(136 days)
The StealthStation™ System, with StealthStation™ ENT software, is intended as an aid for locating anatomical structures in either open or percutaneous ENT procedures. Their use is indicated for any medical condition in which the use of stereotactic surgery may be appropriate, and where reference to a rigid anatomical structure, such as the skull, can be identified relative to images of the anatomy.
This can include, but is not limited to, the following procedures:
- · Functional endoscopic sinus surgery (FESS)
- · Endoscopic skull base procedures
- Lateral skull base procedures
The StealthStation™ ENT software helps guide surgeons during ENT procedures such as functional endoscopic sinus surgery (FESS), endoscopic skull base procedures, and lateral skull base procedures. The StealthStation™ ENT software runs on the StealthStation™ S8 Platform. The StealthStation system is an Image Guided System (IGS), comprised of a platform, clinical software, surgical instruments, and a referencing system (which includes patient and instrument trackers). The IGS tracks the position of instruments in relation to the surgical anatomy, known as localization, and then identifies this position on preoperative or intraoperative images of a patient.
The ENT software can display patient images from a variety of perspectives (axial, sagittal, coronal, oblique) and 3-dimensional (3D) renderings of anatomical structures can also be displayed. During navigation, the system identifies the tip location and trajectory of the tracked instrument on images and models the user has selected to display. The surgeon may also use the ENT software to create and store one or more surgical plan trajectories before surgery and simulate progression along these trajectories. During surgery, the software can display how the actual instrument tip position and trajectory relate to the plan, helping to guide the surgeon along the planned trajectory. While the surgeon's judgment remains the ultimate authority, real-time positional information obtained through the StealthStation™ System can serve to validate this judgment as well as guide.
Here's an analysis of the provided text, focusing on the acceptance criteria and study information for the StealthStation™ S8 ENT Software:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| 3D positional accuracy: mean error ≤ 2.0 mm | Positional Error: 0.88 mm |
| Trajectory angle accuracy: mean error ≤ 2.0 degrees | Trajectory Error: 0.73° |
Note: The reported performance metrics meet the acceptance criteria (0.88mm ≤ 2.0mm and 0.73° ≤ 2.0°).
Study Details
-
Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated as a number of "cases" or "patients." The testing involved "anatomically representative phantoms" and "a subset of system components and features that represent the worst-case combinations of all potential system components." The text does not provide a specific numerical sample size for the test set.
- Data Provenance: The data provenance is from "anatomically representative phantoms" and "laboratory and simulated use settings." It's not human patient data. As such, country of origin is not applicable in the typical sense; the data is generated from simulated environments. This is not retrospective or prospective clinical data.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The provided text does not mention the use of human experts to establish ground truth for the test set. The ground truth for positional and trajectory accuracy is inherent in the design and measurement capabilities of the "anatomically representative phantoms" and the testing methodology itself, which would involve precise physical measurements.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not applicable. The ground truth was established through physical measurements on phantoms, not through expert consensus requiring adjudication.
-
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, an MRMC comparative effectiveness study was not done. The device is a navigation system that aids surgeons, and the performance testing focuses on its accuracy rather than its impact on human reader (or surgeon) diagnostic/interpretative performance in a comparative study. Clinical testing "was not considered necessary prior to release as this is not new technology."
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, the accuracy testing described (positional error and trajectory error) represents the standalone performance of the algorithm and system, as measured on phantoms. This is the performance of the StealthStation™ S8 ENT Software itself in tracking and displaying anatomical information accurately, independent of direct human judgment during the measurement process.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The ground truth for the performance testing (accuracy) was established through physical measurements and known parameters of "anatomically representative phantoms." The expected or "true" position and trajectory within the phantom were precisely known, allowing for the calculation of measurement errors.
-
The sample size for the training set:
- Not applicable. The StealthStation™ S8 ENT Software is an Image Guided System (IGS) that relies on tracking and displaying pre-acquired patient images and instrument positions. It is not an AI/ML algorithm that requires a separate "training set" in the traditional sense of machine learning for classification or prediction tasks. Its functionality is based on established engineering principles and algorithms, not a trained model from a specific data set. The document refers to "Software Verification and Validation testing" which implies testing against requirements, not training data.
-
How the ground truth for the training set was established:
- Not applicable, as there is no mention of a "training set" in the context of an AI/ML algorithm that predicts or classifies. The software's functionality is deterministic based on its programming and inputs (like imaging data and tracker signals).
§ 882.4560 Stereotaxic instrument.
(a)
Identification. A stereotaxic instrument is a device consisting of a rigid frame with a calibrated guide mechanism for precisely positioning probes or other devices within a patient's brain, spinal cord, or other part of the nervous system.(b)
Classification. Class II (performance standards).