Search Results

PIUR tUS inside System is a computer-aided detection device intended to assist and support medical professionals in the diagnostic workflow of thyroid and thyroid nodules acquired from FDA-cleared ultrasound systems, including image documentation, analysis, and reporting. The device supports the physician with additional information during image review, including quantification and visualization of sonographic characteristics of thyroid nodules.

PIUR tUS inside System may be used on any adult patient aged 22 and older, independent of gender, linguistic and cultural background, or health status, unless any of the contraindications apply.

The PIUR tUS inside System acts as part of the diagnostic chain and must not be used as a sole source for treatment decisions, but as an add-on solution to regular 2D ultrasound imaging.

The PIUR tUS inside System is not intended for body contact (including skin, mucosal membrane, breached or compromised surfaces, blood path indirect, tissues, bones, dentin, or circulation blood).

PIUR tUS inside is a medical device which enhances standard ultrasound devices with a three-dimensional (3D) tomographic imaging method for a 3D analysis of ultrasound volumes. With PIUR tUS inside, examining physicians can make diagnostic decisions based on standard 2D as well as 3D image data integrated in an ultrasound device environment. This 3D data provides information which previously could have only been generated using other 3D imaging technologies like CT or MRI.

The PIUR tUS inside runs on a compatible GE Healthcare ultrasound system. The PIUR tUS inside takes as an input a sequence of 2D ultrasound images that are transmitted through a software interface from the ultrasound to the PIUR tUS inside. In addition, the PIUR Sensor must be clipped onto the ultrasound transducer using individually designed PIUR Brackets. For image acquisition, the user moves the 2D ultrasound transducer perpendicular to the structure to be imaged over the region of interest of the patient's body. An inertial measurement unit (IMU), which is built into the PIUR Sensor, tracks the orientation of the transducer during the scan and sends this information to the ultrasound via Bluetooth.

The PIUR tUS inside combines image information and sensor information to generate tomographic 3D ultrasound volumes on which image analysis can be performed. An important property of this method is the unlimited length of the acquired volume. PIUR tUS inside therefore allows recording and analyzing a complete thyroid lobe.

The PIUR tUS inside and the PIUR tUS Infinity Predicate Device share most hardware and software components and algorithms. On the hardware side, both systems use the same PIUR Sensor to track probe movement during a freehand ultrasound acquisition. The data from the PIUR Sensor is transferred wirelessly through a Bluetooth connection to the software where it is being used to generate ultrasound volumes from the freehand sweep. Both systems also share the same volume compounding software algorithms, semi-automatic lobe and nodule segmentation algorithms, and volume calculation algorithms. The performance for image compounding and volume calculations are therefore the same for both systems.

The main difference between the PIUR tUS inside System and the Predicate Device is the interface for image retrieval. While the Predicate Device uses the Infinity Box to transfer digital ultrasound images from a third-party ultrasound system to the software through a Wi-Fi connection, the PIUR tUS inside has direct access to the image stream through a software interface. It runs directly on the compatible ultrasound scanners: GE Healthcare LOGIQ E10 (K231966) and GE Healthcare LOGIQ E10s/Fortis (K231989). This, however, is not performance relevant as the image data remains the same. It only reduces the number of compatible ultrasound systems as a close collaboration with the ultrasound manufacturer is required.

The PIUR tUS inside System acts as part of the diagnostic chain only and must not be used as a sole source for diagnostic or treatment decisions.

The solution is intended to be used on patients aged 22 and older, independent of gender, linguistic and cultural background, or health status, unless any of the contraindications apply, in a non-sterile environment. The solution is not intended to be used on patients with open wounds or irritated skin or during surgery.

The provided FDA 510(k) clearance letter and summary for PIUR tUS inside (K250484) does not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a study that proves the device meets them.

The document primarily focuses on establishing substantial equivalence to a predicate device (PIUR tUS Infinity, K240036) by demonstrating similar intended use, technological characteristics, and principles of operation, rather than providing a detailed clinical performance study with specific acceptance criteria, sample sizes, expert qualifications, or comparative effectiveness.

However, based on the information available in the document, here's what can be extracted and inferred:

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

The document does not explicitly state acceptance criteria in a quantitative manner as one might find in a clinical study report. Instead, the "Performance Data" section indicates that software performance, verification, and validation testing demonstrated that the PIUR tUS inside System met all design requirements and specifications.

It also states that the device was tested for electrical safety, EMC, and a white-noise test was conducted to verify that the wireless equipment does not induce additional white noise or degrade ultrasound image quality. These are performance aspects, but not specific clinical or diagnostic accuracy acceptance metrics.

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

The document mentions "performance validation testing" and "software verification and validation testing," but it does not specify the sample size used for these tests. It also does not provide details on the data provenance (e.g., country of origin, retrospective or prospective nature) for any datasets used in these tests. The only clue is that the device assists in diagnosing thyroid and thyroid nodules acquired from FDA-cleared ultrasound systems.

3. 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):

The document states under "Ground Truth Establishment" in the Substantial Equivalence Comparison Table:
"The ground truth to be established for performance studies of the device are annotated data sets labeled by medical specialists."

However, it does not specify the number of experts used, their qualifications (e.g., specific specialties, years of experience), or their accreditation.

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

The document does not describe any adjudication method used for establishing the ground truth for the test set.

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:

The document does not mention or describe a multi-reader multi-case (MRMC) comparative effectiveness study. The device is described as a "computer-aided detection device intended to assist and support medical professionals" and an "add-on solution to regular 2D ultrasound imaging," implying a human-in-the-loop scenario. However, no study demonstrating the improvement of human readers with AI assistance is detailed.

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

The document states under "Performance Testing Data to Support SE Determination" in the Substantial Equivalence Comparison Table:
"Results from standalone performance testing of machine learning algorithm suggested ROIs of user-selected nodules."

This indicates that some form of standalone performance testing was conducted specifically for the segmentation ("suggested ROIs") of user-selected nodules. However, the details of this standalone performance (e.g., accuracy metrics, specific results) are not provided in this summary.

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

As mentioned above, the ground truth for performance studies is described as "annotated data sets labeled by medical specialists." This suggests an expert consensus or expert labeling approach, rather than pathology or outcomes data specifically.

8. The sample size for the training set:

The document does not specify the sample size used for the training set of the machine learning algorithms.

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

Similar to the test set, the document states generally: "The ground truth to be established for performance studies of the device are annotated data sets labeled by medical specialists." This implies the training set ground truth would also be established through expert labeling, but no further details are provided.

Summary of what is present vs. what is missing:

The provided 510(k) summary focuses heavily on demonstrating substantial equivalence through shared technological characteristics and general compliance with standards. It explicitly states that the device met "all design requirements and specifications" but lacks specific quantitative performance metrics (e.g., sensitivity, specificity, F1-score) or detailed clinical study results often found in AI/CAD device submissions. The information regarding ground truth establishment, sample sizes for training and testing, expert qualifications, and specific study designs (like MRMC or detailed standalone performance) is either very limited or entirely absent from this summary.

Ask a specific question about this device