(45 days)
The SuRgical Planner (SRP) BrainStorm is intended for use as a software interface and image segmentation system for the transfer of image information from a CT, MR, or X-ray 3D Angiography (XA) medical scanner to an output file. It can also be used for pre-operative planning and surgical training in a virtual environment.
The SuRgical Planner (SRP) BrainStorm is intended for use as a software interface and image segmentation system for the transfer of image information from a CT, MR, or X-ray 3D Angiography (XA) medical scanner to an output file. It can also be used for pre-operative planning and surgical training in a virtual environment.
The SuRgical Planner (SRP) BrainStorm is not intended to be used for diagnosis.
The SRP BrainStorm software has the ability of creating 3D models of the patient data from 2D scan slices. Additionally, it provides the user with the ability to input, display, color, and manipulate the 2D scan slices via a 3D representation. The software transforms 2D medical images into a dynamic interactive 3D scene with multiple point of views on a high-definition (HD) touch screen monitor. The use of a virtual reality (VR) or augmented reality (AR) headset provides the surgeon a 3D stereoscopic display of the same scene inside the VR / AR headset. While wearing the VR / AR headset, the surgeon can perform a virtual / simulated "fly-through" inside the 3D scene using controllers to perform such actions as rotate, zoom in and zoom out. The use of the SuRgical Planner (SRP) BrainStorm with VR / AR headset and controllers is not intended for use during surgery. The SRP BrainStorm is intended for use for pre-operative planning.
The SRP BrainStorm software includes additional features to facilitate the review of relevant data by a multidisciplinary team that includes neurosurgeons and neurologists for pre-operative surgical planning.
The SRP BrainStorm product does not include any custom hardware and is a software-based device that runs on a high-performance desktop PC assembled using "commercial off-the-shelt" components that meet minimum performance requirements. The design is based on an advanced, touch screen friendly, Graphical User Interface (GUI) that runs an underlying simulation engine to process medical images in DICOM format, and an image generator software engine.
This 510(k) premarket notification describes a software device, SuRgical Planner (SRP) BrainStorm, which is intended for use as a software interface and image segmentation system for the transfer of image information from medical scanners to an output file. It is also used for pre-operative planning and surgical training in a virtual environment. The submission focuses on demonstrating substantial equivalence to a predicate device, SuRgical Planner (SRP) (K170793), rather than presenting a study to prove the device meets specific performance acceptance criteria for a new clinical task.
Therefore, much of the requested information regarding acceptance criteria and performance study specifics (like sample size, number of experts, adjudication methods, MRMC studies, standalone performance, and ground truth detailed establishment for training/test sets) is not applicable or not explicitly detailed in the provided document. The document describes a verification and validation (V&V) plan to confirm the device meets its intended use and performance requirements, implying internal testing rather than a clinical effectiveness study against predefined criteria like sensitivity or specificity.
Here's a breakdown of the available information:
1. A table of acceptance criteria and the reported device performance:
The document does not provide a table of acceptance criteria with numerical performance targets (e.g., sensitivity, specificity, accuracy) or quantitative performance results. Instead, it states:
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Functional Equivalence: The SuRgical Planner (SRP) BrainStorm performs its intended functions (image segmentation, 3D model creation, 3D scene display, VR/AR integration, pre-operative planning, surgical training) as described in the device description. | "A formal verification and validation plan was executed to confirm that the SRP BrainStorm meets its intended use and performance requirements." "Verification and validation tests demonstrated the SRP BrainStorm is as safe and effective as the predicate SRP, and performs as intended in the specified use conditions." |
| Safety and Effectiveness Equivalence: The modifications implemented in SRP BrainStorm do not raise any new questions regarding safety and effectiveness compared to the predicate device. | "The differences between the subject and predicate device do not raise any new questions regarding safety and effectiveness." "Based on the information provided in this 510(k) submission, the SRP BrainStorm is considered substantially equivalent to the predicate SRP in terms of fundamental scientific technology." "Any differences between the subject and predicate device do not raise any new concerns regarding safety and effectiveness." |
| Usability/Human Factors: The modifications to the device (e.g., AR support, simplified planner mode features) conform to user needs and the intended use. | "In addition, simulated use human factors and usability validation was performed to validate the modifications conform to the user needs and the intended use of the device." |
| Design Control Compliance: Software design verification and validation testing followed internal design control requirements and methods. | "Software design verification and validation testing was performed per the same internal design control requirements and methods used for the predicate device." |
2. Sample size used for the test set and the data provenance:
- Sample Size: Not specified. The document only mentions "a formal verification and validation plan was executed" and "verification and validation tests were performed."
- Data Provenance: Not specified. The source or nature of the data used for the V&V tests (e.g., type of medical images, number of cases, patient demographics, country of origin) is not provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not specified. The document does not describe the use of experts to establish ground truth for a test set in the context of a performance study. Given the nature of the device (software interface and planning tool for pre-operative use), the "ground truth" might refer to the accurate representation of anatomical structures or functional software execution, which would be validated internally rather than through expert clinical review against specific diagnostic criteria.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Not specified. No adjudication method is mentioned, as there is no description of a performance study involving comparison to a ground truth established by multiple experts.
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 is mentioned. The device's purpose is not described as an AI-assisted diagnostic tool for human readers but rather as a planning and training tool.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not explicitly detailed, but the context of "verification and validation tests" implies testing of the software's functionality and performance as an algorithm. The device's primary function is a standalone software system for image processing, 3D modeling, and visualization, with human interaction being part of its intended use (e.g., surgeons using VR/AR headsets). It can be inferred that the software's ability to perform its core functions (e.g., segment images, create 3D models) independently was evaluated.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Not explicitly defined in the document. For a device like SRP BrainStorm, "ground truth" during verification and validation would likely involve:
- Reference Image Data: Comparing segmented 3D models against known anatomical structures from original medical images.
- Functional Specification Compliance: Ensuring that the software performs its specified functions (e.g., correct import/export, proper 3D rendering, accurate display of electrode detections) as designed.
- Usability/User Interface Testing: Confirming that the user interface and interactions (e.g., with VR/AR headsets) meet design requirements and user expectations for pre-operative planning.
8. The sample size for the training set:
- Not applicable. This device is described as an image processing and visualization tool, not an AI/ML algorithm that is trained on a specific dataset for diagnostic or predictive purposes. The "training" mentioned in the context of the device is for surgical training using the virtual environment, not algorithm training.
9. How the ground truth for the training set was established:
- Not applicable for algorithm training set ground truth. For the surgical training aspect, the "ground truth" is typically the anatomical and physiological accuracy of the virtual environment, which would be established through careful modeling based on medical imaging data and validated by anatomical expertise. However, this is not a training set for the algorithm itself.
§ 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).