Median LCS (internal name) / eyonis LCS (trade name) (1.0)

eyonis® LCS 1.1 is an AI/ML-based software (SaMD) for lung cancer screening that detects, localizes, and characterizes solid and part-solid pulmonary nodules measuring 4–30 mm on low-dose chest CT images. It generates a DICOM result report with malignancy scores and is intended to aid radiologists' diagnostic interpretation, not replace clinical judgment.

eyonis® LCS provides a simplified 10-point discrete malignancy score with associated malignancy rates, whereas the predicate (Transpara™ 2.1.0) provides a continuous 100-point score; both employ deep learning models trained on large databases of proven cancer and benign cases. Both are software-only CADe/CADx devices without integrated viewers, using container-based deployment and DICOM output. The predicate distinguishes two finding types (calcifications and soft tissue); eyonis® LCS targets only nodules (solid/part-solid).

IEC 62366-1 (usability engineering), ISO 20417 (labeling), ISO 14971 (risk management), IEC 62304 (software lifecycle), IEC 82304-1 (health software safety), ISO 15223-1 (symbols), and NEMA PS 3.1–3.20 (DICOM). FDA guidance documents on software validation, 510(k) evaluation, cybersecurity, human factors, and quantitative imaging were also applied.

eyonis® LCS is substantially equivalent because it shares the same intended use (concurrent reading aid for screening populations), classification (Class II, 21 CFR 892.2090, product code QDQ), design (software-only CADe/CADx), and fundamental AI/ML technology as the predicate. Differences in scoring format (10-point vs. 100-point), target findings (nodules only vs. calcifications and soft tissue), and output presentation do not raise new safety or effectiveness concerns because both devices function identically in clinical workflow and are subject to the same regulatory controls.