(87 days)
The Surgical Theater, LLC SNAP is intended for use as a software interface and image segmentation system for the transfer of imaging information from a CT or MR medical scanner to an output file. It is also intended for use in simulating and evaluating surgical treatment options both pre-operatively and intra- operatively with validated systems as identified in the device labeling.
The SNAP is software based medical image management system. It is intended for use as a software interface and image segmentation system for the transfer of imaging information from a CT or MR medical scanner to an output file. It is also intended for use in simulating and evaluating surgical treatment options both pre-operatively and intraoperatively with validated systems as identified in the device labeling. The SNAP system is based on the Surgical Theater Surgery Rehearsal Platform (SRP) image management system. The SNAP utilizes the same identical software as the SRP to create 3D models of patient data from 2D scan slices. This provides the user with ability to input, display, color, and manipulate the 2D scan slices via a 3D representation. The SNAP system enhances the SRP's capability by adding additional input and allowing the surgeon to connect to an external Image Guided System and Navigation systems (in general: "IGS"; for example Brainlab Kolibri or Brainlab Curve), and to see the incoming navigation data in the SNAP monitor. The incoming navigation data is then displayed to the surgeon inside the generated 3D model, so the surgeon gets a 3D representation of his surgery navigation session.
The provided document K140819 for the Surgical Navigation Advanced Platform (SNAP) does not contain a specific table of acceptance criteria with numerical performance targets or a detailed study report demonstrating how these criteria were met. Instead, it states that "Verification and validation results confirm that the SNAP Software meets its' performance requirements."
However, based on the information provided, we can infer the acceptance criteria for the device's functionality and its proven performance:
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria Category | Specific Acceptance Criterion | Reported Device Performance |
|---|---|---|
| Basic Functionality | Ability to reconstruct a 3D model of patient anatomy from 2D medical images (DICOM dataset). | The SNAP system "reconstructs a 3D model of a specific patient's anatomy" from 2D DICOM datasets. It "utilizes the same identical software as the SRP to create 3D models of patient data from 2D scan slices." |
| Visualization & Manipulation | Capability to input, display, color, and manipulate the 2D scan slices via a 3D representation, including image tools like rotation, scaling, and coloring. | The SNAP "provides the user with ability to input, display, color, and manipulate the 2D scan slices via a 3D representation" and has "Image tools such as rotation, scaling and coloring." This functionality is identical to the predicate SRP device. |
| External Device Connectivity | Capability of connecting to an external Surgical Navigation system (e.g., Brainlab Kolibri or Brainlab Curve) and processing incoming navigation data. | The SNAP allows the surgeon to "connect to an external Image Guided System and Navigation systems," "see the incoming navigation data in the SNAP monitor," and displays this data "in a 3D fashion inside the SNAP 3D model." It was specifically "tested with the Brainlab Kolibri 2 and Brainlab Curve systems." |
| Navigation Data Display | Display of incoming navigation data (e.g., pointer position and orientation) from an external navigation system within the generated 3D model. | The SNAP "displays the same navigation data (Pointer position and orientation), as it is received from the external navigation system, in a 3D fashion inside the SNAP 3D model of the anatomy." |
| Intra-operative Use | Functionality and safety for use in the Operating Room (OR) during surgery. (This is a key differentiating feature from the predicate SRP). | The SNAP is "also intended to be used in the OR during surgery." This implies it met safety and performance requirements for this environment. |
| Electromagnetic Compatibility (EMC) | Compliance with IEC 60601-1-2 Standard for Electromagnetic Interference and Susceptibility. | The SNAP System "was tested to and meets the requirements of IEC 60601-1-2 Standard for Electromagnetic Interference and Susceptibility." |
| Overall Performance | Software performs as intended and meets its performance requirements, being substantially equivalent to the predicate SRP device for shared functionalities, and effectively extending its use to intra-operative navigation. | "Verification and validation results confirm that the SNAP Software meets its' performance requirements." The device is considered "substantially equivalent" to the SRP for its core functions, with additional intra-operative capabilities. |
2. Sample size used for the test set and the data provenance:
- Sample Size for Test Set: The document states that the SNAP was "validated by two neurosurgeons based on historical DIOCM cases (of patients' cases who had their surgeries done in the past)." The specific number of DICOM cases used is not mentioned in the provided text.
- Data Provenance: The data used consisted of "historical DIOCM cases (of patients' cases who had their surgeries done in the past)." This indicates the data was retrospective. The country of origin is not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Two neurosurgeons were used for validation.
- Qualifications of Experts: They are identified as "neurosurgeons," implying medical expertise relevant to the device's application. Specific years of experience or other detailed qualifications are not provided.
4. Adjudication method for the test set:
- The document states that the device was "validated by two neurosurgeons." It does not specify an adjudication method (e.g., 2+1, 3+1). It is only mentioned that they performed the validation.
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:
- No MRMC comparative effectiveness study was done comparing human reader performance with and without AI assistance (or in this case, SNAP assistance). The SNAP is described as an image management and navigation assistance tool, not an AI diagnostic tool primarily aimed at improving human reader diagnostic performance. The validation focused on the software's functional correctness and suitability for use, particularly the new intra-operative navigation feature. There is no mention of an effect size related to human improvement with assistance.
6. If standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance assessment was conducted in the sense that the software underwent internal "full testing, verification, and validation by Surgical Theater as part of its' own internal design control requirements" to confirm it meets its performance requirements. The subsequent validation by neurosurgeons assessed the usability and correctness of its output for clinical use, but the core functionality and technical performance were first verified in a standalone manner.
7. The type of ground truth used:
- The ground truth was implicitly derived from the "historical DIOCM cases (of patients' cases who had their surgeries done in the past)." This suggests that the ground truth for validating the 3D reconstructions and navigation display was based on the known anatomy and surgical outcomes of these historical cases, likely interpreted by the validating neurosurgeons. It is most akin to expert consensus/clinical data derived from previously treated cases.
8. The sample size for the training set:
- The document does not specify a sample size for a training set. The device is described as software that reconstructs 3D models from DICOM data based on algorithms, rather than a machine-learning model that would typically require a distinct training set. The SNAP system "utilizes the same identical software as the SRP to create 3D models."
9. How the ground truth for the training set was established:
- As the document does not mention a distinct training set in the context of machine learning, there is no information provided on how ground truth for a training set was established. The software's underlying algorithms for 3D reconstruction and visualization likely rely on established medical image processing principles and were developed and refined through engineering and standard software development practices, rather than by training on a labeled dataset in the modern AI 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).