(172 days)
The Lythos Digital Impression System in an optical impression system intended for use by dental professionals to record the topographical characteristics of teeth, gingiva, and/or palate or stone models. The Lythos Digital Impression System is intended for use in conjunction with the production of orthodontic and restorative dental appliances, including orthodontic aligners.
The Lythos Digital Impression System (DIS) is an optical impression system intended for use by dental professionals to record the topographical characteristics of teeth, gingiva, and/or palate or stone models. The Lythos DIS is intended for use in conjunction with the production of orthodontic and restorative dental appliances, including orthodontic aligners.
The Lythos DIS is a point-of-care turnkey imaging system used in the dental industry; the intra-oral wand hardware and personal computer (PC) based software form an integrated system that produces accurate, high resolution three dimensional (3D) digital images. The end result of an intra-oral patient scan is a 3D digital impression data file that accurately describes the surfaces of teeth, gingiva, and palate within a patient's oral cavity, or the surfaces of a stone model.
The system consists of a handheld wand connected to a computer which is housed in a base unit. The computer contains proprietary software to acquire, process, and store the digital 3D image data. Patient information is entered into the software using a touch screen monitor connected to the computer. To capture a 3D image of the patient's dental arch and/or bite, the operator moves the wand along the surface of the teeth to be scanned. A video camera inside the wand captures images of the teeth surfaces. Algorithms in the software process these images into a 3D image and display the 3D image on the computer monitor in real time. The software also saves the 3D image data and identifying patient information to be used by orthodontic or restorative appliance manufacturers to design and manufacture customized appliances. The Lythos DIS device is also equipped with wireless network capability for secure transfer of the 3D image data to the orthodontic or restorative appliance manufacturer.
The Lythos DIS is only used to gather the topography of the mouth and teeth, and to upload the data file (.stl) to the data cloud. The data is available to the licensed dental professional to send to a third party manufacturer. The Lythos DIS .stl data file is used in conjunction with CAD/CAM or 3D printing manufacturing processes. The proposed Lythos DIS is not used for the design, diagnosis or treatment planning of orthodontic aligners.
Based on the provided text, the Lythos Digital Impression System is an optical impression system for dental professionals. The document is a 510(k) premarket notification, aiming to demonstrate substantial equivalence to a predicate device, not necessarily to prove a new device's performance against specific acceptance criteria for AI/ML-based medical devices typically seen today.
Therefore, the information requested in the prompt, particularly related to AI/ML device performance, traditional clinical studies, and specific statistical performance metrics, is largely not present in this regulatory clearance document for a digital impression system. This device is a hardware/software system that captures 3D dental impressions, not an AI/ML algorithm for diagnosis or treatment planning.
However, I can extract information relevant to the device's "performance" in terms of its ability to capture accurate impressions, as well as the types of studies performed to demonstrate its safety and substantial equivalence to a predicate device.
Here's an attempt to answer your questions based only on the provided text, with clarifications where the information is not applicable or not present.
Device Name: Lythos Digital Impression System
Type of Device: Optical Impression System for CAD/CAM in dentistry
Analysis of Acceptance Criteria and Study Proof:
Since this is not an AI/ML device in the modern sense of requiring diagnostic performance metrics (e.g., sensitivity, specificity, AUC), the concept of "acceptance criteria" for an algorithm and "study that proves the device meets the acceptance criteria" as typically understood for AI/ML devices is not directly applicable here.
Instead, acceptance criteria are aligned with demonstrating substantial equivalence to a predicate device and ensuring safety and effectiveness for its intended use, typically through non-clinical performance data (e.g., accuracy, sterilization, EMC, safety testing).
1. A table of acceptance criteria and the reported device performance
The document does not present explicit "acceptance criteria" in the format of a table with numerical targets (e.g., sensitivity > X%, specificity > Y%). Instead, it focuses on demonstrating that the Lythos DIS has "technological characteristics very similar to the predicate device" and that "accuracy testing was performed per internal methods to demonstrate substantial equivalence."
