HealthFLD is an AI-powered software that analyzes CT images of the liver to provide clinicians with quantitative and qualitative measurements of liver attenuation, aiding the assessment of fatty liver disease. It processes both non-contrast and contrast CT scans for adult patients and outputs liver density metrics to support clinical decision-making.
The HealthFLD device is an image processing software that provides quantitative and qualitative analysis of the liver from CT images to support clinicians in the evaluation and assessment of Fatty Liver. Provides measurements of liver attenuation (mean HU in a region of interest). Indicated for use in non-contrast and contrast CT scans, with any clinical indication, for patients aged 18 up to 75. CTs must include significant part of the liver. Not intended to provide diagnosis or risk assessment of fatty liver disease.
HealthFLD processes DICOM CT images, validates input data for compatibility, uses a deep-learning based algorithm for liver segmentation and quantification of liver attenuation in Hounsfield Units (HU). Adjusts thresholds based on contrast phase detection automatically. Outputs are annotated liver attenuation values in selected regions of interest.
Performance was validated in a retrospective study with 250 anonymized CT scans, comparing HealthFLD outputs to ground truth defined by three US board-certified radiologists. The device demonstrated high agreement with ground truth in liver attenuation measurements (95.98% overall agreement for <40HU threshold) and portal venous phase identification (95.98%). Bland-Altman limits of agreement were within acceptable range, and the device showed 100% yield on validation dataset.
No predicate devices specified
Submission
9/26/2023
FDA Approval
2/8/2024
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.