Search Results

The E-Scan is intended for diagnostic nuclear magnetic resonance imaging of the hip, leg, knee, ankle, foot, shoulder, elbow, forearm, wrist and hand. The device produces transverse, sagittal, coronal and oblique cross-sectional images, displaying the internal structure of the limbs and joints being imaged. The images that are produced correspond to the spatial distribution of protons (hydrogen nuclei) that check the magnetic resonance properties and depend upon the MR parameters (spin-lattice relaxation time (T1), spin-spin relaxation time (T2), nuclei density, flow velocity and chemical shift). If interpreted by a medical expert, these images can provide diagnostically useful information.

The system preliminarily named "Artoscan S" is going to be commercialized under the trade name "E-Scan". The changes performed, with respect to the cleared version, are due to the optimization process of the system, in particular in relation to an improvement of the accessibility inside the gantry and therefore toward a greater patient comfort. The intended use of the modified device has not changed as a result of the modifications nor such modifications alter its fundamental scientific technology.

The E-Scan is a Magnetic resonance diagnostic device. It is a System, Nuclear Magnetic Resonance Imaging. The changes performed, with respect to the cleared version (Artoscan S), are due to the optimization process of the system, in particular in relation to an improvement of the accessibility inside the gantry and therefore toward a greater patient comfort.

Here's an analysis of the provided K990968 document, focusing on acceptance criteria and supporting studies.

It's important to note that this document is a 510(k) summary for a Magnetic Resonance Diagnostic Device (E-Scan) from 1999. The submission focuses on demonstrating substantial equivalence to a predicate device (Artoscan S), rather than presenting a performance study with detailed acceptance criteria as one might expect for a modern AI/software device. Therefore, many of the requested categories for AI device studies will not be directly applicable or present in this type of submission.

Acceptance Criteria and Device Performance (Based on Substantial Equivalence)

The acceptance criteria here are implicitly based on demonstrating that the E-Scan device is substantially equivalent to its predicate device, the Artoscan S. The performance metrics are relative to the predicate, showing that the E-Scan maintains or improves upon the predicate's capabilities.

Study Information (Based on the K990968 Submission):

The provided document is a 510(k) summary, which for a device like an MRI, primarily focuses on demonstrating substantial equivalence to a previously cleared predicate device. It typically does not include a detailed, prospective clinical performance study with the types of metrics and specific methodologies you'd find for a novel AI diagnostic device.

Here's an attempt to answer the questions based on what can be inferred from this type of submission, or noting what is not applicable:

1. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

   • Not Applicable / Not Provided. This 510(k) submission does not describe a clinical test set or study in the way an AI/software device would. The "study" here is essentially a technical comparison demonstrating that the modifications to the Artoscan S (to become E-Scan) do not alter the fundamental safety or effectiveness and that the new specifications are within acceptable ranges or represent improvements.
   • There is no mention of patient data, retrospective or prospective studies, or country of origin for such data.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

   • Not Applicable. Since no specific test set and ground truthing process for diagnostic performance are described, this information is not provided. The intended use states that images, "If interpreted by a medical expert, these images can provide diagnostically useful information," implying that medical experts (like radiologists) would interpret the output, but this is not part of a performance study setup in this document.

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

   • Not Applicable. No test set or related adjudication is described.

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:

   • No, this was not done. This is a 1999 submission for an MRI hardware device, not an AI-powered diagnostic tool. The concept of "human readers improve with AI" is not relevant here.

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

   • Not Applicable. This is an MRI scanner, not an algorithm. Its performance is inherent in the image quality and physical specifications.

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

   • Not Applicable. No explicit ground truth for diagnostic performance is mentioned. The implicit "ground truth" for the substantial equivalence claim is the performance and specifications of the predicate device (Artoscan S).

7. The sample size for the training set:

   • Not Applicable. This device is an MRI machine; it does not utilize a "training set" in the context of machine learning.

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

   • Not Applicable. As there is no training set for a machine learning model, this question does not apply.

Summary of this 510(k) Submission:

This 510(k) for the E-Scan MRI machine is a request for clearance based on substantial equivalence to a previous version of the device (Artoscan S). The "study" involves a side-by-side technical comparison of specifications and features, demonstrating that the E-Scan either maintains the same capabilities as the predicate, offers minor improvements (like patient comfort or ease of use for certain anatomical regions), or has minor technical differences (e.g., slices per echo, homogeneity figures) that don't negatively impact safety or effectiveness for the stated intended use. A formal clinical study with patient data, ground truth establishment, or reader performance metrics, as would be expected for a modern AI medical device, is not part of this type of submission.

Ask a specific question about this device