Search Results

hyperion X5 is an extraoral X-ray system for digital panoramic exams, tele-X-rays and tomographies, intended to: 1. produce orthopanoramic images of the maxillofacial region and carry out diagnostic examination on teeth, dental arches and other structures in the oral cavity:

2. produce X-ray images of dental arches, cranium parts, and carpus in support of cephalometric examinations, if equipped with tele-X-ray arm (CEPH);

3. produce tomographic images of the oral cavity and maxillofacial structures and carry out diagnostic examination on teeth, dental arches, structures of the oral cavity and some cranial bones, if equipped with CBCT option. The device is operated and used by physicians, dentists, x-ray technologists and other legally qualified professionals.

The proposed device is a panoramic (PAN, 2D), cephalometric (CEPH, 2D) and tomographic (CBCT, 3D) radiological system, that acquires radiological images by rotating around the patient. The rotating arm is attached to a support column capable of moving vertically through a motorized movement.

The system is equipped with X-ray tube generator and detectors (sensors) for dental panoramic (PAN), cephalometric radiography (CEPH) and cone beam computed tomography (CBCT).

The proposed device can be sold under three different product name and brands names for commercial needs, without changing any of the safety, electrical and functional features. The variants are:

1 hyperion X5 myray CEFLA S.C.
2 NewTom GO NewTom CEFLA S.C.
3 X-RADIUS COMPACT Castellini CEFLA S.C.

Wherever the proposed device is mentioned, it is intended the device with its three different trade/ device names: hyperion X5, NewTom GO and X-RADiUS COMPACT.

The provided document, a 510(k) Premarket Notification summary for the hyperion X5, NewTom GO, and X-RADiUS COMPACT dental X-ray systems, primarily focuses on demonstrating substantial equivalence to predicate devices rather than proving the device meets specific performance acceptance criteria for an AI/CADe system. Therefore, much of the requested information regarding AI acceptance criteria, ground truth establishment, expert adjudication, and MRMC studies is not present in this document.

The document discusses performance tests for image quality and geometrical accuracy, which are standard for X-ray imaging devices, but these are not framed as acceptance criteria for an AI or CADe output.

However, based on the information available, I can answer parts of your request concerning the overall device performance proof.

This device is an X-ray imaging system, not an AI/CADe system. Therefore, the questions related to AI-specific acceptance criteria, ground truth establishment for AI, expert adjudication for AI, and MRMC studies for AI assistance are not directly applicable to the information provided.

Here's what can be extracted and inferred from the document regarding the device's performance proof:

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

The document does not present specific quantitative acceptance criteria in a table format for a pass/fail study, similar to how AI/CADe systems are evaluated. Instead, it relies on demonstrating substantial equivalence to predicate devices. The "performance data" section describes the types of tests conducted and concludes that the results "demonstrated a substantial equivalence."

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

• Sample Size: The document does not specify the sample size (number of images or patients) used for any of the clinical or non-clinical performance tests. For phantom studies, specific phantom names (e.g., DIN 6868-5, suitable cylindrical phantom) are mentioned, but not the number of phantom images acquired. For clinical evaluations, it mentions "different hyperion X5 and hyperion X9 pro," "different patient," and "Same Patient," but no specific patient counts.
• Data Provenance: Not specified in terms of country of origin. The document states that "On-field Clinical Evaluation of hyperion X5 and end-users feedback report" was conducted, implying real-world data collection, but does not specify if it was retrospective or prospective. Given the context of a 510(k) submission for an imaging device, the data is typically from internal company testing or external collaborations, but the source is not detailed.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The document briefly mentions "expert professionals" in the Indications for Use for a reference device (hyperion X5 3D version) but provides no details on their role or qualifications in establishing ground truth for the performance tests. The device is intended to be used by "physicians, dentists, x-ray technologists and other legally qualified professionals."

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

Not specified. No adjudication method is mentioned for any of the performance evaluations.

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

• MRMC Study: No MRMC study is mentioned. This is expected as the device is an imaging system, not an AI-assisted diagnostic tool. The "Comparative Clinical Evaluation" mentioned (e.g., 2D Panoramic X-rays, CBCT) would typically involve comparisons of image characteristics by experts, but not a formal MRMC study on reader performance improvements with AI assistance.
• Effect Size of AI Assistance: Not applicable, as this is not an AI-assisted device.

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

Not applicable, as this is an X-ray imaging device, not a standalone algorithm.

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

The "ground truth" for this device's performance appears to be established through:

• Physical Phantom Measurements: For spatial resolution, low contrast resolution, noise, and geometric distortion using technical phantoms (e.g., QUART Technical Phantom, cylindrical phantom).
• Qualitative Expert Assessment of Clinical Images: In the "Comparative Clinical Evaluation" section, it implies expert review of images from different devices, assessing quality and "identification of main marker points." This is likely a qualitative assessment by an unnamed number of clinical professionals.

8. The sample size for the training set

Not applicable. This is not an AI/ML device that requires a training set.

