Search Results

Planmeca Viso is a system intended to produce two-dimensional (2D) and three-dimensional (3D) digital X-ray images as well as three-dimensional (3D) optical images of the dento-maxillo-facial, cervical spine and ENT (Ear, Nose, and Throat) regions at the direction of healthcare professionals as diagnostic support for pediatric and adult patients.

The Planmeca Viso -X-ray unit uses cone beam computed tomography (CBCT) to produce three-dimensional (3D) images of the maxillofacial and ENT anatomies. Two dimensional (2D) images are produced with tomosynthesis method (panoramic) imaging) as well as conventional 2D radiography (cephalometric imaging, 2D views). In CBCT a cylindrical volume of data is captured in one imaging procedure. The data consists of several hundred sample images which are taken from different directions to cover a certain pre-programmed target area. These samples are used for 3D reconstruction (using a dedicated 3D reconstruction hardware) that can be viewed in three dimensions using separate workstation and Planmeca Romexis software.

The provided text does not contain detailed acceptance criteria or a comprehensive study report for the Planmeca Viso device that would allow for a complete response to all aspects of your request. Specifically, the document focuses on demonstrating substantial equivalence to a predicate device through technical comparisons and general performance claims, rather than detailing specific quantitative acceptance criteria for image quality or clinical performance and exhaustive evidence proving they are met.

However, based on the information provided, here's a partial response:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: For the AI Denoising feature evaluation, the study included eleven patients.
• Data Provenance: Not explicitly stated, but the submission is from a Finnish company (Planmeca Oy), suggesting the data could originate from Finland or other European countries. The study appears to be prospective for the AI denoising evaluation, as it explicitly describes "comparing images with no denoising and AI denoising" for 11 patients, implying new data collection. For the general clinical evaluation, it mentions evaluation of "human phantom images," which could be retrospective or simulated, but again, details are lacking.

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

• Number of Experts: Three dental professionals were involved in the evaluation of the AI Denoising feature.
• Qualifications of Experts: The specific qualifications (e.g., years of experience, subspecialty) of these dental professionals are not specified in the provided text.

4. Adjudication Method for the Test Set

• The adjudication method for the AI Denoising study is not explicitly stated. It mentions that a team of dental professionals "evaluated human phantom images" and that the AI denoising was "evaluated in a study performed by three dental professionals." It does not specify if they reached a consensus, if a majority vote was used, or if there was an independent adjudicator.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• A formal MRMC comparative effectiveness study comparing human readers with AI assistance vs. without AI assistance is not explicitly described in the provided text.
• The clinical evaluation mentions that the device's image quality was evaluated by "product relevant team of professionals who evaluated human phantom images," and this was "substantially equivalent to the evaluation performed on primary predicate device."
• The AI Denoising feature was evaluated by three dental professionals "by comparing images with no denoising and AI denoising," which is a comparative aspect. However, it doesn't quantify an "effect size of how much human readers improve with AI vs without AI assistance" in terms of diagnostic performance metrics. It only states the AI improved images to "produce diagnostic image quality."

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

• The AI Denoising feature was evaluated based on its "ability to produce diagnostic image quality in its intended application." While the evaluation involved human professionals comparing images, the goal was to assess the algorithm's output (denoised images). However, a purely standalone assessment without human input or comparison for decision-making is not explicitly detailed. The evaluation seems to be focused on the impact of the AI on image quality for human interpretation.

7. Type of Ground Truth Used

• For AI Denoising: The ground truth appears to be based on expert assessment/consensus (three dental professionals) regarding the "diagnostic image quality" of images with and without AI denoising.
• For General Image Quality: The clinical evaluation involved "human phantom images" assessed by "product relevant team of professionals," suggesting a form of expert assessment against an assumed standard of diagnostic suitability.
• For Bench Testing: The ground truth for bench testing (Sedentex and DIN 6868 Phantoms) would be the physical properties and known characteristics of the phantoms, with the device's performance measured against those.

8. Sample Size for the Training Set

• The sample size for the training set used for the AI Denoising feature (or any other AI component/algorithm) is not mentioned in the provided text.

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

• How the ground truth for the training set (if any was used for AI model development) was established is not mentioned in the provided text.

