Search Results

The CEREC® inLab and CEREC® Scan Dental Restoration Milling Machines are intended to be used in the computer-aided design and milling of ceramic dental restorations, including inlays, onlays, veneers, crowns (full and partial), crown caps and bridge frameworks.

The CEREC® inLab and CEREC® Scan are identical stationary dental milling units consisting of the same hardware, software, and operating instructions. The table-top rectangular housing encases the motors, mechanical gears, position sensors, and the milling chamber. The milling chamber contains the laser scanner, two grinding burrs and the spindle for the ceramic block. The milling process is driven by electrical DC motors and stepper motors operating under microprocessor control. The laser scanner, mounted within the milling chamber, is used to scan impressions or models of the tooth or teeth. The scanned data is then transferred to a PC computer either via an RS232 interface cable connected to the serial interface port at the rear of the milling machine or via an optional wireless module. The PC contains the software that is used by the dentist or the dental technician to design the restoration from the scanned data. The restoration is then milled from a ceramic block in the milling chamber under microprocessor control using the design parameters.

This 510(k) summary for the CEREC® inLab and CEREC® Scan Dental Restoration Milling Machines primarily establishes substantial equivalence to a predicate device and focuses on the process of creating dental restorations, rather than detailed performance metrics typically associated with AI-driven diagnostic or prognostic devices. Therefore, much of the requested information (like acceptance criteria for AI performance, sample sizes for training/test sets, expert adjudication methods, MRMC studies, standalone performance, and ground truth types related to AI accuracy) is not explicitly present in this document.

The document discusses the approval of an additional capability (milling bridge frameworks) for an existing milling machine, asserting that the process for this new capability is the same as for previously approved restorations. The focus is on the mechanical and computer-aided design capabilities of the milling machine, not on an AI algorithm making diagnostic or predictive decisions.

Based on the provided text, here's what can be extracted:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly state quantitative acceptance criteria or detailed performance metrics in the way a diagnostic AI device would. The "performance" is primarily described by its equivalence to the predicate device and the functionality of its physical components.

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

• Not Applicable/Not provided. This document does not describe a study involving a "test set" in the context of evaluating an AI algorithm's performance on a dataset of patient data. The evaluation is based on engineering similarity and functional equivalence to a predicate device, focusing on the mechanical and CAD/CAM process.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not Applicable/Not provided. No "ground truth" establishment by experts for a test set is discussed, as the device is not an AI diagnostic tool.

4. Adjudication method for the test set:

• Not Applicable/Not provided.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done:

• No. An MRMC study is not mentioned as this device is a milling machine for dental restorations, not an AI-assisted diagnostic tool for human readers.

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

• Not Applicable/Not provided in the context of AI performance. While the milling machine operates "under microprocessor control" for the milling process, and "the PC contains the software that is used by the dentist or the dental technician to design the restoration," the document doesn't describe a standalone AI algorithm's performance independent of the human user designing the restoration or the physical milling process. The "standalone" aspect described is the machine's ability to mill based on design parameters.

7. The type of ground truth used:

• Not Applicable/Not provided in the context of typical AI device evaluation. The "ground truth" for this device would relate to the accuracy and fit of the physical dental restorations produced, and the ability of the machine to mill according to the digital design. This is implicitly covered by demonstrating substantial equivalence to a legally marketed predicate device and the described functionality.

8. The sample size for the training set:

• Not Applicable/Not provided. The document does not describe an AI model trained on a dataset. The software is used for design, and the machine for milling, which are deterministic CAD/CAM processes, not machine learning algorithms in the typical sense that require training sets.

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

• Not Applicable/Not provided. This device does not involve a training set with established ground truth in the context of machine learning.

Ask a specific question about this device