of an AI algorithm making diagnoses was not conducted or reported. The device is a "Medical Image Processing System" intended "for use by the trained medical practitioner" as an "aid in diagnosis." Its function is to display, manipulate, and communicate images, not to make diagnostic interpretations independently. The "performance tests" focused on meeting technical standards and design specifications for these functions.
7. The type of ground truth used
- Type of Ground Truth: Not applicable/not specified for diagnostic performance. The "ground truth" for the tests performed was adherence to technical standards (DICOM, DISC) and the device's own design specifications. There is no mention of pathology, outcomes data, or expert consensus used as ground truth for diagnostic accuracy of image interpretations.
8. The sample size for the training set
- Sample Size for Training Set: Not applicable/not specified. This device is an image processing system, not a machine learning algorithm that undergoes a "training" phase with a dataset to learn patterns for diagnosis.
9. How the ground truth for the training set was established
- Ground Truth for Training Set: Not applicable. As this is not an AI/ML device that requires a training set, the concept of establishing ground truth for a training set does not apply.
In summary: This 510(k) submission from 1996 for the Netra™ Workstation System and NetraMD™ Software focuses on demonstrating functional equivalence to a predicate device and compliance with established technical standards (like DICOM). It does not present the type of detailed clinical performance study, acceptance criteria, or ground truth establishment that would be expected for a diagnostic AI/ML device today. The "study" here refers to technical performance tests against standards and specifications, not a diagnostic accuracy trial.
§ 892.2020 Medical image communications device.
(a)
Identification. A medical image communications device provides electronic transfer of medical image data between medical devices. It may include a physical communications medium, modems, and interfaces. It may provide simple image review software functionality for medical image processing and manipulation, such as grayscale window and level, zoom and pan, user delineated geometric measurements, compression, or user added image annotations. The device does not perform advanced image processing or complex quantitative functions. This does not include electronic transfer of medical image software functions.(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 892.9.