Search Results

The iTero Element 5D is a diagnostic aid for the detection of interproximal caries lesions above the gingiva and for monitoring the progress of such lesions.

The iTero Element 5D is an integrated intraoral imaging system capable of 3D confocal optical impressions for CAD/CAM of dental devices, which also captures 2D color images and Near Infrared (NIR) images.

The iTero Element 5D consists of a scanning wand cradle, single-use, disposable, 5D barrier sleeve, iTero Element 5D Sleeve (protective sleeve), software (including GUI), and a computer hardware platform that is offered in two configurations:

1. Laptop Configuration, where the GUI is presented on a customer-provided PC Laptop Touchscreen;
2. Wheel Stand Configuration where the GUI is presented on a display panel that is mounted on a wheel stand base unit.
   The scanning wand and software, including the GUI, are common to both configurations.

The scanning wand which has 3 imaging capabilities: 1) 3D confocal optical impression, 2) 2D color imaging and 3) near infrared imaging (NIRI), is designed to be used with a single-use, disposable, scanning wand barrier sleeve ("5D barrier sleeve") during scans and a protective sleeve during storage. At the beginning of every scan, the single-use, disposable, 5D barrier sleeve is placed on the scanning wand's head. The wand tip is placed slightly above the patient's teeth and the scan is initiated. At the end of the scan, proprietary imaging software converts the scan into an image that is simultaneously presented alongside the 2D color images on the GUI display. The 3D confocal optical impression and 2D color images assist in orientation by providing an enhanced view of the scanned teeth, thus helping the user identify which areas (i.e. occlusal direction/angles) to view as NIR images. The 2D color image displays a close-up view of the teeth while the NIR Image translates the teeth structure (enamel and dentin) to different brightness levels.

Here's an analysis of the provided text regarding the iTero Element 5D device, focusing on its acceptance criteria and the supporting study information.

It is important to note that the provided document is a 510(k) summary for a medical device cleared by the FDA. Such documents often focus on demonstrating substantial equivalence to a predicate device rather than presenting extensive de novo clinical trial data. Therefore, some of the requested information, particularly detailed clinical study specifics, might not be explicitly present.

1. Table of Acceptance Criteria and Reported Device Performance

Based on the non-clinical performance testing section, the acceptance criteria are implicitly defined by the demonstration of "substantially equivalent manner relative to the predicate" for various parameters. The reported performance is a statement of this equivalence.

2. Sample Size Used for the Test Set and Data Provenance

The document does not specify sample sizes for the test sets in the non-clinical performance testing. It mentions "comparison testing" and "system level testing" but does not quantify the number of devices or scenarios tested for each parameter.

Data provenance (e.g., country of origin, retrospective/prospective) is also not mentioned. Given the nature of a 510(k) summary and the non-clinical focus, this information is typically not included.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

This information is not provided. The performance testing described is non-clinical, primarily focusing on physical and technical characteristics of the device and its components, rather than clinical evaluation against a "ground truth" established by experts in a diagnostic context. This would be more relevant in a clinical study for diagnostic accuracy.

4. Adjudication Method for the Test Set

This information is not provided. As the testing is non-clinical, an adjudication method in the traditional sense (e.g., for expert disagreement on ground truth) is not applicable.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly stated as performed. The document explicitly states: "Clinical performance testing was not conducted/provided." The device is described as a "diagnostic aid" but the primary focus of the submission is non-clinical equivalence. There is no mention of an AI component improving human reader performance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

A standalone performance study in the sense of algorithm-only diagnostic accuracy was not conducted or reported in this document. The device is hardware-based with integrated software and its function relies on a human operator to perform the scan and interpret the images. The testing focused on the performance of the device's imaging capabilities (e.g., image sharpness, signal-to-noise ratio).

7. The Type of Ground Truth Used

For the non-clinical performance tests, the "ground truth" would be objective measurements and established engineering standards. For example:

• Image Quality: Calibrated measurement systems for sharpness, field of view, signal-to-noise ratio against known targets.
• Barrier Testing: Standardized material property tests (e.g., ASTM standards) with defined thresholds for tensile strength, tear resistance, etc.
• Biocompatibility: Adherence to ISO 10993 series for material compatibility.
• Safety/EMC: Compliance with IEC standards.

There is no mention of ground truth established by expert consensus, pathology, or outcomes data, as these typically relate to clinical diagnostic accuracy which was not performed.

8. The Sample Size for the Training Set

The document does not mention a "training set" in the context of machine learning or AI development. The device described appears to leverage established imaging principles (Near Infrared Transillumination) rather than a deep learning model that requires a large training dataset. The software discussed controls display, storage, live stream, and camera functions, rather than performing automated diagnostic interpretations based on trained algorithms.

9. How the Ground Truth for the Training Set Was Established

As no training set is mentioned (see point 8), this information is not applicable.

Ask a specific question about this device