FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

(1) 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 radiographs of jaws, parts of the skull and carpus for the purpose of cephalometric examination, if equipped with tele-radiographic arm (CEPH);

(III) the production of tomographic images of the head, including the ear, nose and throat (ENT), of the dentomaxillofacial complex, teeth, mandible and maxilla, temporomandibular-articular joint (TMI), other areas of the human skull and neck with sections of the cervical spine for use in diagnostic support, if equipped with the CBCT option. The device is operated and used by physicians, dentists, x-ray technologists and other legally qualified professionals.

Device Description

The Proposed device is a panoramic, cephalometric andiological system developed and manufactured by CEFLA S.C. The proposed device is a change of the predicate device: hyperion X9 pro (K190496). Like the predicate device the proposed device can be sold under three different product name and brands for commercial needs, without changing any of the basic safety, essential performances and functional features:

Like the predicate device hyperion X9 pro (K190496) the proposed device is equipped with X-ray tube generator and X-ray sensors (solid state X-ray imaging detectors) for dental panoramic (PAN), cephalometric radiography (CEPH) and cone beam computed tomography (CBCT). The proposed device permits to acquire radiological images (panoramic images, cephalometric images and 3D volumes) at varying radiographic angles by rotating around the patient following different trajectories depending on the selected examination. The exposed area can be adapted to a specific region of interest to keep the radiation dose as low as possible for the patient. This is achieved by collimating the x-ray beam and the adjustment of starting and ending points of the x-ray source and sensor movement. Furthermore, the radiation dose can be adapted by various parameters such as examination types and exposure technique factors. Class I lasers pointers are utilized to define reference lines for the patient position. The patient, stabilized through adjustable patient supports, can sit or stand. Control panel allows user actions as: height adjustment, selection of examination, and exposure parameters and delivers information about the unit status. The obtained digital image data are processed to provide a reconstructed image. The images are transferred to a computer, in real time or later depending on the needs and choice of the operator. The software used to manage the images, essential for CBCT acquisitions, is NNT/iRYS, a radiological imaging software developed by CEFLA S.C.

AI/ML Overview

The provided text describes a 510(k) premarket notification for a dental X-ray system, comparing a proposed device (hyperion X9 pro, NewTom GiANO HR, X-RADiUS TRiO PLUS) to a predicate device (hyperion X9 pro, K190496). The submission focuses on demonstrating substantial equivalence, particularly related to the introduction of new 2D X-ray sensors.

Based on the provided text, the device in question is not an AI-powered device; it is a general dental X-ray imaging system. Therefore, the detailed acceptance criteria and study design elements typically associated with AI/ML-based medical devices (such as MRMC studies, sample sizes for test/training sets, expert adjudication, or ground truth establishment for AI performance) are not applicable or reported in this document.

The "acceptance criteria" discussed in this document relate to the performance and safety standards that the medical device must meet to demonstrate substantial equivalence to a legally marketed predicate device. The text does not detail specific performance thresholds or how the device as an AI would be evaluated. Instead, it confirms compliance with general medical device standards.

Here's a breakdown of what is available and what is not for the requested points, given that this is not an AI device:

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

Acceptance Criteria (as implied by the document for a general medical device): Compliance with recognized consensus standards for medical electrical equipment, radiation protection, and software.
- IEC 60601-1: Medical electrical equipment (basic safety and essential performance)
- IEC 60601-1-2: Electromagnetic compatibility
- IEC 60825-1: Safety of laser products
- IEC 60601-1-3: Radiation protection in diagnostic X-ray equipment
- IEC 62366: Application of usability engineering
- IEC 62304: Medical device software Software lifecycle processes
- IEC 60601-2-63: Dental extra-oral X-ray equipment (particular requirements)
- IEC 60601-1-6: Usability
- Demonstration of equivalent or lower radiation dose (DAP values).
- Demonstration of equivalent image quality.
Reported Device Performance (against these criteria):
- Radiation Dose: The Proposed Device showed "similar or lower measured DAP values than Predicate Device for the same selected exams."
  - Proposed Device (Sensors with scintillator): 11 mGy*cm2 to 126 mGy*cm2
  - Proposed Device (Direct conversion sensors): 7 mGy*cm2 to 103 mGy*cm2
  - Predicate Device (Sensor with scintillator): 13.01 mGy*cm2 to 229.81 mGy*cm2
- Mechanical & Technical Features: Largely identical or with justified differences that do not negatively affect safety or performance (e.g., new direct conversion sensors, updated firmware/software to manage new sensors, but conforming to standards).
- Image Quality: "The results of the image quality review have demonstrated that the device is substantially equivalent to the predicate device." (No specific metrics or quantitative values are provided for image quality beyond this statement).
- Software Validation: Updated firmware and viewing software for new sensors were managed according to IEC 62304 and FDA Guidance on Medical Device Software.
- Electrical Safety & EMC: Complies with IEC 60601-1:2012 and IEC 60601-1-2:2014.

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

Not applicable / Not specified for AI performance. This document describes non-clinical performance testing (e.g., electrical safety, EMC, radiation output, image quality review) of the X-ray system itself, not a test set for an AI algorithm.
The document states "The results of the Non-clinical performance testing support substantial equivalence." No specific "test set" sample size in the context of diagnostic performance (e.g., number of patient images) is mentioned.
Data Provenance: Not explicitly stated, but the testing would likely have been conducted by the manufacturer (CEFLA S.C.) in Italy, given their location. The nature of the testing (bench testing, phantom imaging, etc.) suggests it's not patient data for an algorithm.

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):

Not applicable. There is no mention of a "test set" requiring expert-established ground truth for diagnostic performance, as this is not an AI device. The "image quality review" is mentioned, but without details on experts or methodology.

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

Not applicable. No adjudication method is mentioned as this is not an AI device or a study involving human reader performance evaluation in a diagnostic context.

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. The document explicitly states: "Given the differences from the predicate device, no human clinical studies have been considered necessary to support substantial equivalence." Therefore, no MRMC study was performed, and no AI assistance is part of this device.

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

Not applicable. This device does not feature a standalone algorithm in the context of AI. It is an X-ray imaging system.

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

Not applicable in the AI context. Ground truth in this submission pertains to the physical and technical specifications of the device, confirmed through engineering measurements, compliance with standards, and comparison to the predicate device's established performance parameters. For image quality, it's inferred that the review was against expected image characteristics for such a system, rather than diagnostic outcomes.

8. The sample size for the training set:

Not applicable. This is not an AI/ML device, so no training set for an algorithm is mentioned or relevant.

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

Not applicable. As above, no training set for an AI/ML algorithm is involved.

Summary

Regulation Number and Section

§ 892.1750 Computed tomography x-ray system.

(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.