Search Results

SIS Software is an application intended for use in the viewing, presentation of medical imaging, including different modules for image fusion, and intraoperative functional planning where the 3D output can be used with stereotactic image quided surgery or other devices for further processing and visualization. The device can be used in conjunction with other clinical methods as an aid in visualization of the subthalamic nuclei (STN).

SIS Software is an application intended for use in the viewing, presentation and documentation of medical imaging, including different modules for image processing, image fusion, and intraoperative functional planning where the 3D output can be used with stereotactic image guided surgery or other devices for further processing and visualization. The device can be used in coniunction with other clinical methods as an aid in visualization of the subthalamic nuclei (STN).

SIS Software uses machine learning and image processing to enhance standard clinical images for the visualization of the subthalamic nucleus ("STN"). The SIS Software supplements the information available through standard clinical methods, providing additional, adjunctive information to surgeons, neurologists and radiologists for use in visualization and planning stereotactic surgical procedures. SIS Software provides a patient specific, 3D anatomical model of the patient's own brain structures that supplements other clinical information to facilitate visualization in neurosurqical procedures. The software makes use of the fact that some structures in the brain are not easily visualized in 1.5T or 3T clinical MRJ, but are better visualized using high-resolution and high-contrast 7T MRI.

The company's software methodology relies on a reference database of high-resolution brain images (7T MRI) and standard clinical brain images (1.5T or 3T MRI). The 7T images allow visualization of anatomical structures that are then used to find regions of interest within the brain (i.e., the STN) on a patient's clinical image.

SIS visualization is incorporated in the standard clinical MR data, thereby not changing the current standard-of-care workflow protocol and does not require any additional visualization software or hardware platforms.

Here's a breakdown of the acceptance criteria and the study that proves the SIS Software meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are focused on the accuracy of the Subthalamic Nuclei (STN) visualization. The study compared the machine-predicted STN to ground truth STN.

2. Sample Sizes Used for the Test Set and Data Provenance

• Pivotal Validation Test Set: Images from 34 subjects, resulting in 68 STNs (each subject has two STNs).
• Data Provenance: The text does not explicitly state the country of origin. It indicates that the data was retrospective, as it was composed of previously scanned clinical MRI (1.5T and 3T) and High Field (7T) MRI. Crucially, none of these 68 STNs were part of the company's database for algorithm development or optimization/design, ensuring an independent validation set.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

The document does not specify the number of experts or their qualifications for establishing the ground truth for the pivotal validation test set. It only mentions "ground truth STNs (manually segmented clinical images and 7T images superimposed)."

For the developmental testing phase, it refers to the STN as "segmented on the 7T image of that subject." This implies expert segmentation, but details on the number or qualifications of these experts are not provided.

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1, none) for the test set ground truth. It states that the ground truth STNs were "manually segmented clinical images and 7T images superimposed," suggesting a single ground truth was established, likely by an expert or team of experts, but without specifying a review and adjudication process.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done. The study focuses on evaluating the standalone performance of the SIS Software against a pre-established ground truth. There is no mention of human readers assisting with or without AI, or any comparison of human reader performance.

6. Standalone (i.e., algorithm only without human-in-the-loop performance) Study

Yes, a standalone (algorithm only) performance study was conducted. The "Performance Data" section describes how the "subject machine-learning method then predicted the subthalamic nucleus (STN)" and how the "SIS visualization via the subject software" was compared to ground truth. There is no indication of human interaction or interpretation improving the algorithm's output during the validation.

7. The Type of Ground Truth Used

The ground truth used was primarily based on expert defined anatomical structures from High-Field MRI (7T). Specifically, for the pivotal validation testing, it involved "ground truth STNs (manually segmented clinical images and 7T images superimposed)." For developmental testing, it was "the STN as segmented on the 7T image." The 7T MRI is noted to "allow visualization of anatomical structures that are then used to find regions of interest within the brain (i.e., the STN) on a patient's clinical image," implying that the 7T images serve as a higher-fidelity reference for the ground truth.

8. The Sample Size for the Training Set

The document refers to a "reference database of high-resolution brain images (7T MRI) and standard clinical brain images (1.5T or 3T MRI)" which the software methodology "relies on." However, it does not explicitly state the sample size of this training database.

For the developmental testing, which seems to analyze aspects of the training/development process, it mentions "10 subject datasets that were retrospectively selected from the locked SIS reference database." This is a smaller subset used for a specific "leave-one-out" test, not the full size of the training set.

9. How the Ground Truth for the Training Set Was Established

The ground truth for the training set (referred to as the "reference database") was established by using 7T MRI images which "allow visualization of anatomical structures that are then used to find regions of interest within the brain (i.e., the STN)." This implies that experts segmented or labeled the STN structures on these high-resolution 7T images to create the ground truth for the training data that the machine learning model learned from.

Ask a specific question about this device