Search Results

EFAI CARDIOSUITE SPECT MYOCARDIAL PERFUSION AGILE WORKFLOWS is an image processing software that provides analysis on DICOM images acquired from GE Medical Systems Nuclear Quantitative Perfusion SPECT software to support appropriately trained healthcare professionals in the evaluation and assessment of myocardial perfusions.

It provides the following functionality:

• Segmentation of the Bull's Eye images from the original DICOM
• Analysis of the Bull's Eye images to help assess perfusion
• Custom settings to generate text reports

The results of this processing may be used to aid in evaluating and assessing myocardial perfusions.

The system is an adjunct tool for GE Medical Systems Nuclear Quantitative Perfusion SPECT software.

The device allows users to interact with the software application via a web interface to upload, inspect, assess myocardial perfusion from Bull's Eye images. The user can change the quantitative settings to correct for numerical calculations and clinical adjustments.

The device is designed to take images produced by GE Medical Systems Nuclear Quantitative Perfusion SPECT software and process the data to provide both numerical analysis of the Bull's Eye images to help assess for myocardial perfusions, and generate a report based on the users report settings and preference.

The algorithm segments bull's eye images from SPECT images generated by GE's workstation and conducts quantitative analysis based on the color settings set by the user. The color scale is designed to follow GE's design convention, where the color red is indicative of a normal condition and blue representing severe perfusion. Each of the 17 segments would produce a quantitative evaluation under rest and stress conditions based on the color scale. The clinician would then design and fill in diagnosis terminologies that is best suited for each associated numerical results of each segment and generate a template report documenting the patient's condition.

Based on the provided text, the document is a 510(k) Premarket Notification from EverFortune.AI Co., Ltd. for their device, EFAI CARDIOSUITE SPECT Myocardial Perfusion Agile Workflows. The primary purpose of this document is to demonstrate "substantial equivalence" to a legally marketed predicate device (AutoQUANT® Plus) rather than providing detailed performance data from a clinical study for specific acceptance criteria.

The document explicitly states: "EFAI SPECT Workflows did not require clinical study since substantial equivalence to the currently market and predicate device was demonstrated with the following attribute: Principle of Operation; Indications for Use; Fundamental scientific technology; Non-clinical performance testing: Safety and effectiveness."

Therefore, much of the requested information regarding "acceptance criteria" based on a study proving the device meets the criteria, particularly clinical performance data, is not present in this 510(k) summary because a clinical study was not conducted or deemed necessary for this submission. The tests performed were non-clinical, focusing on software verification and validation, and usability engineering.

Here's a breakdown of the information that can be extracted or inferred, and what is explicitly not available:

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

• Acceptance Criteria: No specific numerical acceptance criteria (e.g., minimum sensitivity, specificity, or image quality scores) from a performance study are provided in this document. The "criteria" for this 510(k) submission appear to be demonstrating substantial equivalence through non-clinical testing and comparison of technological characteristics with the predicate device.
• Reported Device Performance:
  • Non-Clinical Tests: "Results confirm that the design inputs and performance specifications for the device are met." (General statement, no specific metrics provided).
  • Standards Met:
    • Software verification and validation per IEC 62304/FDA Guidance
    • Application of usability engineering to medical devices - Part 1 per IEC 62366-1
    • Guidance on the application of usability engineering to medical devices per IEC 62366-2

Table (based on inferred "acceptance" for substantial equivalence and reported non-clinical performance):

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

• Sample Size for Test Set: Not specified. Since no clinical study was performed, there isn't a "test set" of patient data in the sense of a clinical trial. The non-clinical testing would have used various test cases and scenarios, but the number of these is not disclosed.
• Data Provenance: Not specified for the non-clinical tests. For the intended use of the device, it processes DICOM images acquired from GE Medical Systems Nuclear Quantitative Perfusion SPECT software. The origin of the training data is not mentioned.

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

• This information is not available as no clinical study with expert-established ground truth on a test set was conducted for this 510(k) submission.

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

• This information is not available as no clinical study with a test set requiring adjudication was conducted.

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 study was done. The document explicitly states: "EFAI SPECT Workflows did not require clinical study". Therefore, no effect size of human reader improvement with AI assistance is provided.

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

• The document describes the device as "image processing software that provides analysis on DICOM images... to support appropriately trained healthcare professionals in the evaluation and assessment of myocardial perfusions." It's stated as an "adjunct tool." While software verification and validation were done, indicating standalone technical performance testing, no specific "algorithm only" performance metrics comparable to a clinical study (e.g., sensitivity/specificity for a clinical outcome) are reported. The focus was on software functionality and compliance with standards.

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

• This information is not available as no clinical study with established ground truth was conducted. For the non-clinical software tests, the "ground truth" would be determined by the software's specified design outputs and expected behavior, not clinical expert consensus or pathology.

8. The sample size for the training set

• The sample size for the training set is not specified in this document. The document focuses on demonstrating substantial equivalence, not detailing the development or training of the AI components.

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

• How the ground truth for the training set was established is not specified in this document. Similar to point 8, the focus of this 510(k) summary is on equivalence and non-clinical validation, not on the specifics of algorithm development and training data curation.

Ask a specific question about this device