K Number
K200810
Device Name
IPS CaseDesigner
Manufacturer
Date Cleared
2020-10-08

(195 days)

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

IPS CaseDesigner is indicated for use as a software and image segmentation system for the transfer of imaging information from a scanner such as a CT scanner. It is also indicated to support the diagnostic and treatment planning process of craniomaxillofacial procedures. IPS CaseDesigner facilitates the service offering of individualized surgical aids.

Device Description

IPS CaseDesigner has specific functionalities to visualize the diagnostic information, e.g. from CT-imaging, to perform specific measurements in the image data and to plan surgical actions in order to support the diagnostic and treatment planning process. Based on the diagnostic and planning data, the IPS design service can offer individualized surgical aids.

AI/ML Overview

The IPS CaseDesigner 2.0 is a software and image segmentation system for the transfer of imaging information from a CT scanner, indicated to support the diagnostic and treatment planning process of craniomaxillofacial procedures and facilitate the service offering of individualized surgical aids.

Here's an analysis of its acceptance criteria and the supporting study:

1. Table of Acceptance Criteria and Reported Device Performance

The provided documentation does not explicitly list quantitative acceptance criteria in a dedicated table format. The "Differences" section, however, outlines new functionalities and improvements compared to the predicate device, implying that the performance of these new features needed to be validated. The "Performance Data" section states that the device was verified and validated and that "requirements for the features have been met."

Based on the text, the key performance aspects that were likely evaluated for the new features are:

Feature/FunctionalityAcceptance Criteria (Implied)Reported Device Performance
Additional Segmental Maxillary OsteotomiesAccurate simulation and planning of segmental maxillary osteotomies (Split, Y-cut, H-cut).Allows planning of segmental maxillary osteotomies, enabling different types of virtual cuts and bone fragment movement.
Intraoral Surface Scan Data ImportAbility to accurately import and utilize intraoral surface scan data (dental casts) for occlusal information.Can use intraoral surface scans for detailed occlusal information.
Osteosynthesis Plates Selection/OrderingCorrect display and selection of osteosynthesis plates, and accurate generation of a list for ordering.Possible to export a list of specific plates selected from an available list.
3D CephalometryAccurate setting of 3D landmarks and planes, correct calculation of measurements, and automatic updates based on planning.Supports 3D Cephalometry with setting landmarks, measurements, and automatic updates. Virtual lateral and frontal cephalograms are calculated.
New Algorithm for Virtual OcclusionAccuracy and efficiency comparable to the manual workflow of placing and digitizing dental casts.Concluded to be as efficient and accurate as the manual workflow; provides the same level of accuracy and reliability.
Splint VisualizationAccurate generation and visualization of the surgical splint directly within the 3D workspace.Allows generation and visualization of surgical splint directly in the 3D workspace.
3D Photo Mapping (Soft Tissue Simulation)Improved visualization of soft tissue simulation with the ability to add "real-world" textures.Improved visualization of soft tissue simulation.
Operating System CompatibilityCompatibility and validated performance on specified operating systems (Windows 7, 10; Mac OS Catalina, Mojave, High Sierra).Tested and validated on all specified systems.

2. Sample Size for the Test Set and Data Provenance

The document does not specify the sample size used for the test set for any of the performance evaluations. It also does not mention the data provenance (e.g., country of origin, retrospective or prospective nature) for any specific testing data.

3. Number of Experts and Qualifications for Ground Truth

The document does not specify the number of experts or their qualifications used to establish ground truth for the test set. For the "New algorithm for virtual occlusion and occlusion alignment," it states "This algorithm was validated and it was concluded that it is as efficient and as accurate as the manual workflow..." but does not detail who performed this validation or how the "manual workflow" ground truth was established by experts.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method used for the test set.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document does not describe a multi-reader multi-case (MRMC) comparative effectiveness study. There is no mention of human readers improving with AI assistance or without. The device functions as a planning tool for clinicians, and the focus of the validation is on the accuracy and functionality of the software's new features.

6. Standalone Performance

Yes, the study primarily describes the standalone performance of the algorithm and software features. The validation of the "New algorithm for virtual occlusion and occlusion alignment" specifically states that it was concluded to be "as efficient and as accurate as the manual workflow," which implies a standalone assessment of the algorithm's output against a defined standard. The other listed features also focus on the core functionality of the software itself.

7. Type of Ground Truth Used

The type of ground truth used is not explicitly stated in detail for each feature. However, based on the description, it can be inferred that:

  • Expert Consensus/Manual Workflow: For the "New algorithm for virtual occlusion and occlusion alignment," the ground truth likely involved a manual workflow of placing dental casts in occlusion and digitizing them, implicitly representing an expert-derived or standard clinical practice ground truth. The algorithm's output was compared against this.
  • Engineering/Design Specifications: For functionalities like "Additional segmental maxillary osteotomies," "Osteosynthesis plates," "3D Cephalometry," and "Splint visualization," the ground truth for validation likely involved verifying the software's output against pre-defined engineering specifications, anatomical accuracy, and expected physiological movements/measurements as determined by medical and software experts during the design and development phases.

8. Sample Size for the Training Set

The document does not specify the sample size for the training set. As this device is a planning and visualization tool, rather than a deep learning model requiring extensive training data, explicit mention of a "training set" might not be applicable in the same way as for diagnostic AI algorithms. However, if any machine learning components were used (e.g., for occlusion alignment), this information is not provided.

9. How the Ground Truth for the Training Set was Established

Since the document does not specify a training set or its sample size, it does not describe how ground truth for a training set was established.

§ 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).