(49 days)
ON3D is software that is designed for use by specialized dental practices for capturing, storing and presenting patient images and assisting in treatment planning and case diagnosis. Results produced by the software's diagnostic and treatment planning tools are dependent on the interpretation of trained and licensed dental practitioners.
ON3D is a stand-alone software that captures, stores and present patient data in volumetric views to assist specialized dental practitioners for treatment and surgical planning and case diagnosis. With a user-friendly graphical user interface, ON3D makes processing 3D data extremely simple, enabling dental specialists from a wide variety of disciplines to diagnose, plan treatment, document and present cases. ON3D allows visualization and analysis of craniofacial anatomy from data produced by 3D dataset format, such as cone beam computed tomography (CBCT), and it creates a personalized 3D model for the dentists with the optimal pre-surgical information necessary for the surgeries. It features tools for the manipulation and analysis of volumetric datasets, and the images are easily oriented and rotated. Tissue density thresholds can be adjusted for detailed views of craniofacial anatomy. ON3D product features include 3D airway analysis, multiple planar views, volume stitching, 2D/3D facial photo wrap onto the volumetric model, 3D neural canal markings, TMJ analysis, 3D/2D measurements, export images to other applications, such as STL or PLY, and more.
The provided text does not contain detailed information about acceptance criteria or a specific study proving the device meets an established acceptance criteria. It primarily focuses on demonstrating substantial equivalence to a predicate device for FDA clearance.
However, based on the information provided, here's a breakdown of what can be inferred and what is missing:
Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria or performance metrics for the ON3D device. Instead, it relies on demonstrating substantial equivalence to a predicate device (Dolphin Imaging K110430) by comparing features and functionalities. The "reported device performance" is essentially the claim of identical or equivalent features/functions.
| Feature/Function | Acceptance Criteria (Inferred from Predicate) | Reported ON3D Performance |
|---|---|---|
| Operation System | Windows or Mac OS | Windows |
| User Interface | Mouse, Keyboard | Mouse, Keyboard |
| Image Rendering | 2D and 3D | 2D and 3D |
| Image Manipulation | Preview, Rotate, Enhance, Zoom, Brightness, Contrast, Sharpness | Preview, Rotate, Enhance, Zoom, Brightness, Contrast, Sharpness |
| Basic Image Measurement | Distance, angle | Distance, angle |
| 3D Airway Analysis | Yes | Yes |
| Cross Sections in MPV | Yes | Yes |
| Volume Orientation Control | Yes | Yes |
| Volume Stitching | Combine two separate volumes into one | Combine two separate volumes into one |
| Volume-to-volume Superimposition | Yes | Yes |
| Cephalometric Tracing/Analysis | Manual point picking and automatic structure templates for 3D volume and 2D photo | None (Difference noted, but deemed not to affect SE as demonstrated in V&V documents and performance test reports.) Simple outline of mandible and maxilla by user-drawn lines connecting landmarks. |
| 3D/2D Analysis | Both 3D and 2D analysis. 3D on 3D volume; 2D on 2D photo or x-ray. | Both 3D and 2D analysis. 3D on 3D volume; 2D on pre-determined plane (mid-sagittal plane) of 3D volume using projected 3D landmarks. No 2D photo/x-ray input. |
| 3D Neural Canal Marking | Yes | Yes |
| TMJ Analysis | Yes | Yes |
| Surgical Planning/Simulation | Orthodontic and orthognathic applications using maxillary, mandible, and chin and cheek cuts. User can translate, rotate the cuts. | Orthodontic and orthognathic applications using maxillary, mandible, and chin and cheek cuts. User can translate, rotate the cuts. |
| Distinguish Biological Structures | Yes (via radiolucency) | Yes (via radiolucency) |
| Soft Tissue Deformation | Yes. 2D and 3D | Yes. 2D and 3D |
| Photo Wrapping | Can wrap 2D and 3D photos on volume image | Can wrap 2D and 3D photos on volume image |
| Dental Implant & TAD Treatment Planning/Simulation | Yes | None (Difference noted, but deemed not to affect SE.) |
| Generate Panoramic Radiographs | Yes | Yes |
| Scanner Connection | Yes | Yes |
| Export Images/Data | Yes | Yes |
| DICOM Support | Yes | Yes |
Study Details
The document mentions "Software Verification and Validation" and "Performance Testing - Bench Testing" to support the claim of substantial equivalence. However, it does not provide details on a specific clinical study or quantitative performance metrics against defined acceptance criteria.
-
Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not specified.
- Data Provenance: Not specified. The document does not mention the use of real patient data or specific datasets for testing.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- This information is not provided. The document describes "Software Verification and Validation" and "Performance Testing - Bench Testing" but not the involvement of human experts for ground truth establishment.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- This information is not provided.
-
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 MRMC study or comparative effectiveness study of human readers with/without AI assistance is mentioned. The device is described as "software that is designed for use by specialized dental practices... assisting in treatment planning and case diagnosis. Results produced by the software's diagnostic and treatment planning tools are dependent on the interpretation of trained and licensed dental practitioners." This suggests it's a tool for practitioners, not an AI intended to improve human reader performance or operate autonomously.
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- The document states "ON3D is a stand-alone software..." and compares it to a predicate that is also "Standalone Software" ("Yes" for both). However, the "Indications for Use" explicitly states that "Results produced by the software's diagnostic and treatment planning tools are dependent on the interpretation of trained and licensed dental practitioners." This means that while the software operates independently as an application, its use is not standalone in a clinical decision-making context but rather as an assistive tool requiring human interpretation. The "performance test" was a "software system-level test" assessing UI and main functions, not an algorithm-only diagnostic accuracy test.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- This information is not provided. The "Software Verification and Validation" implies internal testing against defined specifications, but the nature of external ground truth (if any) is not detailed.
-
The sample size for the training set:
- This information is not provided. The document describes the device as software for image management and processing, not as a machine learning/AI model that typically requires a distinct training set. If there are AI/ML components, their training methodology and data are not detailed.
-
How the ground truth for the training set was established:
- This information is not provided, as the existence or details of a training set for an AI/ML model are not discussed.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).