(144 days)
The EAGLE EDGE AXR90 and AXR120 are CBCT / Panoramic / Cephalometric X-Ray units designed to obtain 2D and 3D radiological images of the oral anatomy, including teeth, maxillofacial areas, oral structures, carpal images and head-neck bone regions. This system is exclusively for dental use and should be handled only by qualified health professionals.
EAGLE EDGE Models AXR90, AXR120 are complete 3-in-1 dental imaging systems capable of generating panoramic, cephalometric and tomographic images using cone beam computerized tomography (CBCT) technique. The AXR90 has a maximum kVp of 90 while the AXR120 has a maximum kVp of 120. The digital acquisition process utilizes one or more X-ray sensors and automatic image processing that allow you to increase the speed of diagnosis and improve the workflow of your clinic.
The provided document does not contain a detailed study proving the device meets specific acceptance criteria with reported device performance metrics in a table. It primarily outlines the non-clinical and clinical testing performed to establish substantial equivalence to a predicate device.
However, based on the information provided, here's a breakdown of what can be extracted and inferred regarding acceptance criteria and the study:
1. Table of Acceptance Criteria and Reported Device Performance:
The document does not present a formal table of acceptance criteria with corresponding device performance metrics. Instead, it offers a qualitative assessment of imaging equivalence and software feature effectiveness.
| Acceptance Criteria (Inferred from testing) | Reported Device Performance |
|---|---|
| Safety Standards (Electrical, EMC) | All standards tests passed. |
| Biocompatibility | All tests passed. |
| Software Validation | Performed according to FDA guidance for moderate level of concern. |
| Cybersecurity | Compliance with FDA Guidance recommendations. |
| Image Quality (Equivalence to predicate) | Images found to be equivalent or better than predicate device. |
| Effectiveness of Motion Artifact Reduction Software | Found to be effective. |
| Effectiveness of Metal Artifact Reduction Software | Found to be effective. |
2. Sample Size and Data Provenance:
- Test Set Sample Size: The document does not specify a numerical sample size for the "Sample X-Ray images" taken for evaluation. It only states that images were taken "across the different operational modes".
- Data Provenance: The document indicates that the evaluation was performed by a "USA Board Certified Radiologist" implying the data was evaluated in the USA, but the country of origin of the actual patients for the "Sample X-Ray images" is not explicitly stated. The manufacturer is from Brazil (Alliage S/A Indústrias Médico Odontológica, Rodovia Abrão Assed, ... Ribeirão Preto - São Paulo- Brazil), so it's possible the images were generated in Brazil. The study is retrospective in the sense that the images were taken and then evaluated, but it's not explicitly labeled as such.
3. Number of Experts and Qualifications:
- Number of Experts: At least one expert. The document states, "Image evaluation was performed by both licensed dentist and a USA Board Certified Radiologist." and "These images were evaluated by an American Board of Radiology certified radiologist." This indicates one radiologist and at least one licensed dentist.
- Qualifications of Experts:
- "USA Board Certified Radiologist" or "American Board of Radiology certified radiologist."
- "licensed dentist."
4. Adjudication Method:
The document does not describe a formal adjudication method (like 2+1 or 3+1). It states that image evaluation was performed by multiple individuals ("both licensed dentist and a USA Board Certified Radiologist"), but it doesn't detail how disagreements, if any, were resolved or if a consensus mechanism was employed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
A full MRMC comparative effectiveness study, comparing human readers with and without AI assistance to quantify improvement, was not reported. The study focused on assessing the device's image quality and the effectiveness of its built-in software features (motion and metal artifact reduction) in a standalone capacity.
6. Standalone Performance:
Yes, a standalone performance assessment was done. The "Sample X-Ray images" taken by the device were evaluated by a radiologist to determine image quality and the effectiveness of the software features (motion and metal artifact reduction). This evaluation was of the algorithm's output without direct human-in-the-loop interaction for diagnostic decision-making improvement.
7. Type of Ground Truth:
The ground truth used for evaluating image quality and software effectiveness appears to be expert consensus/opinion. The "USA Board Certified Radiologist" and "licensed dentist" provided their professional opinions on the equivalence of images to the predicate and the effectiveness of the artifact reduction software. There is no mention of pathology or outcomes data as ground truth.
8. Sample Size for the Training Set:
The document does not specify a sample size for the training set. It mentions "software validation" but doesn't detail any machine learning models or their training data. The entire submission focuses on the X-ray units and their imaging capabilities, not on an AI diagnostic algorithm.
9. How Ground Truth for Training Set was Established:
Since a training set for an AI model is not explicitly mentioned, the method for establishing its ground truth is not provided. The document describes validations for safety, EMC, biocompatibility, and software in general, but not the specific training process for an AI component with an associated ground truth.
§ 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.