K Number
K151371
Date Cleared
2015-08-19

(90 days)

Product Code
Regulation Number
892.2050
Panel
RA
Reference & Predicate Devices
Predicate For
N/A
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

Corporate Dental Imaging (CDI) Application™ is a software device for general dental diagnostic imaging. It controls capture, display, transfer, enhancement, and storage of X-ray dental images from digital imaging systems.

Device Description

The Corporate Dental Imaging (CDI) Application™ is a software application used for storing and displaying medical dental images. The application conforms to the DICOM 3.x standard to allow interoperability with other DICOM compliant systems. The implementation of CDI interface has been tested to assure compliance with the DICOM Conformance Statement. CDI is comprised of one (1) desktop client for Modality Image Capture, one (1) web-based client for Image Viewing and Diagnostics with Microsoft SQL Server back-end database(s) for storing DICOM images. CDI will capture images directly from intra-oral and extra-oral acquisition modalities, full color images from intra-oral cameras, digital cameras and other video sources. CDI is loaded onto the Acquisition PCs in the clinic where either the images will be acquired or where the images will need to be viewed. CDI will use the hardware vendor's own drivers to seamlessly initialize the acquisition modality from within the CDI UI. CDI will be designed to create a standard DICOM object that conforms to industry standards. CDI will also provide easy-to-use image processing tools that aid providers in analyzing images and making diagnoses. CDI will allow users to enhance the contrast and brightness of an image, reverse image values to show dental caries, and magnify specific areas of concern.

AI/ML Overview

This document is a 510(k) summary for the Corporate Dental Imaging (CDI) Application™. It primarily aims to demonstrate substantial equivalence to a predicate device (XELIS DENTAL, K102684) and does not contain detailed information about acceptance criteria and a study proving the device meets them in the context of diagnostic accuracy or clinical performance.

The provided text focuses on:

  • Device Description: What the CDI Application is (software for storing and displaying dental X-ray images, DICOM compliant).
  • Indications for Use: General dental diagnostic imaging, control of capture, display, transfer, enhancement, and storage of X-ray dental images.
  • Technological Characteristics Comparison with Predicate Device: A table comparing functionalities like computer platform, OS, networking, image compression, image storage, 2D image viewer tools, and specialized dental features.
  • Nonclinical Testing: Mentions that the device has been "assessed and tested at the factory" and "passed all in-house testing criteria." It also states "Validation testing indicated that... results demonstrated that the predetermined acceptance criteria were met."

However, it does not provide:

  • A specific table of acceptance criteria with reported device performance metrics (e.g., sensitivity, specificity, accuracy, precision for image analysis tasks).
  • Details about a study that measures the device's diagnostic performance against such criteria.
  • Information on sample sizes, ground truth establishment methods (e.g., pathology, expert consensus), or expert qualifications for a diagnostic study.
  • Any mention of Multi-Reader Multi-Case (MRMC) comparative effectiveness studies or standalone algorithm performance.

The "Nonclinical Testing" section refers to "predetermined acceptance criteria" for verification and validation but does not define these criteria or present the results in a way that would allow for a detailed analysis of diagnostic performance. It implies that these tests were related to software functionality and system performance rather than clinical diagnostic efficacy.

Therefore, based solely on the provided document, the requested information regarding acceptance criteria and performance study as typically understood for diagnostic AI/CADe devices cannot be fully detailed.

Here's a summary of what is available and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria Mentioned (Implicit from "Nonclinical Testing" section):

  • Device functions as intended (e.g., capture, display, transfer, enhancement, storage of images).
  • DICOM 3.x standard compliance for interoperability.
  • Adherence to software requirements and specifications.
  • Absence of new potential safety risks compared to the predicate.
  • Operational efficiency for the specified computer platforms and operating systems.
  • Basic image manipulation tools (pan, zoom, centering, windowing, flip, rotation, layouts, annotation).

Reported Device Performance:
The document states: "Validation testing indicated that... results demonstrated that the predetermined acceptance criteria were met." However, no specific quantitative performance metrics (e.g., error rates, processing speeds, image quality metrics) are provided. The comparison table with the predicate device (XELIS DENTAL) focuses on functionality presence rather than quantitative performance comparison. The key takeaway from the comparison is that the CDI Application™ has reduced functionality compared to the predicate, but these differences "do not create new risks and do not impact safety or efficacy" and are not required for its intended use.

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

Not provided. The document refers to "in-house testing criteria" and "Validation Test Plan" but does not specify the number of images or cases used in any testing, nor their origin (e.g., country, retrospective/prospective).

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

Not applicable/Not provided. The document focuses on software functionality and substantial equivalence to a predicate PACS system, not on a diagnostic performance claim that would typically require expert-established ground truth for a test set. There's no mention of experts or their qualifications in the context of evaluation.

4. Adjudication method for the test set

Not applicable/Not provided. As no diagnostic performance study is detailed, no adjudication method is mentioned.

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. The document does not describe any MRMC study or any study involving human readers' performance with or without AI assistance. The device is described as a Picture Archiving and Communications System (PACS) with basic image manipulation tools, not an AI/CADe diagnostic aid.

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

No. The device is a software application for image handling and display, not a standalone diagnostic algorithm. The document explicitly states: "The subject device does not include any automated or semi-automated processes for the detection of nodules or other shapes." and "A physician, providing ample opportunity for competent human intervention interprets images and information being displayed and or printed."

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

Not applicable/Not provided. As this is a PACS system without automated diagnostic capabilities, a ground truth in the sense of disease presence/absence is not discussed for its evaluation. Its evaluation focuses on functional performance and adherence to standards.

8. The sample size for the training set

Not applicable/Not provided. The device described is a software application (PACS) for image management and display, not a machine learning or AI algorithm that would typically require a training set.

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

Not applicable/Not provided. As stated above, this is not an AI/ML device requiring a training set.

§ 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).