Ask a specific question about this device

Planmeca Viso is a system intended to produce two-dimensional (2D) and three-dimensional (3D) digital x-ray images as well as three-dimensional (3D) optical images of the dento-maxillo-facial, cervical spine and Throat) regions at the direction of healthcare professionals as diagnostic support for pediatric and adult patients.

The Planmeca Viso -X-ray unit uses cone beam computed tomography (CBCT) to produce three-dimensional (3D) images of the maxillofacial and ENT anatomies. Two dimensional (2D) images are produced with tomosynthesis method (panoramic) imaging) as well as conventional 2D radiography (cephalometric imaging, 2D views). In CBCT a cylindrical volume of data is captured in one imaging procedure. The data consists of several hundred sample images which are taken from different directions to cover a certain pre-programmed target area. These samples are used for 3D reconstruction (using a separate 3D reconstruction PC) that can be viewed in three dimensions using separate workstation and Planmeca Romexis software.

The provided text describes a 510(k) premarket notification for the Planmeca Viso, a CT X-ray system. However, the document focuses on establishing substantial equivalence to a predicate device rather than presenting detailed acceptance criteria and a study proving the device meets those criteria, as would typically be seen in a clinical performance study for an AI/CAD device.

The document primarily compares the technical characteristics and intended uses of the Planmeca Viso with its predicate device (Planmeca ProMax 3D Max) and reference devices. It states that "Results from performance bench testing demonstrate that Planmeca Viso produces substantially equivalent image quality compared to the predicate and reference devices," but does not provide specific acceptance criteria or the details of these performance bench tests.

Therefore, based on the provided text, it is not possible to fully answer all aspects of your request, especially regarding acceptance criteria, sample sizes, expert involvement, and ground truth establishment in a clinical performance study context for an AI device. The document is a regulatory clearance letter, not a detailed study report.

However, I will extract and infer what information is available and highlight what is missing.

Acceptance Criteria and Device Performance (based on provided text):

The document does not explicitly state quantitative acceptance criteria or corresponding device performance in a table format for diagnostic accuracy (e.g., sensitivity, specificity, AUC). Instead, the "acceptance criteria" appear to be met by demonstrating substantial equivalence to a predicate device in terms of intended use, technological characteristics, and image quality as determined through "performance bench testing."

Study Details (as much as can be inferred from the provided text):

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

   • The document mentions "performance bench testing" but does not specify the sample size of images or patients used for these tests.
   • Data provenance (e.g., country of origin, retrospective/prospective) is not mentioned.

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

   • This information is not provided. The document refers to "diagnostic support for pediatric and adult patients" at the "direction of healthcare professionals," but it does not detail the process of establishing ground truth for evaluating device performance.

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

   • This information is not provided.

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:

   • The document does not describe an MRMC study or any AI components, nor does it discuss human reader improvement with or without AI assistance. The device is a "Computed tomography x-ray system" (hardware).

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

   • The document focuses on the imaging system itself (hardware) rather than an AI algorithm. Therefore, "standalone performance" in the context of an algorithm is not applicable or discussed.

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

   • This information is not provided. For an imaging device, ground truth for image quality often involves quantitative metrics (e.g., spatial resolution, contrast-to-noise ratio, dose efficiency) derived from phantoms or objectively evaluated clinical images against a reference standard, but the specific methods are not detailed here.

7. The sample size for the training set:

   • This information is not applicable as the document describes a hardware device (CT X-ray system), not a machine learning/AI algorithm that would typically have a "training set."

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

   • This information is not applicable for the same reason as above.

Summary of Missing Information (Critical for a complete answer to your prompt):

The provided document is a 510(k) clearance letter for an imaging device (Planmeca Viso). It confirms the device's substantial equivalence to a predicate device. It lacks the detailed clinical study information (acceptance criteria, specific metrics, sample sizes, ground truth establishment, expert involvement, and reader studies) that would typically be required for evaluating the performance of an AI-driven diagnostic device. The "performance data" mentioned is stated to be from "bench testing" demonstrating image quality equivalence, rather than a clinical performance study with human readers or diagnostic accuracy metrics.

Ask a specific question about this device