LVivo Software Application
K243862DiA Imaging Analysis Ltd. · cleared 2025-03-17 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.5)
“The LVivo platform is a software system for automated analysis of ultrasound examinations.”
source quote (p.8)
“Yes. Based on the same machine learning algorithm, multiple rocessing steps were added and the calculated features revised”
source quote (p.8)
“Risk control measures are identified by the threat models and incorporated into the risk analysis process and SW design. The verification and validation testing including 3rd party libraries vulnerability assessment of the SW (SBOM) to ensure that cybersecurity related design requirement are implemented successfully. The company has defined a Cybersecurity plan for ongoing cybersecurity maintenance.”
Validation studies (3)
Bench
sample size not stated
standards: IEC 62304:2006+A1:2015 CSV, Medical Device Software – Software Life-Cycle Processes, IEC 62366-1 Medical devices - Part 1: Application of usability engineering to medical devices, 2015 + AMD 2020., IEC/TR80002-1:2009, Medical device software - Part 1: Guidance on the application of ISO 14971 to medical device software systems, software, and services information
Retrospective clinical
n=170 cases · 3 site(s)
Retrospective clinical
n=101 patients · 1 site(s)
Reported performance (10 observations)
source quote (p.9)
“The Specificity and sensitivity of WMSI were 79% and 82% respectively and the accuracy was found to be 82%.”
source quote (p.9)
“The Specificity and sensitivity of WMSI were 79% and 82% respectively and the accuracy was found to be 82%.”
source quote (p.9)
“The Specificity and sensitivity of WMSI were 79% and 82% respectively and the accuracy was found to be 82%.”
source quote (p.9)
“WMSI 0.85”
source quote (p.9)
“Expert 1 vs Expert 2 0.64”
source quote (p.9)
“Expert 1 vs Expert 3 0.74”
source quote (p.9)
“Expert 2 vs Expert 3 0.81”
source quote (p.10)
“Specificity 82%”
source quote (p.10)
“Sensitivity 82%”
source quote (p.10)
“Accuracy 82%”
Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.
Predicate network
Postmarket — what happened after clearance
Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device). Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.
Reimbursement — how devices like this got paid
Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).