LVivo Software Application

LVivo is a software platform that automatically analyzes ultrasound images (DICOM movies) to detect, measure, and calculate cardiac parameters including left ventricular ejection fraction, segmental wall motion, strain, right ventricular function, and bladder volume. It is intended for non-invasive processing of ultrasound images in patients with suspected disease aged >18, with the ability to provide quality score feedback during acquisition.

The submitted device maintains the same modules (PLAX, IQS, EF, SG, SAX, RV, Seamless, Bladder), automation, manual adjustment, biplane EF evaluation, and offline DICOM analysis capabilities as the predicate. The key modification is enhanced segmental wall motion (SWM) evaluation: the submitted device uses the same machine learning algorithm as the predicate but adds multiple processing steps and revised calculated features to improve SWM assessment.

IEC 62304:2006+A1:2015 (Medical Device Software – Software Life-Cycle Processes); IEC 62366-1 (Application of usability engineering to medical devices, 2015 + AMD 2020); IEC/TR80002-1:2009 (Guidance on application of ISO 14971 to medical device software).

The intended use and core technological characteristics are identical to the predicate device. The modification to the SWM module—adding processing steps and revising calculated features within the same machine learning framework—does not change the fundamental algorithm or intended use. Clinical validation on 170 exams (and 101 additional Taiwan cases) demonstrated comparable performance: ICC of 0.85 between automated WMSI and ground truth, with 82% specificity, sensitivity, and accuracy, which is consistent with expert-to-expert variation (ICC 0.64–0.81), demonstrating that the enhanced SWM analysis does not raise new safety or efficacy concerns.