FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

PET VCAR (Volume Computer Assisted Reading) is a PET/CT software package which can be used by the clinician to assist in diagnosis, staging, treatment planning and monitoring treatment response. The PET VCAR automatically highlights and bookmarks PET defined regions of interest based on user-defined threshold settings. The software can be used for visualization and analytical monitoring of disease progression or response to treatment or therapy using multiexam comparison. The software is designed to measure Standard Uptake Value (SUV) and volume for any PET defined metabolic activity. The software automatically propagates bookmarks from one time point to another for the purpose of improving analysis and workflow. PET VCAR offers a tool called Interactive Data Analysis (IDA) spreadsheet that compiles and manages all the analytical information in an organized and interactive design. The IDA is synchronized with the image display layouts offering quick measurement / image visual validation. PET VCAR's workflow is designed to allow clinicians to make informed follow-up decisions in an efficient manner. PET VCAR does not provide or claim any automatic detection or automatic diagnosis of abnormal anatomy, structure or function.

Device Description

The GE PET VCAR has to ensure relations with the following external systems:
Data Import: Image, exam and patient data can be imported in accordance with the DICOM Standard.
Data Export: Finding, exam and patient information can be exported in the Secondary Capture format of the DICOM standard that enables its storage on PACS systems. Finding, exam and patient information can be exported in the Structured Report format of the DICOM standard that enables its display with DICOM SR compatible viewers. Finding, exam and patient information can be exported in standard formats like HTML, XML, PDF, CSV, that enables its display with viewers compatible with the mentioned formats.
Configuration Requirements: PET VCAR is compatible with Advantage Windows Workstation™ 4.4 or higher

AI/ML Overview

This submission is a 510(k) summary for GE Healthcare's PET VCAR, focusing on its substantial equivalence to previously marketed devices. The document does not contain acceptance criteria or a study that extensively describes device performance against such criteria. The 510(k) clearance process primarily relies on demonstrating substantial equivalence to a predicate device rather than undergoing extensive clinical trials with predefined acceptance criteria as might be seen for novel devices requiring PMA.

Therefore, many of the requested details about acceptance criteria, specific performance studies, sample sizes, ground truth establishment, and MRMC studies are not present in the provided text.

Based on the available text, here's what can be inferred or explicitly stated:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly define acceptance criteria in terms of numerical performance thresholds (e.g., sensitivity, specificity, accuracy, or quantitative measurement error) that the PET VCAR device needed to meet. Instead, the "performance" discussed is related to its functional capabilities and equivalence to predicate devices.

Acceptance Criteria	Reported Device Performance
Functional equivalence to predicate devices (Volume Viewer Plus, Advantage Lung Analysis II, Advantage Fusion).	Device stated to be "substantially equivalent" in functional features to listed predicate devices.
Software Development, Validation, and Verification Process ensures performance to specifications, Federal Regulations, and user requirements.	Acknowledges that these processes are in place to ensure performance and control potential hazards.
No new potential safety risks compared to marketed devices.	Stated that "The PET VCAR does not result in any new potential safety risks and performs as well as devices currently on the market."
Ability to assist in diagnosis, staging, treatment planning, and monitoring treatment response.	Device description outlines these capabilities (highlighting, bookmarking, SUV/volume measurement, multiexam comparison, IDA spreadsheet).
Automatic highlighting and bookmarking based on user-defined threshold settings.	Explicitly stated as a feature.
Measurement of Standard Uptake Value (SUV) and volume for PET defined metabolic activity.	Explicitly stated as a feature.
Automatic propagation of bookmarks from one time point to another.	Explicitly stated as a feature.
Interactive Data Analysis (IDA) spreadsheet for compiling and managing analytical information.	Explicitly stated as a feature.

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

Not provided in the document. The 510(k) summary focuses on substantial equivalence based on technical characteristics and intended use, rather than a detailed performance study with a specific test set.

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

Not provided in the document. Since no explicit test set or ground truth establishment is detailed for clinical performance, this information is absent.

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

Not provided in the document. No adjudication method is mentioned as a dedicated performance study is not 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 comparative effectiveness study was not explicitly mentioned or detailed. The device's role is described as "assist in diagnosis" and "improving analysis and workflow," but no quantitative measure of human reader improvement with the AI assistance is provided. The 510(k) submission does not include data on the effectiveness of human readers with AI versus without AI assistance.

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

No, a standalone performance study was not explicitly mentioned or detailed. The device is described as a "software package which can be used by the clinician to assist," indicating a human-in-the-loop design. It explicitly states, "PET VCAR does not provide or claim any automatic detection or automatic diagnosis of abnormal anatomy, structure or function." This confirms it's not a standalone diagnostic device.

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

Not provided in the document. As no specific performance study with a test set is detailed, the type of ground truth used is not mentioned.

8. The sample size for the training set:

Not provided in the document. The document does not discuss the training of the software's algorithms, and therefore, no training set size is mentioned.

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

Not provided in the document. Similar to point 8, this information is absent from the 510(k) summary.

Summary

Regulation Number and Section

§ 892.1750 Computed tomography x-ray system.

(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.