(130 days)
The INLIANT Surgical Navigation System (INLIANT) is a computerized navigational system intended to provide assistance in both pre-operative planning and the intra-operative surgical phase of dental implantation procedures. INLIANT provides software to pre-operatively plan dental implantation procedures and provides navigational guidance of surgical instruments.
INLIANT is intended for use for partially edentulous adult patients who require dental implants as part of their treatment plan.
INLIANT is a dynamic surgical navigation system designed to allow a clinician to plan a dental procedure and then provide accurate guidance in real-time as to the location of dental surgical tool's drill tip relative to the patient's anatomy and plant position during the dental surgical procedure.
INLIANT includes a stand-alone cart which provides mobility and structural support for the computer, monitor and the camera which consists of two high resolution optical image sensors and lens assemblies. The system also includes the handpiece (model WI-75 LED G cleared under K080939), Patient Trackers and Fiducial Kit.
Operation of INLIANT is based on optical tracking. Stereoscopic images of the markers on the Patient Tracker and a handpiece are captured by the camera above the surgical site. INLIANT software processes the captured images to determine the location and orientation of the hand piece with respect to the Patient Tracker which is rigidly attached to the patient. The position of the handpiece, drill and the planned implant position is overlaid on existing CBCT scans of the patient's jaw and displayed to the clinician.
The submitted document describes the K213392 510(k) summary for the INLIANT® Surgical Navigation System. This device is a computerized navigational system intended for dental implantation procedures, assisting in pre-operative planning and intra-operative guidance. The primary purpose of the validation study was to demonstrate substantial equivalence to a predicate device (K150222, X-Guide Surgical Navigation System) in terms of accuracy.
Here's an analysis of the acceptance criteria and the study that proves the device meets them:
1. A table of acceptance criteria and the reported device performance
The document provides a comparison table (page 5-6) outlining performance characteristics. The critical performance characteristic for this device is its accuracy at the drill tip.
| Acceptance Criteria | Reported Device Performance (INLIANT) | Predicate Device Performance (X-Guide) |
|---|---|---|
| Accuracy at the Drill Tip | ≤1.0mm | ≤1.0mm |
| Presentation Update Rate | Real time | Real time |
Note: The document explicitly states that the INLIANT system performed identically to the predicate device in terms of "Accuracy at the Drill Tip" and "Presentation Update Rate." The clinical study (described below) then aimed to confirm that the angular non-inferiority was met compared to the predicate's performance against freehand.
2. Sample size used for the test set and the data provenance
- Sample Size: A total of 23 implants were placed among 22 adult subjects in the clinical performance study.
- Data Provenance: The study was a single-clinic, confirmatory, non-randomized study. The subjects were dental clinic patients. The document does not explicitly state the country of origin, but given the FDA submission, it's typically assumed to be within the US or a region with comparable regulatory standards. The study appears to be prospective as it involved placing implants and following patients post-surgery.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not specify the number of experts used to establish the ground truth or their qualifications for the clinical performance study. It states that "Four investigators used INLIANT to place the dental implants." These investigators are presumably qualified dental professionals, but their specific qualifications (e.g., years of experience, specialization) are not detailed.
4. Adjudication method for the test set
The document does not describe an explicit adjudication method for the test set, such as 2+1 or 3+1 consensus. The ground truth (deviations between planned and placed implant positions) was established by "registering pre-operative and post-operative CBCT scans in a common reference," suggesting an objective measurement process rather than a subjective expert adjudication.
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
The study was a clinical performance study of the device (INLIANT), not a multi-reader, multi-case study comparing human readers with and without AI assistance. The study's objective was to confirm the device's accuracy and non-inferiority to the predicate device by measuring implant deviations, rather than assessing human reader performance improvement. The "AI" component here is the navigational system assisting a human operator, not a diagnostic AI analyzing images by itself or providing a read.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
This device is a surgical navigation system, inherently designed for human-in-the-loop use. It provides real-time guidance to a clinician during a procedure. Therefore, a standalone (algorithm only) performance assessment would not be relevant or feasible for this type of device. The accuracy assessment (≤1.0mm drilling accuracy) is a system-level performance metric that includes the device's software and hardware in operation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth for the clinical performance study was primarily objective measurements based on imaging data. Specifically, "lateral (coronal and apical) and angular deviations between the pre-planned implant positions and actual implant positions were measured by registering pre-operative and post-operative CBCT scans in a common reference." This method uses the physically placed implant's position as "ground truth" compared to the pre-planned position.
8. The sample size for the training set
The document does not provide a sample size for a "training set." This device is a surgical navigation system, not a machine learning model that typically undergoes a distinct training phase with a labeled dataset in the same way an image classification AI would. It's an engineered system with algorithms for real-time tracking and guidance. Its development would involve engineering design, calibration, and verification, rather than "training" on a large dataset of patient cases to learn to perform a task.
9. How the ground truth for the training set was established
As there is no "training set" in the context of a machine learning model, the concept of establishing ground truth for it does not apply in this document. The device's performance is validated through non-clinical bench testing (e.g., performance testing to evaluate tolerance analysis, latency, positional and tracking accuracy per ASTM F2554) and the clinical study described. The ground truth for these non-clinical tests would involve highly controlled experimental setups with known reference points and precise measurement instruments.
§ 872.4120 Bone cutting instrument and accessories.
(a)
Identification. A bone cutting instrument and accessories is a metal device intended for use in reconstructive oral surgery to drill or cut into the upper or lower jaw and may be used to prepare bone to insert a wire, pin, or screw. The device includes the manual bone drill and wire driver, powered bone drill, rotary bone cutting handpiece, and AC-powered bone saw.(b)
Classification. Class II.