K Number
K250005
Device Name
Clever One
Manufacturer
Date Cleared
2025-05-23

(141 days)

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

Clever One is dental imaging software that is intended to provide tools for supporting diagnosis and treatment. These tools enable end users to view and interpret a series of DICOM compliant medical images and are intended for use by trained medical professionals. Clever One allows users to load, view, and save DICOM images from CT, panoramic, cephalometric, intraoral, and other imaging equipment. It also provides functionalities such as 2D viewing, 2D analysis, 3D visualization, 3D analysis.

Device Description

Clever One is a dental imaging software designed to acquire, process, view, edit, and analyze medical images for supporting diagnostic and preoperative planning purposes. It supports standard DICOM formats for 2D and 3D image files and enables advanced imaging functionalities for enhanced diagnostic accuracy.

The software provides a range of features, including:

  • 2D Imaging: Loading, editing, and viewing 2D dental images in standard formats (e.g., DICOM, JPG, BMP).
  • 3D Imaging: Visualization and reconstruction of 3D CT images, including multi-planar views (MPR) and volume rendering.
  • Preoperative Planning: Implant position simulation, canal drawing, and bone density analysis to support treatment planning.
  • Data Interoperability: Facilitates data transfer and storage using DICOM-compliant workflows, ensuring compatibility with third-party systems and imaging devices.

The software interfaces with dental imaging equipment, such as CT, panoramic, cephalometric, and intraoral X-ray systems, as well as intraoral cameras, for image acquisition. It is designed for use in network environments, allowing users to upload and download clinical diagnostic images and patient data for enhanced collaboration and efficient patient management.

AI/ML Overview

Here's the breakdown of the acceptance criteria and the study information based on the provided FDA 510(k) clearance letter for the "Clever One" device.

Unfortunately, the provided document does not contain detailed information about specific acceptance criteria or a dedicated study proving performance against those criteria in a quantitative manner. The clearance letter primarily focuses on demonstrating substantial equivalence to predicate devices (EzDent-i and Ez3D-i) for a medical image management and processing system. The performance data section is very general.

Therefore, many of the requested fields will state "Not specified in the document" or "Not applicable/provided."


Acceptance Criteria and Reported Device Performance

Given the nature of the device as a "Medical Image Management and Processing System" that provides viewing, analysis, and processing tools, the acceptance criteria are generally focused on functionality, accuracy, interoperability, and cybersecurity rather than diagnostic performance metrics like sensitivity/specificity for disease detection.

Acceptance Criterion (Inferred from device description and typical software V&V)Reported Device Performance (as stated or inferred)
Functional Verification & Validation (V&V): All listed functionalities (2D imaging, 3D imaging, preoperative planning, data interoperability, image manipulation, implant module) work as intended."SW verification/validation... were conducted to establish the performance, functionality and reliability characteristics of the subject devices. The device passed all of the tests based on pre-determined Pass/Fail criteria." (Specific functionalities tested and their pass/fail rates are not detailed.)
Measurement Accuracy: Tools for length, angle, volume, etc., provide accurate measurements."Measurement accuracy test were conducted to establish the performance, functionality and reliability characteristics of the subject devices. The device passed all of the tests based on pre-determined Pass/Fail criteria." (Specific accuracy metrics and thresholds are not detailed.)
DICOM Compliance & Interoperability: Ability to load, view, and save DICOM images from various equipment (CT, panoramic, cephalometric, intraoral, etc.)."It supports standard DICOM formats for 2D and 3D image files... Facilitates data transfer and storage using DICOM-compliant workflows, ensuring compatibility with third-party systems and imaging devices... It also supports the acquisition of CT/Panoramic/Cephalo/Intra-Oral Sensor images by interfacing with X-ray capture software." (Implied successful demonstration of these capabilities.)
Cybersecurity: Protection against unauthorized access, use, disclosure, disruption, modification, or destruction of information."Comprehensive cybersecurity risk management and verification and validation activities were conducted. The results of these cybersecurity assessments, the supporting documentation, and the cybersecurity management plan are included in this premarket submission." (Specific metrics like CVEs, penetration testing results are not provided.)
System Reliability/Stability: Software operates without crashes or significant errors during typical usage."The device passed all of the tests based on pre-determined Pass/Fail criteria." (Implied through general V&V statement.)
User Interface Responsiveness: User interactions are smooth and timely.Not explicitly stated but implied by successful functional V&V.
Compatibility: Operates correctly on specified hardware and OS (Microsoft Windows 10 or higher, IBM-compatible PC)."All devices, including Clever One, operate on a Windows-based platform using Windows 10 as the operating system." (Stated as a characteristic, implying successful operation on this platform.)
Data Integrity: Patient data and images are handled without corruption.Not explicitly stated but implied through functional V&V and cybersecurity.

Study Details

  1. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

    • Sample Size: Not specified in the document.
    • Data Provenance: Not specified in the document.
  2. 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/provided. The document describes a software verification and validation process and "measurement accuracy test," not a clinical study involving ground truth established by experts for diagnostic performance. The device is for "supporting diagnosis and treatment," and "all diagnosis and treatment decisions made are solely up to the user."
  3. Adjudication method (e.g. 2+1, 3+1, none) for the test set

    • Not applicable/provided, as there is no mention of a test set requiring adjudication in the context of expert ground truth. The V&V process likely involved internal testing against specifications.
  4. 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 comparative effectiveness study was performed or mentioned. The device is described as "dental imaging software that is intended to provide tools for supporting diagnosis and treatment," and is compared to predicate devices for its functionality and technical characteristics, not its impact on human reader performance. Its purpose is "visualizing data," and "visualization results only assist end-users in patient counseling, diagnosis, and treatment planning."
  5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

    • Not applicable/provided. The device is a software suite with various tools for human users, making a standalone "algorithm only" performance evaluation less relevant in the context of its stated functionality as a viewing and analysis platform for a clinician.
  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

    • For the "measurement accuracy test," the ground truth would typically be established against known physical measurements or validated digital standards (e.g., using phantoms or geometrically characterized digital models) rather than clinical ground truth like pathology. For functional V&V, the "ground truth" is adherence to software specifications.
  7. The sample size for the training set

    • Not applicable/provided. The document does not describe the use of machine learning that would require a "training set." The device is presented as software that processes and visualizes DICOM images using established algorithms (e.g., for MPR, volume rendering, measurement tools), rather than an AI/ML-driven diagnostic algorithm that learns from data.
  8. How the ground truth for the training set was established

    • Not applicable/provided, as there is no mention of a training set.

Summary of Performance Data (from the document):

"SW verification/validation and the measurement accuracy test were conducted to establish the performance, functionality and reliability characteristics of the subject devices. The device passed all of the tests based on pre-determined Pass/Fail criteria."

Additionally, "comprehensive cybersecurity risk management and verification and validation activities were conducted" and their results "are included in this premarket submission."

The document concludes that the "new device does not introduce a fundamentally new scientific technology, and the device has been validated through system level test."

§ 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).