Search Results

Liver Suite is an aiding tool for the clinician to review multi-phase liver CT images following LI-RADS® guidelines. Liver Suite is designed to help analyzing liver lesions in patients with known or suspected hepatocellular carcinoma (HCC). It provides optimized series display and a guided workflow to assess relevant clinical features for user-defined observations, to enable computation of a LI-RADS score. It is intended for use by healthcare professionals. The clinician remains ultimately responsible for the final assessment and diagnosis based on state-of-the-art practices, clinical judgment and interpretation of liver images or quantitative data.

Liver Suite is a medical software that offers a guided workflow for the review and assessment of multi-phase CT liver exams per LI-RADS® v2018 guidelines. It is designed to help analyze liver lesions in patients with known or suspected hepatocellular carcinoma (HCC) by providing optimized image display and assessment of intensity metrics related to the 3 major imaging features for LI-RADS scoring. Liver Suite takes phased contrast CT series as input. It only processes one exam at a time (no longitudinal analysis). Liver Suite guided workflow includes: Automatic phase identification of the four hepatic imaging phases: unenhanced, arterial, portal venous and delayed; Semi-automatic lesion contouring based on an initial deposition from the user, user selects applicable appropriate score (LRNC, LR-TIV, LR-1, LR-2 or LR-M) based on image review; A user interface to guide the user in the application of LI-RADS scoring guidelines v2018; User sets the features - non-rim APHE (Yes/No), Enhancing Capsule (Yes/No), Non-peripheral washout (Yes/No), Threshold growth (Yes/No/Not Applicable), Ancillary Features; Automated computation of intensity metrics to help characterize Arterial Phase -Hyper Enhancement (APHE), Washout and Capsule; Automated calculation of LI-RADS score (per LI-RADS v2018 guidelines) from user assessment of major and ancillary features; Display of all measurements in a table for review and export. Identification of hepatic phases is based on a model-based algorithm or can be set manually by the user. Semi-automatic contouring of the lesion is based on the Auto Contour feature and user input. The Auto Contour feature is already part of Volume Viewer (K041521). User sets LI-RADS major and ancillary features and compute associated LI-RADS score. To assist with the assessment of Arterial Phase Hyper Enhancement (APHE), Washout and Capsule, intensity metrics based on enhancement characteristics around the lesion are automatically computed. LI-RADS score is computed based on LI-RADS features using LI-RADS diagnostic table. User can edit the major features, add ancillary features or manually choose a different score.

The provided text does not contain detailed information about the acceptance criteria and the study that proves the device meets those criteria, specifically concerning the performance metrics of the Liver Suite software. It primarily outlines the regulatory approval process (510(k) pathway), the device's intended use, and a comparison to predicate devices.

However, based on the information provided, we can infer some aspects and highlight what is missing for a complete answer to your query:

Here's an attempt to structure the answer based on the available text, with
[Information Not Provided] for missing details:

Acceptance Criteria and Device Performance Study for Liver Suite (K211180)

The provided documentation, a 510(k) summary, focuses on demonstrating substantial equivalence to predicate devices for regulatory clearance rather than a detailed clinical performance study with specific acceptance criteria and results. Therefore, many of the requested details about performance metrics, study design, and ground truth establishment are not explicitly stated.

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not specify quantitative acceptance criteria or a dedicated performance table for the Liver Suite's accuracy in LI-RADS scoring or lesion characterization. Instead, it mentions "Algorithm Qualification (Validation)" and verification activities.

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

• Test Set Sample Size: [Not Provided] The document refers to "a set of expert-annotated lesions" for validating intensity metric distribution, but the number of lesions or cases is not specified.
• Data Provenance: [Not Provided] The country of origin and whether the data was retrospective or prospective are not mentioned.

3. Number of Experts and Qualifications for Ground Truth Establishment:

• Number of Experts: [Not Provided] The document mentions "expert-annotated lesions" but does not specify the number of experts involved.
• Qualifications of Experts: [Not Provided] No details on the qualifications (e.g., specific medical specialty, years of experience, board certification) of the experts are provided.

4. Adjudication Method for the Test Set:

• Adjudication Method: [Not Provided] The method used to establish ground truth from multiple experts (e.g., 2+1, 3+1 consensus, majority vote) or if a single expert was used, is not described.

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

• MRMC Study: [Not Provided] There is no mention of an MRMC study comparing human readers with AI assistance versus without AI assistance. The device is described as an "aiding tool" for the clinician, but no data on its impact on human reader performance is presented.
• Effect Size of Improvement: [Not Applicable, as no MRMC study details are provided]

6. Standalone (Algorithm Only) Performance Study:

• Standalone Study: The document implies some standalone algorithmic validation for specific components:
  • "Engineering bench testing for the Liver Suite Phase Identification algorithm demonstrated the capabilities to identify automatically the two, three or four phases acquired on multi-phases CT images for LI-RADS scoring." No quantitative metrics (e.g., accuracy, sensitivity, specificity) for this standalone performance are given.
  • "APHE. Washout and Capsule intensity metric calculation was verified through testing on synthetic images and validated by comparing intensity metric distribution on a set of expert-annotated lesions." This suggests an algorithm-only evaluation for these specific calculations, but again, no quantitative results are provided.
    However, a comprehensive standalone performance study for the entire LI-RADS scoring process (algorithm-computed score vs. ground truth) is not described.

7. Type of Ground Truth Used:

• Type of Ground Truth: "Expert-annotated lesions" were used for validating intensity metric distribution. This indicates expert consensus/interpretation as the ground truth for those specific features. No mention of pathology or outcomes data is made. For the overall LI-RADS score, the system computes it based on user input of features, implying the ground truth for the features would be expert interpretation, and the algorithm's role is to correctly compute the score based on those user-provided features.

8. Sample Size for the Training Set:

• Training Set Sample Size: [Not Provided] The document does not specify the size of any training dataset used for the underlying models (e.g., phase identification, auto-contouring, or intensity metric calculations).

9. How Ground Truth for the Training Set was Established:

• Training Set Ground Truth Establishment: [Not Provided] The method for establishing ground truth for any training data (e.g., expert annotation, specific criteria, adjudication process) is not detailed.

Ask a specific question about this device