Search Results

ViewStation supports image and information flow among health care facility personnel. ViewStation can be used whenever digital images and associated data are the means for communicating information. ViewStation is not intended for use in diagnosis. The images and associated information are stored in a database, providing users access to the information necessary to perform their functions.

The intended use of ViewStation is to provide health care facility personnel with an efficient and effective means to utilize patient images during the course of therapy or treatment. ViewStation allows users to import, view, annotate, manipulate, enhance, manage, and archive patient images.

The primary function of ViewStation is to provide a means to move image information in a therapy or treatment environment. ViewStation provides the ability to import, view, annotate, manage, and archive patient images during the course of therapy, treatment, and follow-up.

ViewStation imports existing digital images acquired or generated by other products. ViewStation retains the original image, which was acquired or generated by a third party product.

The provided text describes a Premarket Notification (510(k)) Summary of Safety and Effectiveness for "ViewStation, Image Processing System" by IMPAC Medical Systems, Inc. This document focuses on establishing substantial equivalence to a predicate device, rather than presenting a detailed study with acceptance criteria and performance metrics typically seen for standalone diagnostic AI/ML devices.

Here's an analysis based on the provided text, highlighting what is present and what is absent in relation to your request:

1. A table of acceptance criteria and the reported device performance

The document does not provide a table of acceptance criteria or specific reported device performance metrics in the way one would expect for a diagnostic or AI/ML algorithm that generates specific output values (e.g., accuracy, sensitivity, specificity, AUC).

Instead, the "acceptance criteria" can be inferred from the document's claims about equivalency and safety:

2. Sample sized used for the test set and the data provenance

• Test Set Sample Size: Not specified. The document states "Engineering testing was also performed to ensure that the algorithms and all other technical changes function exactly as intended." This implies internal testing, but no details on the size or characteristics of the test data are provided.
• Data Provenance: Not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Not applicable as this is not a diagnostic device undergoing a typical clinical validation study with ground truth established by experts. The "effectiveness" is primarily about the algorithms functioning as intended, not about diagnostic accuracy against expert consensus.

4. Adjudication method for the test set

• Not specified.

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 MRMC or comparative effectiveness study is mentioned. The device's purpose is to automate a previously manual process (identifying a treatment field edge and ordering images), not to provide a diagnostic AI/ML assistant to human readers. The document explicitly states: "No additional or changed diagnostic or therapeutic claims arise as the result of the ViewStation product. Therefore, demonstration of clinical efficacy is not a required element of this Premarket Notification. Further, clinical performance data is not required for determination of substantial equivalence for this type and class of device."

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Yes, in a sense. The algorithms perform automated functions without human intervention in the specific tasks they are designed for (determining treatment field images, identifying edges, ordering images). The document focuses on the standalone functioning of these algorithms as part of the overall ViewStation system. "Engineering testing was also performed to ensure that the algorithms and all other technical changes function exactly as intended."

7. The type of ground truth used

• The concept of "ground truth" for diagnostic accuracy (e.g., pathology, outcomes data, expert consensus) is not directly applicable here. The "ground truth" for the engineering testing would relate to whether the algorithms correctly identify the treatment field image, correctly identify the field edge (based on pre-defined criteria or reference images), and correctly order the images. This would be a technical ground truth related to the algorithm's intended function, not clinical ground truth for diagnosis.

8. The sample size for the training set

• Not specified.

9. How the ground truth for the training set was established

• Not specified.

Summary of Device and its Purpose:

The ViewStation is an image processing system primarily for radiation therapy, designed to import, view, annotate, manipulate, enhance, manage, and archive patient images during therapy. The reported changes involve new automated image processing algorithms to:
* Determine which of two portal images is the treatment field portal image.
* Employ an edge detection algorithm to identify the treatment field edge in a portal image.
* Modify an existing histogram optimization algorithm to accept dynamic inputs from the new edge detection algorithm.
* Superimpose a polygon of the field edge onto an open field image and automatically order images.

Crucially, the document states, "ViewStation is not intended for use in diagnosis." and explicitly notes that "No additional or changed diagnostic or therapeutic claims arise as the result of the ViewStation product." This means it is a tool to enhance workflow and image management in a therapy setting, not a device that provides diagnostic outputs requiring traditional clinical performance metrics. The "study" referenced is the internal verification and validation testing to ensure the algorithms function as intended and that the changes do not introduce new safety concerns or alter the intended use, maintaining substantial equivalence to its predicate device.

Ask a specific question about this device