(564 days)
Mimics Enlight CMF is intended for use as a software interface and imaging segmentation system for the transfer of medical imaging information to an output file.
Mimics Enlight CMF is also intended to support the diagnostic and treatment planning process of maxillofacial procedures. For this purpose, Mimics Enlight CMF provides visualization, measurement and design tools.
The Mimics Enlight CMF output file can be used for the fabrication of the output file using traditional or additive manufacturing methods. The fabricated output can be used for diagnostic purposes in the field of maxillofacial applications.
Mimics Enlight CMF should be used in conjunction with other diagnostic tools and expert clinical judgement.
Mimics Enlight CMF is an image processing software for the diagnosis and treatment planning of maxillofacial procedures. Mimics Enlight CMF allows the user to import, visualize and segment medical images. Mimics Enlight CMF also allows the user to perform measurements, treatment planning and occlusal splint design. Mimics Enlight CMF allows the user to output digital 3D models of the anatomy to be used for fabrication of physical anatomical models. Mimics Enlight CMF is structured as a modular package consisting of separate workflows for the diagnosis and treatment planning of various indications within the maxillofacial field. The workflows in Mimics Enlight CMF are built on the Mimics Enlight platform. The workflows in Mimics Enlight CMF cover following steps and functionality in the diagnostic and treatment planning process of maxillofacial procedures:
Digital 3D model creation
- . Importing medical images in DICOM format and other formats
- Viewing images and DICOM data
- Selecting a region of interest using generic segmentation tools
- . Verifying and editing a region of interest
- . Calculating a digital 3D model and editing the model
- . Creating composite models by combining medical image information and dental information using registration tools
- Exporting digital 3D models for additive manufacturing (3D printing) of physical replicas (anatomical models)
Planning
- Indicating nerves and cephalometric landmarks
- . Setting the natural head position
- Planning the treatment by cutting the models and repositioning the parts
- Setting the occlusion digitally or by importing an occlusion model ●
- Measuring on images and digital 3D models
- Simulating the soft tissue of the face after the planned treatment
Design
- Designing personalized digital occlusal splints using generic design and finishing tools ●
User fabrication using additive manufacturing (3D printing) of physical replicas includes only fabrication of anatomical models and does not include additive manufacturing of occlusal splints.
The provided text describes the device, Mimics Enlight CMF, and its substantial equivalence to predicate devices, but it does not contain the specific acceptance criteria or detailed study results (like sample sizes, expert qualifications, or MRMC study results) that would typically be found in a detailed performance study section of a 510(k) submission.
The document mainly focuses on:
- Indications for Use
- Comparison of Technological Characteristics with Predicate Device
- Statements about Software Verification and Validation
- Geometrical Accuracy Testing for Virtual Models and Physical Replicas (by reference to the predicate device)
- Soft Tissue Simulation Equivalence
Based on the available text, here's what can be extracted and what information is not present:
1. A table of acceptance criteria and the reported device performance
The document does not provide a specific table with numerical acceptance criteria and reported performance values. It mentions:
- "The results revealed no deviations in the virtual models, demonstrating substantial equivalency between the two devices."
- "The deviations were found to be within the acceptance criteria, indicating that the virtual models can be printed accurately using one of the compatible 3D printers." (This refers to predicate device testing, with the conclusion that it applies to the subject device due to no significant deviations in virtual models).
- "The test demonstrated that the soft tissue simulation in Mimics Enlight CMF is equivalent to the soft tissue simulation in the reference device Proplan CMF (K111641)."
This implies acceptance criteria related to "no deviations" or "deviations within acceptance criteria" and "equivalence," but the specific numerical thresholds are not detailed.
2. Sample sizes used for the test set and the data provenance
- Sample Size for Test Set: Not specified. The document mentions "virtual models were compared" and "soft tissue simulation in the subject device Mimics Enlight CMF" was tested, but no specific number of cases or models used for these comparisons is provided.
- Data Provenance: Not specified. There is no information regarding the country of origin of the data or whether it was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not specified. The document mentions testing for geometrical accuracy and soft tissue simulation equivalence, but it does not describe any expert-based ground truth establishment process involving specific numbers of experts or their qualifications.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not specified. Given that the described tests involve comparisons of virtual models and simulations rather than human interpretation of cases to establish ground truth, an adjudication method in the traditional sense (for clinical interpretation) is not mentioned or implied.
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 mention an MRMC study. The device, Mimics Enlight CMF, is described as an image processing software for segmentation, visualization, measurement, and design tools, supporting diagnostic and treatment planning. It's not an AI-assisted diagnostic tool in the sense that medical images are interpreted by human readers with or without AI assistance. Therefore, an MRMC study to show human reader improvement with AI assistance is not relevant to the described performance evaluation.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, in a sense. The described tests on "geometrical accuracy" of virtual models and "soft tissue simulation" are evaluations of the algorithm's output directly, without a human in the loop for the performance measurement itself. The device is an "image processing software," so its performance is inherently about the quality and accuracy of its processing capabilities. The statement "Mimics Enlight CMF should be used in conjunction with other diagnostic tools and expert clinical judgement" implies that it is not intended for standalone clinical decision-making but rather as a tool within a broader clinical workflow, where the algorithm's output is then used by a human expert.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth for the "geometrical accuracy" appears to be based on:
- Comparison with the predicate device's virtual models ("no deviations in the virtual models").
- Optical scans of physical models (for the predicate device, implying this accuracy carries over to the subject device).
For "soft tissue simulation," the ground truth was equivalence to the reference device Proplan CMF (K111641).
This is a technical ground truth based on direct comparison to a known state (predicate/reference device's output or physical measurements via optical scans), rather than a clinical ground truth like pathology or expert consensus on a diagnosis.
8. The sample size for the training set
Not specified. The document does not provide details about a training set, as it emphasizes verification and validation against requirements and comparison to predicate devices, rather than a machine learning model's training process.
9. How the ground truth for the training set was established
Not applicable/Not specified. Since no training set or machine learning model training is described for this device in the provided text, the establishment of ground truth for a training set is not pertinent to the information given. The device appears to be a rule-based or algorithmic image processing software, not a deep learning AI model that requires a labeled training dataset in the traditional sense.
§ 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).