Search Results

Indications for use vary depending on the specific product and its intended application. These products are designed for use in medical or laboratory settings by trained professionals. Depending on the device, intended uses may include:

• Diagnostic purposes: Analyzing biological samples (e.g., blood, urine, tissue) to identify diseases, conditions, or other health markers. This can include detecting infections, monitoring chronic illnesses, or screening for genetic predispositions.
• Therapeutic procedures: Assisting in or performing medical interventions, such as administering medications, delivering fluids, or providing respiratory support.
• Research and development: Used in laboratory experiments and studies to investigate biological processes, test new drugs, or develop new medical technologies.
• Monitoring physiological parameters: Measuring heart rate, blood pressure, oxygen saturation, or other vital signs.
• Sample collection and preparation: Gathering, processing, and storing biological samples for further analysis.

Specific indications for use are provided in the product's labeling, instructions for use (IFU), or accompanying documentation. Users should always refer to the manufacturer's provided information for the most accurate and complete indications.

{{overview}}

The FDA Clearance Letter for the Swoop® Portable MR Imaging® System (V2) provides details on the acceptance criteria and the studies conducted to demonstrate the device meets these criteria, particularly focusing on the "Advanced Reconstruction" feature which likely incorporates deep learning for image quality optimization.

Here's a breakdown of the requested information:

1. Acceptance Criteria and Reported Device Performance

The core performance of the device's "Advanced Reconstruction" was evaluated through three studies: Performance Analysis, Contrast-to-Noise Ratio (CNR) Validation, and Advanced Reconstruction Image Validation.

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

The document describes three distinct test sets for different validation studies.

• Performance Analysis (Robustness, Stability, Generalizability):

  • Sample Size:
    • T1, T2, FLAIR group: 40 patients, 111 images.
    • DWI group: 29 patients, 94 images.
  • Data Provenance: Not explicitly stated regarding country of origin. The test set was "entirely independent from the dataset used for model training." The "Equipment Type" is listed as "Swoop v2" (with <1% Swoop Mk1.9), indicating prospective data collection or data acquired specifically for the V2 system.

• Contrast-to-Noise Ratio (CNR) Validation:

  • Sample Size: 15 patients, 46 images, 58 pathologies, 464 ROIs.
  • Data Provenance: Not explicitly stated regarding country of origin. The "Equipment" is listed as "Swoop v2," suggesting data acquired for the V2 system.

• Advanced Reconstruction Image Validation (Human Reader Study):

  • Sample Size: 32 patients, 167 images. (Minimum of 16 images per sequence).
  • Data Provenance: Not explicitly stated regarding country of origin. The "Equipment" is listed as "Swoop v2," suggesting data acquired for the V2 system.

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

• Performance Analysis: This study used "a set of images including Swoop data, high field images, and synthetic contrast images" as "ground truth target images." It does not mention human experts directly establishing ground truth for this reconstruction quality metric. The ground truth was based on pre-existing high-quality images.
• Contrast-to-Noise Ratio (CNR) Validation: "Regions of interest (ROI) encompassing pathologies were annotated and reviewed by two American Board of Radiology (ABR) certified radiologists." Their qualifications are explicitly stated: ABR-certified radiologists.
• Advanced Reconstruction Image Validation (Human Reader Study): "Five external, ABR-certified radiologists representing clinical users were asked to review side-by-side clinical image sets." Their qualifications are explicitly stated: ABR-certified radiologists.

4. Adjudication Method for the Test Set

• Performance Analysis: Not applicable as ground truth was defined by reference images and quantitative metrics.
• Contrast-to-Noise Ratio (CNR) Validation: "ROIs were annotated and reviewed by two ABR-certified radiologists." "All annotated images were then reviewed, and inaccurate ROI annotations were excluded from the analysis." This suggests a consensus/review process, but a specific "2+1" or "3+1" formal adjudication is not detailed. The wording implies a collaborative review to ensure quality of ROIs.
• Advanced Reconstruction Image Validation (Human Reader Study): Not applicable, as this was a reader study where each reader independently scored images. There was no explicit adjudication of differences in reader scores for a single case; rather, the median score across all readers was used for evaluation.

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

Yes, a multi-reader multi-case (MRMC) comparative effectiveness study was done. This is the "Advanced Reconstruction Image Validation" study.

• Study Design: Five ABR-certified radiologists reviewed side-by-side clinical image sets (Advanced vs. Linear Reconstruction) and rated image quality and consistency of diagnosis using a five-point Likert scale.
• Effect Size: The study found that "Advanced Reconstruction achieved a median score of 2 (the most positive rating scale value) in all categories."
  • The Likert scale categories were noise, sharpness, contrast, geometric fidelity, artifact, and overall image quality.
  • The acceptance criterion was "median score ≥0 on Likert scale" (at least as good) and "≥1 on Likert scale" in at least one category (better).
  • Achieving a median score of 2 in all categories strongly indicates an improvement in perceived image quality and diagnostic consistency with Advanced Reconstruction compared to Linear Reconstruction. While not a direct measure of diagnostic accuracy improvement (e.g., AUC), it indicates a significant positive effect on the radiologists' perception and utility of the images. The exact numerical improvement (e.g., specific percentage increase in accuracy) is not provided, but the qualitative improvement is clear based on the scoring.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, standalone performance was evaluated through the "Performance Analysis" and the "Contrast-to-Noise Ratio Validation" studies.

• Performance Analysis: The study directly compared the output of the "Advanced Reconstruction" algorithm to a defined ground truth using quantitative metrics (NMSE, SSIM) without human interpretation as the primary endpoint.
• Contrast-to-Noise Ratio (CNR) Validation: This study measured the CNR of the algorithm's output independently, comparing it to the linear reconstruction, to ensure pathology features are preserved. While expert knowledge was used to annotate ROIs, the metric itself (CNR) is a direct, quantitative measure of the algorithm's output.

7. The Type of Ground Truth Used

Different types of ground truth were used depending on the study:

• Performance Analysis: "Reference-based metrics" using "a set of images including Swoop data, high field images, and synthetic contrast images" as "ground truth target images." This implies a reference image-based ground truth for evaluating reconstruction fidelity.
• Contrast-to-Noise Ratio (CNR) Validation: Relied on expert consensus/review for pathology ROI annotation by two ABR-certified radiologists. The CNR metric itself is a quantifiable measure derived from these annotations rather than a clinical outcome.
• Advanced Reconstruction Image Validation: The ground truth for comparative effectiveness was expert consensus/opinion (the subjective ratings of the five ABR-certified radiologists).

8. The Sample Size for the Training Set

The document states: "Performance analysis and validation of the subject device Advanced Reconstruction models was performed using a test dataset entirely independent from the dataset used for model training." However, the exact sample size for the training set is not disclosed in the provided text.

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

The document states: "models are trained and validated with MRI data and images as the only inputs and outputs." It also mentions "synthetic k-space generated from the target images" for the performance analysis, suggesting that synthetic data or high-quality reference scans might have been part of the training data as well. However, the specific method for establishing the ground truth for the training set is not explicitly detailed in the provided text. It implies the training was done using existing MRI data, but does not specify how labels or ideal reconstructions were determined for that training data.

Ask a specific question about this device