(255 days)
The D2P software is intended for use as a software interface and image segmentation system for the transfer of DICOM imaging information from a medical scanner to an output file. It is also intended as pre-operative software for surgical planning. For this purpose, the output file may be used to produce a physical replica. The physical replica is intended for adjunctive use along with other diagnostic tools and expert clinical judgement for diagnosis, patient management, and/or treatment selection of cardiovascular, craniofacial, genitourinary, neurological, and/or musculoskeletal applications.
The D2P software is a stand-alone modular software package that provides advanced visualization of DICOM imaging data. This modular package includes, but is not limited to the following functions:
- DICOM viewer and analysis
- Automated segmentation
- Editing and pre-printing
- Seamless integration with 3D Systems printers
- Seamless integration with 3D Systems software packages
- Seamless integration with Virtual Reality visualization for non-diagnostic use.
The provided text does not contain detailed information regarding acceptance criteria, specific study designs, or performance metrics in a structured format that directly addresses all the requested points. The document summarizes the device, its intended use, and its equivalence to a predicate device for FDA 510(k) clearance.
However, based on the limited information available, here's what can be extracted and inferred:
1. A table of acceptance criteria and the reported device performance:
The document states: "All performance testing... showed conformity to pre-established specifications and acceptance criteria." and "A measurement accuracy and calculation 3D study, usability study, and decimation study were performed and confirmed to be within specification." It also mentions "Validation of printing of physical replicas was performed and demonstrated that anatomic models... can be printed accurately when using any of the compatible 3D printers and materials."
Without specific numerical thresholds or target values, a detailed table cannot be created. However, the categories of acceptance criteria and the qualitative reported performance are:
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Measurement Accuracy & Calculation 3D | Confirmed to be within specification |
| Usability | Confirmed to be within specification |
| Decimation | Confirmed to be within specification |
| Accuracy of Physical Replica Printing | Anatomic models can be printed accurately on compatible 3D printers and materials for specified applications. |
2. Sample size used for the test set and the data provenance:
This information is not provided in the text. There is no mention of sample size for any test set or the origin (country, retrospective/prospective) of the data used for validation.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
This information is not provided in the text. The document does not detail how ground truth was established for any validation studies.
4. Adjudication method for the test set:
This information is not provided in the text.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, and if so, what was the effect size of how much human readers improve with AI vs without AI assistance:
The document describes the D2P software as an "image segmentation system," "pre-operative software for surgical planning," and a tool for "transfer of DICOM imaging information." It also mentions the "Incorporation of a deep learning neural network used to create the prediction of the segmentation."
However, there is no mention of an MRMC comparative effectiveness study involving human readers with and without AI assistance, nor any effect size related to human reader improvement. The focus appears to be on the performance of the software itself and the accuracy of physical replicas.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Yes, the testing described appears to be primarily standalone performance testing of the D2P software and its ability to produce accurate segmented models and physical replicas. The statement "All performance testing... showed conformity to pre-established specifications and acceptance criteria" without mention of human interaction suggests standalone evaluation.
7. The type of ground truth used:
This information is not explicitly stated in the text. While it mentions "measurement accuracy," "usability," and "accuracy of physical replicas," it does not specify the method used to establish the gold standard or ground truth for these measurements (e.g., expert consensus, pathology, outcomes data, etc.). It can be inferred that for "measurement accuracy" and "accuracy of physical replicas," there would be established objective standards or measurements used as ground truth.
8. The sample size for the training set:
This information is not provided in the text. The document mentions the "Incorporation of a deep learning neural network," which implies a training set was used, but its size is not disclosed.
9. How the ground truth for the training set was established:
This information is not provided in the text. While a deep learning network was used, the method for establishing the ground truth for its training data is not discussed.
§ 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).