(152 days)
The Clear Guide SCENERGY is software that provides fusion of images from Computed Tomography (CT), Magnetic Resonance (MR), and Ultrasound (US) modalities. US images can be fused with either CT or MR.
The Clear Guide SCENERGY utilizes the Clear Guide CORE and Clear Guide SuperPROBE platform to display images of the target regions and the projected path of the interventional instrument, while taking into account patient movement and deformation. Instrumentation used with the Clear Guide SCENERGY might include an interventional needle or needle-like rigid device, such as a biopsy needle, an aspiration needle, or an ablation needle. The device is intended to be used in any interventional or diagnostic procedure where the combination of these modalities is used for visualization, except for procedures on the brain. The device is intended for use in a clinical setting, in patients of sufficient size (at least 25 kg).
The Clear Guide SCENERGY guidance system is intended to be an accessory to existing ultrasound imaging systems, to provide image fusion, instrument tracking, and image/instrument guidance functionality to operators during image-guided medical interventions that utilize data from multiple modalities (e.g., ultrasound and computed-tomography (CT), ultrasound and magnetic resonance (MR)). The Clear Guide SCENERGY uses optical detection technology to identify and track objects in the field of view. By pairing this information with the aforementioned imaging data, the Clear Guide SCENERGY executes proprietary software algorithms to display fused images in real-time to the clinician. These segmentation and registration algorithms are automated. Segmentation results are deterministic, meaning that new inputs (e.q., new CT or MR) would be required to change the segmentation output. Registration can be reset by the user at any time during use.
The Clear Guide SCENERGY is a software device that provides fusion of images from Computed Tomography (CT), Magnetic Resonance (MR), and Ultrasound (US) modalities. The device utilizes optical detection technology to identify and track objects, overlaying instrument positioning data onto existing ultrasound images through proprietary software algorithms for segmentation and registration.
Here's an analysis of the acceptance criteria and study information provided:
1. Table of Acceptance Criteria and Reported Device Performance:
The document describes the type of tests performed rather than specific numerical acceptance criteria. However, it indicates that the device's performance was evaluated to ensure its safe and effective operation compared to its predicate.
| Acceptance Criteria Category | Reported Device Performance |
|---|---|
| Segmentation Accuracy | The automatic segmentation of fiducial markers was evaluated by comparing software outputs to manual selection in phantom datasets. (The specific accuracy metrics or thresholds met are not detailed in this summary.) |
| Fusion Quality (TRE) | The device's ability to provide fused US and CT/MR images was assessed using Tissue Registration Error (TRE). This involved taking distance measurements between identifiable landmarks or surfaces on ultrasound and CT, or ultrasound and MR. (Specific TRE thresholds or results are not provided.) |
| Systematic Error ("Tip-to-Tip" Tracking Error) | This metric, also known as "tracking error" for the predicate device, measures the cumulative error across segmentation, registration, fusion, and guidance. It's defined as the "tip-to-tip" distance from the needle point seen by ground truth CT (or MR) to the same needle point displayed by the Clear Guide SCENERGY's guidance. Phantom datasets were used for this evaluation. (Specific error ranges or maximum deviations are not provided.) |
| Clinical Safety in Pediatric Patients | A small safety study was conducted to demonstrate the safe usability of the Clear Guide SCENERGY in pediatric patients without raising new safety or effectiveness concerns. The study included patients aged 5 to 17 and weighing 11.9 to 78.9 kg, to represent children and adolescents. (Specific safety endpoints or results are not detailed, but the conclusion states no new or different questions of safety or effectiveness were raised). |
| Overall Safety and Effectiveness | "Performance data was collected to demonstrate that the Clear Guide SCENERGY achieves its intended function in a manner that is as safe and as effective as the predicate device." "Results of performance testing show that the subject device is as safe and as effective as the predicate device." |
2. Sample Size Used for the Test Set and Data Provenance:
- Segmentation Testing: "phantom datasets" (specific number not provided). Data provenance is synthetic (phantom).
- Fusion Testing: Utilized phantoms. (Specific number of phantom datasets not provided). Data provenance is synthetic (phantom).
- Systematic Error (Tip-to-Tip) Testing: "Phantom datasets were utilized for this evaluation." (Specific number not provided). Data provenance is synthetic (phantom).
- Clinical Testing: "A small safety study was run... The study included patients ranging in age (5 to 17) and weight (11.9 to 78.9 kg) to demonstrate use in children and adolescents." (Specific number of patients not provided, but implies a prospective clinical study involving human subjects). The country of origin for this clinical data is not specified. It's a prospective study.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
The document does not explicitly state the number of experts used for establishing ground truth or their qualifications.
- For Segmentation Testing, ground truth for fiducial markers was established by "manual selection." It's implied this was done by human experts, but their number and qualifications are not provided.
- For Fusion Testing and Systematic Error Testing, ground truth was based on measurements from phantom datasets and comparison to "ground truth CT (or MR)." The process for establishing this phantom-based ground truth or any expert involvement in verifying it is not detailed.
- For the Clinical Testing, the safety assessment would have involved clinicians, but their role in establishing ground truth for device performance measurements (if any were taken) is not specified.
4. Adjudication Method for the Test Set:
The document does not describe any specific adjudication method (e.g., 2+1, 3+1) for the test sets. For tests involving "manual selection" or comparison to "ground truth CT/MR," it implies a singular reference standard rather than an adjudicated consensus process.
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 with and without AI assistance is described in the provided text. The studies focus on the standalone performance of the device and its safety.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:
Yes, standalone performance (algorithm only) was assessed for:
- Segmentation Testing: Comparison of software outputs to manual selection in phantom datasets.
- Fusion Testing: Evaluation of the device's ability to provide fused images and assessment of Tissue Registration Error (TRE) using phantom datasets.
- Systematic Error (Tip-to-Tip) Testing: Measurement of cumulative error by comparing the device's displayed guidance to ground truth CT/MR needle points in phantom datasets.
These tests evaluate the device's algorithmic performance in isolation.
7. The Type of Ground Truth Used:
- Segmentation Testing: Ground truth was established by "manual selection" in phantom datasets, implying expert human judgment on fiducial markers.
- Fusion Testing: Ground truth was based on identifiable landmarks or surfaces on ultrasound and CT/MR in phantom datasets.
- Systematic Error (Tip-to-Tip) Testing: Ground truth was based on the "needle point seen by ground truth CT (or MR)" in phantom datasets.
- Clinical Testing: The "small safety study" would likely have relied on clinical observations and assessments by healthcare professionals for safety endpoints.
8. The Sample Size for the Training Set:
The document does not provide any information regarding the sample size used for the training set for the segmentation, registration, or fusion algorithms.
9. How the Ground Truth for the Training Set Was Established:
The document does not provide details on how the ground truth for the training set was established, as no information on the training set itself is given.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.