Search Results

BrightMatter Plan is indicated for:

· Viewing, presentation and documentation of medical imaging, including different modules for image processing, image fusion, and image segmentation where the output can be used for image guided surgery.

· Planning and simulation of cranial surgical procedures.

· Reviewing of existing treatment plans.

Typical users of the software are medical professionals, including but not limited to surgeons and radiologists.

BrightMatter Plan is a treatment planning software that enables the user to view and process medical image data. The software is intended for pre-operative planning of neuro-surgical treatments based on image guided surgical systems. The planning software system provides the ability to visualize diagnostic images in 2D and 3D formats and fusion of image datasets. The software automatically segments the skull from the acquired image and generates diffusion tracts from Diffusion Tensor Imaging (DTI) data. The user can also manually annotate regions of interest, resulting in structures which can subsequently be visualized in 3D. A trained person can use the software to segment structures, define regions of interest and establish one or more trajectories.

The software, operated on a stand-alone computer workstation, is expected to be used by a Clinician in an office or home setting, in preparation for one of several possible surgical procedures. The end of the processing is a surgical plan which can be exported to a Picture Archiving and Communication Systems (PACS) for subsequent use in image guided surgery.

Here's a breakdown of the acceptance criteria and study information for BrightMatter Plan 1.6.0, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

Study Details

1. Sample Size used for the test set and the data provenance:

   • Test Set Sample Size: Not explicitly stated as a number of cases/patients. The document mentions "representative preoperative images" for design validation.
   • Data Provenance: Not specified in the provided text (e.g., country of origin, retrospective/prospective). It only mentions "representative preoperative images."

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Number of Experts: Not explicitly stated. The design validation was conducted by "the intended user population," which typically implies multiple clinicians, but a specific number is not provided.
   • Qualifications of Experts: The intended user population consists of "medical professionals, including but not limited to surgeons and radiologists." No specific experience level (e.g., 10 years) is mentioned.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Not specified. The document states "evaluation of resulting plan for conformance to clinical expectations," which implies a qualitative assessment by the users, but no formal adjudication method is detailed.

4. 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 was performed. The non-clinical testing and design validation focused on the software's performance and conformance to clinical expectations, assuming the user would utilize the tool. The comparison was primarily to a previous version of the same device.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

   • The performance testing and unit/integration verification assessed the "algorithm pipeline" and "functional verification," which are inherent to standalone algorithm performance. However, the design validation explicitly involved "the intended user population," indicating a human-in-the-loop evaluation for the overall system. The focus appears to be on the device as a tool for clinicians, rather than a fully autonomous AI system.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • Expert Consensus/Clinical Expectation: The ground truth for the design validation was "conformance to clinical expectations" as determined by the "intended user population." This implies clinical assessment and consensus on the accuracy and utility of the generated plans.

7. The sample size for the training set:

   • Not applicable/Not provided. This device is an updated version of a previous planning software (BrightMatter Plan 1.0) and primarily focuses on image viewing, processing, and surgical planning based on existing medical images. It's not described as a deep learning or machine learning model that requires a distinct "training set" in the conventional sense for a new algorithm. The "underlying technology used to process images is the same" as the predicate device.

8. How the ground truth for the training set was established:

   • Not applicable (see point 7).

Ask a specific question about this device