| Element/Characteristic | Predicate Device (K122065) | Lythos Digital Impression System (Proposed) | Assessment/Performance (based on comparison) |
|---|---|---|---|
| Indications for Use | Orthodontic use (record topographical characteristics of teeth, gingiva, palate for orthodontic appliances) | Expanded: Orthodontic and restorative dental appliances, including orthodontic aligners (record topographical characteristics of teeth, gingiva, palate, or stone models) | Similar, but expanded for Lythos DIS. This expansion requires demonstrating continued substantial equivalence. |
| Target users | Dental Professionals trained in orthodontics | Dental Professionals | Broader for Lythos DIS. |
| Anatomical Sites | Upper and lower arches of teeth, left and right bite | Upper and lower arches of teeth, left and right bite | Identical |
| Technique to produce 3D images | Interferometry measurement of video camera images | Interferometry measurement of video camera images | Identical |
| Light used for illumination | Blue-violet (405 nm) | Blue-violet (405 nm) | Identical |
| Light source | Diode (laser) | Diode (laser) | Identical |
| Tooth coating | No tooth coating required | Optional tooth coating | Minor difference, not indicating inferiority. |
| Components | Handheld scanning wand, computer in housing, cable, touch screen monitor | Handheld scanning wand, computer in housing, cable, touch screen monitor | Identical |
| Key characteristics | Handheld wand moved over teeth; Real-time display of 3D images | Handheld wand moved over teeth; Real-time display of 3D images | Identical |
| Device Output | Software file (input to CAD/CAM dental processes) | Software file (.stl) (input to CAD/CAM dental processes or 3D printing) | Identical in format, slightly expanded in use (3D printing). |
| Storage Temperature | -10C - +50C | -10C - +50C | Identical |
| Operating Temperature | +10C - +35C | +10C - +35C | Identical |
| Operating Humidity | 30-85% non-condensing | 30-85% non-condensing | Identical |
| Patient contact areas; cross-contamination control | Wand tip is single use and disposable | Wand tip is single use and disposable | Identical |
| Operator contact areas - cross-contamination control | Surfaces disinfected using CaviCide | Surfaces disinfected using CaviCide | Identical |
| Checks of software and hardware function | Scan of verification target | Scan of verification target | Identical |
| Biocompatibility testing of patient contact areas | Passed based on ISO 10993-1:2009 | Has not changed since predicate (K122065) | Relied on predicate's testing. |
| Sterilization | Validated parameters for wrapped per ANSI/AAMI ST 79:2010 | Validated parameters for wrapped per ANSI/AAMI ST 79:2010 | Identical confirmation. |
| Safety Testing | IEC 60601-1, IEC 60601-1-2, IEC 62366 | IEC 60601-1, IEC 60601-1-2, IEC 62366 | Identical standards applied. |
| Internal temperature | Upper temp 85 | Upper temp 60 | Difference noted, but likely within acceptable safety limits. |
| Drives | 500 GB HD - disk based drive | 120 GB SSD - solid state drive | Improvement (SSD is faster/more durable), not a functional difference of concern. |
| Memory | 8GB Ram | 16 GB Ram | Improvement (more RAM), not a functional difference of concern. |
| Overall Performance | Established as predicate | "the Lythos DIS is safe and effective for its intended use" based on non-clinical data including "Accuracy testing...per internal methods to demonstrate substantial equivalence." | Found substantially equivalent. |
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
The document states:
- "No human clinical data has been provided to support substantial equivalence."
- Performance data relies on "Non-Clinical Performance Data" and "Internal specification and testing for Lythos Accuracy," "Internal specification and testing for Aligner Accuracy," and "Internal specification and testing to verify use of Surface Enhancement Products."
Therefore, details like sample size for a "test set" in the context of human data (patients/cases), data provenance (country, retrospective/prospective) are not applicable as no human clinical data was used for substantial equivalence. The "test sets" would be non-human elements (e.g., dental models, materials) used for engineering and performance validation. No specific sample sizes for these internal tests are mentioned.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
Not applicable/Not mentioned. Since no human clinical data was used, there were no "experts" establishing ground truth for patient cases as would be required for an AI/ML diagnostic algorithm. Ground truth for accuracy would likely be established by metrology standards for 3D scanning, which is not detailed here.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not applicable/Not mentioned. No human clinical test set, so no adjudication method for human readers.
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
No. This device is an image acquisition system, not an AI assisting human readers. No MRMC study was done, and no human-in-the-loop performance improvement with AI was assessed as there is no stated AI component in the traditional sense.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, in spirit, for the device's functional performance. The "Accuracy testing was performed per internal methods" acts as a standalone performance assessment of the device's ability to accurately capture 3D impressions. However, this is not a diagnostic algorithm's standalone performance in the context of sensitivity/specificity. The output is a data file (.stl), which is then used by a human (dental professional) and other CAD/CAM systems.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
For the "Accuracy testing," the ground truth would typically be established by highly precise metrology equipment or reference objects with known dimensions. The document does not specify the exact methods or reference standards used for this "internal methods" accuracy testing but implies an objective measure of "accuracy."
8. The sample size for the training set
The document does not detail how the internal algorithms for 3D image processing were "trained" in the machine learning sense. The device uses "algorithms in the software process these images into a 3D image." This is likely deterministic image processing / computational geometry, not typical machine learning training. Therefore, not applicable/Not mentioned in the context of ML training data.
9. How the ground truth for the training set was established
Not applicable/Not mentioned. See point 8.
§ 872.3661 Optical Impression Systems for CAD/CAM.
(a)
Identification. An optical impression system for computer assisted design and manufacturing (CAD/CAM) is a device used to record the topographical characteristics of teeth, dental impressions, or stone models by analog or digital methods for use in the computer-assisted design and manufacturing of dental restorative prosthetic devices. Such systems may consist of a camera, scanner, or equivalent type of sensor and a computer with software.(b)
Classification. Class II (Special Controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of the chapter subject to the limitations in § 872.9. The special control for these devices is the FDA guidance document entitled “Class II Special Controls Guidance Document: Optical Impression Systems for Computer Assisted Design and Manufacturing (CAD/CAM) of Dental Restorations; Guidance for Industry and FDA.” For the availability of this guidance document, see § 872.1(e).