Search Results

DeltaView is intended to generate a secondary residual image based on a current and prior chest x-ray image of the same patient, resulting in improved detection of lung nodules that have changed between the two examinations. The DeltaView image provides adjunctive information and is not a substitute for the original PA/AP image. This device is intended to be used by trained professionals, such as physicians and radiologists, on patients with risk of having lung nodules, and is not intended to be used on pediatric patients.

DeltaView is a dedicated post-processing application which registers current and prior chest exams to provide an image that shows areas of change.

Here's a breakdown of the acceptance criteria and study details for the DeltaView™ device based on the provided text:

Acceptance Criteria and Device Performance

Study Details

1. Sample sizes used for the test set and the data provenance:

   • The document does not explicitly state the sample size (number of cases or images) used for the test set.
   • The document does not specify the data provenance (e.g., country of origin, retrospective or prospective).

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

   • The document does not specify the number of experts or their qualifications for establishing ground truth.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • The document does not specify an adjudication method for the test set.

4. 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:

   • Yes, an MRMC reader study was done.
   • Effect size: The area under the LROC curve (AUCLROC) "increased from 0.477 to 0.536 (12.4%)" when radiologists were aided by DeltaView compared to unaided interpretation. This indicates a 12.4% improvement in the AUCLROC.

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

   • The document does not state that a standalone (algorithm-only) performance study was conducted. The study described focuses on human-in-the-loop performance with the device as an adjunct.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The type of ground truth used is not explicitly stated. However, the study evaluated "the detection of actionable lung nodules," implying that a determination of the presence or change of such nodules constituted the ground truth.

7. The sample size for the training set:

   • The document does not provide information on the sample size used for the training set.

8. How the ground truth for the training set was established:

   • The document does not provide information on how the ground truth for the training set was established.

Ask a specific question about this device

The FirstView™ is intended to display and manipulate x-ray images.
The FirstView™ is indicated for displaying and manipulating chest x-ray images. It acts as an interface with the CAD component, if installed or available at the clinical site, and provides display of information contained within the DICOM header of the images. This device is intended to be used by trained professionals, such as physicians, radiologists, and technicians.

The FirstView™ consists of a dedicated server that has been programmed with a database and server software, as well as client software that is loaded onto an existing workstation. New images, which may be a chest x-ray or CAD result, are sent to the FirstView™ server from a Digital or from the PACS network, prompting FirstView to query the PACS for additional images related to that study. The FirstView™ server manages the images within its Riverain proprietary database.

The provided text concerns the 510(k) summary for the FirstView™ device, a system for displaying and manipulating chest x-ray images. However, the document does not contain information related to specific acceptance criteria, formal study design, sample sizes for test or training sets, ground truth establishment, expert qualifications, adjudication methods, or MRMC studies that would typically be described as "proving the device meets the acceptance criteria."

Instead, the document focuses on the device's substantial equivalence to predicate devices for its intended use as a "Picture archiving and communications system" (PACS). The 510(k) process primarily evaluates whether a new device is as safe and effective as a legally marketed predicate device, rather than requiring extensive clinical trials to meet novel performance criteria in the way a PMA (Premarket Approval) might.

Therefore, many of the requested sections regarding acceptance criteria and study details cannot be filled from the provided text. The information available is presented below within the constraints of the provided document.

Acceptance Criteria and Device Performance

The document does not explicitly state quantitative acceptance criteria or report specific device performance metrics in the format typically used for demonstrating performance against such criteria (e.g., sensitivity, specificity, accuracy).

Instead, the "acceptance criteria" in this context appear to be met by demonstrating substantial equivalence to legally marketed predicate devices.

Study Details (Based on available information)

1. Sample size used for the test set and the data provenance:

   • The document does not report any specific test set sample size or data provenance (e.g., country of origin, retrospective/prospective). The 510(k) submission primarily relies on comparison to predicate devices, not independent performance testing against a specific dataset.

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

   • The document does not mention a test set with ground truth established by experts.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • The document does not describe any adjudication method for a test set.

4. 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:

   • The document does not describe an MRMC comparative effectiveness study. The FirstView™ is described as an image display and manipulation system, potentially interfacing with CAD, but not inherently as an AI-powered diagnostic aid that would typically undergo such a study to evaluate human reader improvement.

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

   • The document does not describe any standalone algorithm performance study.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • The concept of "ground truth" for a specific performance evaluation test set is not mentioned in the document.

7. The sample size for the training set:

   • The document does not report any training set sample size.

8. How the ground truth for the training set was established:

   • The document does not report how ground truth for a training set was established, as it does not mention a training set.

Ask a specific question about this device