(371 days)
The PRE-SURE software system 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 genitourinary applications.
End Users of the PRE-SURE device receive digital and/or physical patient anatomical models from Lazarus 3D. The physical models are intended for adjunctive use along with other diagnostic tools and expert clinical judgement for diagnosis, patient management, and/or treatment selection of genitourinary applications. Digital models may be viewed by End Users using any program cleared for their intended use.
The PRE-SURE patient modeling system is a method for the creation of patient models. This system will be used exclusively by Lazarus 3D, with some physician input and feedback, to produce models for End Users. Importantly, and unlike other 3D modeling systems, in the PRE-SURE process the design and production of patient models is performed by Lazarus 3D and not by the End User or a third party. The internal process within Lazarus 3D used for creating PRE-SURE patient models includes use of an FDA cleared stand-alone software package. As a part of the PRE-SURE production process, this software is intended for internal use within Lazarus 3D to create digital anatomical models from patient radiological data that can be used by End Users for a variety of uses such as training, education, and pre-operative surgical planning.
The patient specific digital anatomical models may be further used as an input to a 3D printing-based production process performed by Lazarus 3D to create physical patient models. Each individual patient's model can be created rapidly from the patient's radiological data using Lazarus 3D's patented rapid prototyping technology. The resulting physical models of patient anatomy are primarily composed of silicone materials that can be cut, can be sutured, and in some cases can even bleed.
The PRE-SURE software system 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 judgment for diagnosis, patient management, and/or treatment selection of genitourinary applications.
1. A table of acceptance criteria and the reported device performance:
The document summarizes that all performance testing demonstrated conformity to pre-established specifications and acceptance criteria, which were established to prove device performance and substantial equivalence to the predicate device. However, the specific acceptance criteria and detailed reported device performance are not explicitly provided in a quantitative table within the given text. The tests performed aimed to show that:
| Acceptance Criteria (Implied) | Reported Device Performance (Summary) |
|---|---|
| Production Process Accuracy: Physical models match in-silico designs within pre-defined criteria. | Measurements between physical models created using PRE-SURE and in-silico input data "fell within pre-defined acceptance criteria." |
| Digital and Physical Model Accuracy: PRE-SURE workflow results compare accurately with predicate device results. | Comparisons between PRE-SURE models and predicate device models (from MRI/CT input) "fell within pre-defined acceptance criteria." |
| Build Envelope Accuracy: Models built with different printer locations and orientations achieve sufficient accuracy. | "Sufficient accuracy can be achieved for models built in any orientation or position" on the 3D printer for genitourinary conditions. |
| Materials Testing Accuracy & Bonding: Range of materials and combinations produce models of sufficient accuracy and bond well. | "All materials and material combinations produce models of sufficient accuracy for the intended use" and "all tested materials bond well with all other tested materials." |
| Challenging Cases Accuracy: Complex genitourinary models are reproduced with sufficient accuracy. | The 3D manufacturing process can reproduce "complex genitourinary conditions with sufficient accuracy for the intended use" when testing models of three difficult-to-produce conditions, with volumetric comparison against the digital design using CT scans. |
2. Sample size used for the test set and the data provenance:
- Production Process Accuracy Study: The document mentions "models of various dimensions" but does not specify the exact sample size. Data provenance is implied to be internal, as it compares physical models created by PRE-SURE against "in-silico input data" (computer models with pre-defined dimensions).
- Digital and Physical Model Accuracy Study: "MRI and CT scan input data from actual cases were analyzed." The number of actual cases is not specified. Data provenance is "actual cases," which suggests retrospective patient data, but the country of origin is not mentioned.
- Build Envelope Testing - Accuracy Validation: "Models of genitourinary conditions were built." The number of models tested is not specified.
- Materials Testing - Accuracy Validation: "Multi-material genitourinary models were produced." The number of models or material combinations tested is not specified.
- Testing on Especially Challenging Genitourinary Cases: "Models of three conditions that are difficult to produce for a variety of reasons were manufactured." The sample size here is explicitly three models. Data provenance is not specified beyond "complex genitourinary models."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
The document does not provide information on the number of experts used or their qualifications for establishing ground truth in any of the described studies. The ground truth for the "Production Process Accuracy Study" was "pre-defined in silico" dimensions. For other studies, it seems to rely on comparisons to existing imaging data or digital designs, without explicit involvement of human experts for ground truth establishment.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
The document does not mention any adjudication method being used for the test sets. The studies described are focused on direct measurement comparisons rather than expert interpretation requiring adjudication.
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 MRMC comparative effectiveness study involving human readers or AI assistance is mentioned in the provided text. The device, PRE-SURE, is described as a software interface and image segmentation system for creating digital and physical anatomical models for surgical planning and adjunctive use (diagnosis, patient management, treatment selection). It is not presented as an AI-assisted diagnostic tool that directly impacts human reader performance.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
The studies described ("Production Process Accuracy Study," "Digital and Physical Model Accuracy Study," "Build Envelope Testing - Accuracy Validation," "Materials Testing - Accuracy Validation," "Testing on Especially Challenging Genitourinary Cases") appear to evaluate the output of the PRE-SURE system (digital and physical models) based on defined metrics or comparisons. These are standalone evaluations of the system's accuracy in model production, independent of human interpretation or intervention in the evaluation phase, although human feedback is mentioned in the production process ("physician input and feedback").
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Production Process Accuracy Study: In-silico input data (pre-defined dimensions in computer models).
- Digital and Physical Model Accuracy Study: Comparison against the predicate device's output and presumably the original MRI/CT scan input data (although not explicitly pathology or expert consensus).
- Testing on Especially Challenging Genitourinary Cases: "Volumetrically compared against the digital design" and original CT scanner data.
Generally, the ground truth appears to be based on engineering specifications (in-silico designs) and direct comparisons against source radiological data or outputs of a legally marketed predicate device, rather than clinical outcomes, pathology, or expert consensus on a diagnosis.
8. The sample size for the training set:
The document does not mention any "training set" or "training" for the PRE-SURE device. This suggests that the device, being an "image segmentation system" and a tool for creating models, might not rely on a machine learning model that requires a distinct training set in the conventional sense, or this information is not disclosed in the provided summary.
9. How the ground truth for the training set was established:
As no training set is mentioned, information on how its ground truth was established is not provided.
§ 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).