Search Results

Elucis is intended for use as a software interface and image segmentation system for the transfer of medical imaging information to an output file. It is also intended for measuring and treatment planning.

Elucis should be used in conjunction with expert clinical judgement.

Elucis is a software system for creating, visualizing, and interacting with three-dimensional (3D) models in a desktop 2D environment and an extended (virtual) reality (XR) environment. Medical images (e.g., CT and MRI) and, optionally, 3D structure files in a variety of file formats are used as input. Users can create 3D anatomical models directly from one or more medical images using a variety of manual and semi-automatic image segmentation tools available in the XR environment. These models, and the images from which they were created, can be used to conduct measurements and plan treatments.

The core functionality in Elucis includes the ability to:

• View medical images in a variety of planar and volumetric reformations
• Import medical images in DICOM and other formats and import 3D model files
• Create 3D models from medical images using a variety of common modeling tools
• Review and edit existing 3D models
• Perform measurements on images and models
• Plan treatments using 3D models and associated medical images
• Save and export images, measurements, 3D models, and other treatment planning information

The provided text does not contain the detailed acceptance criteria or a specific study that proves the device meets them, in the format requested.

The document is a 510(k) summary for the Elucis device, which outlines its intended use, comparison to a predicate device, and general statements about performance data. However, it lacks the specific quantifiable details required to fill out the table and answer all the questions.

Here's what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size for Test Set: Not specified. The document mentions "a range of anatomical structures and medical image scan types" but does not provide a number.
• Data Provenance (country of origin, retrospective/prospective): Not specified.

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

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

4. Adjudication method for the test set

• Adjudication Method: Not specified.

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

• MRMC Study: Not explicitly stated or detailed. The document mentions "End-user was conducted with a group of intended users, representing a diverse mix of clinical roles, educational backgrounds, and experience, to confirm overall usability," but this is a usability study, not necessarily an MRMC comparative effectiveness study measuring improvement with AI assistance.
• Effect Size: Not provided.

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

• The document implies a standalone assessment for geometric accuracy: "The geometric accuracy of virtual models created in the subject device was assessed via comparisons against the same models made with the predicate device." This suggests an algorithm-only evaluation for accuracy against a reference. However, a dedicated "standalone performance" section with metrics is not present.

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

• The ground truth for the geometric accuracy assessment appears to be the "same models made with the predicate device (Mimics Medical K183105)". This implies the predicate device's output is considered the reference.

8. The sample size for the training set

• Sample Size for Training Set: Not specified. The document does not mention a training set, as it describes a software system with modeling tools rather than a machine learning algorithm that requires explicit training data for image interpretation.

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

• Ground Truth for Training Set: N/A, as a training set is not discussed or implied for this device's functionality as described.

Ask a specific question about this device