Search Results

INNOVISION-EXII is a stationery X-ray system intended for obtaining radiographic images of various anatomical parts of the human body, both pediatrics and adults, in a clinical environment. INNOVISION-EXII is not intended for mammography, angiography, interventional, or fluoroscopy use.

INNOVISION-EXII can receive X-ray signals from X-ray irradiation and digitize them into X-ray images by converting digital images to DICOM image format using Elui imaging software. INNOVISION-EXII is a general radiography X-ray system and not for mammography nor fluoroscopy. In addition, the system must be operated by a user who is trained and licensed to handle a general radiography X-ray system to meet the regulatory requirements of a Radiologic Technologist. Target areas for examinations include the head, spine, chest, and abdomen for diagnostic screening of orthopedic, respiratory, or vertebral discs. The system can capture a patient's postures, such as sitting, standing, or lying. This system can be used for patients of all ages, but it should be used with care for pregnant women and infants. The INNOVISION-EXII system has no part directly touching the patient's body.

The provided text describes a 510(k) summary for the INNOVISION-EXII stationary X-ray system, asserting its substantial equivalence to a predicate device (GXR-Series Diagnostic X-Ray System). However, the document does not contain information about acceptance criteria or a detailed study proving the device meets specific acceptance criteria related to its performance metrics for diagnostic imaging or AI assistance.

The "Clinical testing" section on page 9 merely states: "Clinical image evaluation of INNOVISION-EXII has been performed. The evaluation results demonstrated that INNOVISION-EXII generated images are adequate and suitable for expressing contour and outlines. The image quality including contrast and density are appropriate and acceptable for diagnostic exams." This is a very general statement and does not provide specific acceptance criteria or detailed study results.

Similarly, there are no details regarding AI performance (standalone or human-in-the-loop), sample sizes, ground truth establishment, or expert qualifications for such studies. The document focuses on establishing substantial equivalence based on intended use, technological characteristics, and compliance with various safety and performance standards (electrical safety, EMC, software validation, risk analysis).

Therefore, based solely on the provided text, the requested information about acceptance criteria and a study proving the device meets these criteria cannot be extracted or inferred. The document is a 510(k) summary focused on demonstrating substantial equivalence, not a detailed clinical performance study report.

Here is a breakdown of why each requested point cannot be addressed from the given text:

1. A table of acceptance criteria and the reported device performance: Not present. The "clinical testing" section is too vague.
2. Sample sized used for the test set and the data provenance: Not present. No specific test set for clinical performance is detailed.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not present. No ground truth establishment process is described beyond a general "clinical image evaluation."
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not present.
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: Not present. The document does not mention any AI component or MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not present. No mention of an algorithm or standalone performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not detailed. Only a general "clinical image evaluation" is mentioned.
8. The sample size for the training set: Not present. The document describes a medical imaging device, not a machine learning model requiring a training set.
9. How the ground truth for the training set was established: Not applicable, as there's no mention of a training set or machine learning components.

In summary, the provided FDA 510(k) summary largely focuses on engineering and regulatory compliance (electrical safety, EMC, software validation, comparison of technical specifications to a predicate device) to establish substantial equivalence, rather than detailed clinical performance metrics derived from a study with specific acceptance criteria and ground truth for diagnostic accuracy.

Ask a specific question about this device