(74 days)
The Stratasys FDM MedModeler is indicated as an image processing accessory, used to create three dimensional models from 3D surface representation data or 2D contour data as a diagnostic tool, as a pre-operative planning tool, and to enhance communication with patients, other professionals or students.
The Stratasys FDM MedModeler produces anatomical models for use in a variety of medical applications using CT and MRI imaging data. The four main parts of the FDM system, as displayed in Figure 1 (previous page) are 1) the QuickSlice Software, 2) FDM Hardware, 3) Modeling Materials and a 4) Computer Workstation.
Here's an analysis of the provided text regarding the Stratasys FDM® MedModeler System, focusing on acceptance criteria and study details:
This device is not an AI/ML powered device. It is a system for creating physical 3D models from imaging data. Therefore, many of the typical questions related to AI/ML device studies (like MRMC studies, standalone algorithm performance, number of experts for ground truth, and training set details) are not applicable or described in the provided 510(k) summary. The summary focuses on the safety and performance of the model generation process itself, rather than diagnostic accuracy.
Acceptance Criteria and Reported Device Performance
The provided 510(k) summary is very limited regarding specific, quantifiable acceptance criteria typical for diagnostic accuracy studies. The criteria are broadly defined around the system's intended function.
| Acceptance Criterion | Reported Device Performance |
|---|---|
| Safety of the system | "Hazard/Risk Analysis demonstrates that the safety of the Stratasys FDM MedModeler is acceptable and that identified potential risks are within acceptable limits for likelihood of occurrence and severity of hazards." |
| Performance as intended for model generation | "The model generation report demonstrates that the FDM MedModeler performed as intended and within system requirements for CAD, CT and MRI image modeling, and produced satisfactory models." |
| Compliance with software and hardware validation requirements | "Software development information, software validation and hardware validation information are also provided according to FDA guidance requirements." |
Study Details (Where Applicable)
Given the nature of the device (a 3D modeling system rather than a diagnostic AI), many of these categories are not explicitly addressed in the provided summary.
- Sample size used for the test set and the data provenance: Not explicitly stated. The summary mentions "CAD, CT and MRI image modeling" data but does not specify the number of cases or their origin.
- Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable or not specified. The "ground truth" here would relate to the geometric accuracy and usability of the physical models compared to the original imaging data. There's no mention of expert radiologists or similar medical professionals evaluating model accuracy in the way they would evaluate diagnostic images.
- Adjudication method for the test set: Not applicable or not specified.
- 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: Not applicable. This is not an AI diagnostic device for human readers.
- If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable in the context of typical AI diagnostic devices. The performance of the FDM MedModeler system itself (the "algorithm only," if you consider the software and hardware combined) was assessed based on its ability to produce "satisfactory models" per the model generation report.
- The type of ground truth used: The ground truth appears to be the original 2D contour or 3D surface representation data from CT/MRI, against which the generated 3D physical models were compared for "satisfactory" replication and adherence to "system requirements."
- The sample size for the training set: Not applicable. This is not a machine learning device that uses a "training set" in the conventional sense. The "training" here would be the development and calibration of the system itself.
- How the ground truth for the training set was established: Not applicable.
§ 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).