(108 days)
The DENTAL CT SCANNER AXR is 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.
The Dental CT Scanner AXR is a complete 4-in-1 dental imaging system capable of generating panoramic, cephalometric and tomographic images using cone beam computerized tomography technique (Cone Beam). The AXR90 has a maximum kVp of 90 while the AXR120 has a maximum kVp of 120. The digital acquisition process utilizes an X-ray sensor and automatic image processing that allow you to increase the speed of diagnosis and improve the workflow of your clinic.
Here's an analysis of the provided text regarding the acceptance criteria and study for the Dental CT Scanner AXR, presented in the requested format.
It's important to note that the provided text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed clinical study report for novel AI algorithms. Therefore, specific details common in AI/ML performance studies, such as effects of AI assistance on human readers, detailed ground truth establishment for a large test set, and precise metrics for algorithm-only performance against acceptance criteria, are not present in this type of document. The "device" in this context refers to the entire CT scanner, not a specific AI component for interpretation.
Acceptance Criteria and Device Performance Study for Dental CT Scanner AXR
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Criteria | Reported Device Performance | Comments |
|---|---|---|---|
| Safety | General Electrical Safety (IEC 60601-1) | All tests passed | Met |
| Electromagnetic Compatibility (IEC 60601-1-2) | All tests passed | Met | |
| Radiation Safety (IEC 60601-1-3, IEC 60601-2-63) | All tests passed | Met | |
| Biocompatibility (EN ISO 10993-1) | All tests passed | Met (for irritation, sensitization, cytotoxicity) | |
| Risk Analysis & Software Validation | Performed according to FDA guidance for moderate level of concern | Met | |
| Cybersecurity | Complied with FDA guidance recommendations | Met | |
| Performance | Image Evaluation | Images found to be equivalent or better than predicate device | Met (Qualitative assessment) |
| Manufacturing/Quality | Connection to Software | 100% tested | Met |
| Exposure Accuracy | 100% tested | Met | |
| Tube Voltage and Exposure Time | 100% tested | Met | |
| Reproducibility | 100% tested | Met | |
| Beam Quality | 100% tested | Met | |
| Tube Efficiency | 100% tested | Met | |
| Leakage Radiation | 100% tested | Met |
2. Sample Size Used for the Test Set and Data Provenance
The provided 510(k) summary does not mention a specific "test set" in the context of an AI algorithm's performance evaluation against ground truth. The performance data presented refers to the overall system's image quality and technical specifications.
- Sample Size: Not applicable in the context of an AI test set. The document states that "Each unit manufactured is 100% tested" for certain technical parameters. For image evaluation, a single statement is made: "Dental images were compared to the images obtained on the predicate device." This suggests a qualitative comparison rather than a quantitative study on a defined test set.
- Data Provenance: Not specified. Based on the manufacturer's location (Brazil), it's likely the "dental images" used for comparison were generated internally or through clinical partners in Brazil. The data is implicitly retrospective as it compares images from the new device to a predicate, not a prospective clinical trial.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Two experts are mentioned for image evaluation: "both licensed dentist and a USA Board Certified Radiologist." The exact number of licensed dentists is not specified (e.g., one or multiple).
- Qualifications:
- "licensed dentist" (general qualification)
- "USA Board Certified Radiologist" (specific high-level qualification in radiology)
4. Adjudication Method for the Test Set
No formal adjudication method (e.g., 2+1, 3+1) is described. The text states that "Dental images were compared to the images obtained on the predicate device and found to be equivalent or better," implying a consensus or agreement was reached by the experts during their evaluation, but no structured adjudication process is detailed.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done
No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not explicitly done. The document does not describe any study comparing human readers with and without AI assistance, nor does it provide an effect size for human reader improvement. The "Mult Slice" functionality is a software feature that enhances image quality for the reader by allowing virtual adjustment of the cutting plane, but it's not described as an AI-assisted diagnostic tool requiring an MRMC study.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
This device is not described as having a standalone artificial intelligence component that performs diagnostic tasks without human-in-the-loop. The "Mult Slice" panoramic software functionality described is an image processing feature, not a diagnostic AI algorithm. Therefore, no standalone algorithm-only performance study was conducted or is relevant based on the provided information.
7. The Type of Ground Truth Used
The concept of "ground truth" for a diagnostic AI is not directly applicable here. The evaluation of the device relied on:
- Technical Standards Compliance: Successful completion of tests against established international safety and performance standards (IEC, ANSI/AAMI, EN ISO).
- Expert Qualitative Image Comparison: Subjective assessment by a licensed dentist and a USA Board Certified Radiologist, comparing images from the new device to those from the predicate device.
8. The Sample Size for the Training Set
Not applicable. This document describes a medical imaging device (CT scanner) demonstrating substantial equivalence to a predicate, not an AI/ML algorithm that requires a training set. The "Mult Slice" function is described as a software functionality rather than a machine learning model that would be trained on data.
9. How the Ground Truth for the Training Set Was Established
Not applicable, as no training set for an AI/ML algorithm is described in this submission.
§ 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.