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

Not applicable. This is not an AI/ML device that requires a training set.

Ask a specific question about this device

The Hyperion X5 device, 3D version machine, intended to:

I. produce orthopanoramic images of the maxillofacial region and carry out diagnostic examination on teeth, dental arches and other structures in the oral cavity;

II. produce tomographic images of the oral cavity and maxillofacial structures and carry out diagnostic examination on teeth, dental arches, structures of the oral cavity and some cranial bones.

The subject device Hyperion X5 is a dental radiographic imaging system, that consists of two image acquisition modes: panoramic and cone beam computed tomography (CBCT). Specifically designed for dental radiography of the teeth, jaws and oral structures, the subject device:

produces orthopanoramic images of the maxillofacial region and carry out diagnostic l. examination on teeth, dental arches and other structures in the oral cavity;

produces tomographic images of the oral cavity and maxillofacial structures and carry out II. diagnostic examination on teeth, dental arches, structures of the oral cavity and some cranial bones. Hyperion X5 has been developed according to FDA-Guidance "Guidance for the Submission of 510(k)'s for Solid State X-ray Imaging Devices".

The subject device can be sold under different brands and commercial names for commercial needs, without changing any of the safety, electrical and functional features.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

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

The document does not explicitly state formal "acceptance criteria" with numerical or categorical targets for performance metrics. Instead, it describes performance tests designed to demonstrate "substantial equivalence" to predicate devices. The implicit acceptance criterion is that the subject device's performance should be "substantially equivalent" to the predicate devices in the tested aspects.

Given this, the table below reflects what was tested and the reported outcome relative to the predicate devices.

Note: The document refers to "Images resolution (panoramic X-rays)" and then proceeds to discuss "3D performance evaluation" and "Clinical tests... in CBCT acquisition". It appears the "Images resolution" entry under non-clinical tests refers to 2D aspects, while the 3D aspects are covered separately.

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

• Test Set Sample Size:
  • Non-Clinical (Phantoms): The sample sizes are not explicitly stated as numbers of images or scans. Instead, it refers to the use of "a specific QUART phantom," "a specific geometric phantom," "an anthropomorphic phantom," and "phantom Catphan® 500." For the Catphan® 500, it mentions "a number of axial images extracted by the volumetric reconstructions." This suggests phantom data was used, not human subject data for these tests.
  • Clinical (Qualitative 3D CBCT): The sample size for the qualitative clinical evaluation is not explicitly stated as a number of cases or patients. It mentions examining images from "relevant clinical conditions: pediatric patient, Edentulous, third molar, Upper arch endodontics." This implies a selection of cases representing these conditions but the exact number isn't provided.
• Data Provenance: Not specified. The document does not indicate the country of origin of any clinical data or whether the phantom studies were conducted in a specific country.
• Retrospective or Prospective: Not specified. For the "clinical tests," it's unclear if these were prospectively acquired or retrospectively analyzed images. Given the phrasing "images obtained with the two devices," it could imply either.

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 does not detail how ground truth was established for the "clinical tests." It refers to "a qualitative evaluation of images obtained with the two devices focusing on relevant clinical conditions." It implies expert assessment for this qualitative evaluation but does not specify the number of experts, their qualifications, or the method used to establish ground truth or consensus.
• For the non-clinical phantom studies, the "ground truth" is inherently defined by the phantom properties and the physical measurements performed (e.g., resolution, geometry, MTF/NPS values). No human experts are involved in establishing this type of ground truth.

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

• The document does not describe any adjudication method for the qualitative clinical evaluation. It's unclear if multiple experts were involved and how discrepancies would have been resolved. For the quantitative phantom studies, adjudication by human experts is generally 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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted.
• This device is an X-ray imaging system (hardware), not an AI algorithm. Therefore, the concept of "human readers improve with AI vs without AI assistance" is not applicable in this context. The study focuses on demonstrating the imaging system's performance and equivalence to predicate devices, not on evaluating human reader performance or the impact of AI.

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

• This question is not applicable. The device is a "Computed tomography x-ray system" (hardware for image acquisition), not a standalone algorithm. The performance evaluation is of the imaging system itself.

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

• For Non-Clinical Tests: The ground truth was based on the objective physical properties of phantoms and established measurement methodologies for imaging parameters (e.g., resolution targets on a QUART phantom, geometric patterns on a geometric phantom, known properties of the Catphan® 500).
• For Clinical Tests (Qualitative): The document implies ground truth was established by expert judgment/qualitative evaluation of images from "relevant clinical conditions." However, the method, number of experts, and their qualifications are not detailed. It does not mention pathology or outcomes data.

8. The sample size for the training set

• This is not applicable. The Hyperion X5 is a conventional X-ray imaging system, not a machine learning or AI-driven algorithm that requires a "training set" in the context of AI model development.

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

• This is not applicable, as there is no training set for this type of medical device (conventional X-ray imaging system).

Ask a specific question about this device