LiverMultiScan

K202170

Perspectum LTD · cleared 2020-10-02 · product code LNH · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
LiverMultiScan is a standalone software device.
AlgorithmThe algorithm uses the LMS IDEAL method for PDFF quantification and liver fat quantification. T2* parametric maps can be computed using the three-point DIXON method or the LMS MOST method. It also supports automatic multi-slice full liver segmentation of cT1 and PDFF parametric maps.
source quote (p.9)
PDFF is quantified using the LMS IDEAL method. Parametric maps of T2* may be optionally be computed using either the three-point DIXON method or the LMS MOST method. Utilizes MR images that exploit the difference in resonance frequencies between hydrogen nuclei in water and triglyceride fat using the LMS IDEAL method. LMSv4 supports automatic multi-slice full liver segmentation of the cT1 and PDFF parametric map, use of this functionality is at the discretion of the operator instead or in combination with the ROI based method.
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.5)
Validation and verification activities were conducted in a controlled environment and in compliance with IEC 62304:2006, ISO 13485:2016 and 21 CFR 820. LMSv4 is also in compliance with the DICOM standard.

Validation studies (2)

Bench

sample size not stated

endpoints: Accuracy; Precision

Retrospective clinical

sample size not stated

endpoints: Repeatability; Reproducibility

Reported performance (6 observations)

accuracyas written: “cT1 Accuracy (1.5T)stated without valueCI -189.5 to -35.11 ms
source quote (p.10)
cT1 -189.5 to -35.11 ms
accuracyas written: “cT1 Accuracy (3T)stated without valueCI -187.0 to -19.12 ms
source quote (p.10)
cT1 -187.0 to -19.12 ms
accuracyas written: “T2* Accuracy (1.5T)stated without valueCI -0.68 to 0.64 ms
source quote (p.10)
T2* -0.68 to 0.64 ms
accuracyas written: “T2* Accuracy (3T)stated without valueCI -0.30 to 0.39 ms
source quote (p.10)
T2* -0.30 to 0.39 ms
accuracyas written: “IDEAL PDFF Accuracy (1.5T)stated without valueCI -3.80 to 6.08%
source quote (p.10)
IDEAL PDFF -3.80 to 6.08%
accuracyas written: “IDEAL PDFF Accuracy (3T)stated without valueCI -1.39 to 5.58%
source quote (p.10)
IDEAL PDFF -1.39 to 5.58%

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

100
recalls in product code, 24mo
510
MAUDE reports in code, 12mo
+5%
vs code's own 3-yr baseline
4
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K253413 (decision 2026-03-09) from Perspectum, Ltd. for a matching device line ("LiverMultiScan (v6.0)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K253413

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K213960 (decision 2022-09-06) from Perspectum for a matching device line ("LiverMultiScan v5 (LMSv5)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K213960

  • recall_reason_pattern

    Software/algorithm-related recall in product code LNH (Philips North America, initiated 2026-04-14): "The potential for stiffness value errors when a specific range of image reconstruction parameters is used in combination with Resoundant's algorithm, leading to the reconstruction " Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98779

  • recall_reason_pattern

    Software/algorithm-related recall in product code LNH (Philips North America, initiated 2025-12-03): "The potential for stiffness value errors when viewing exported MR Elastography (MRE) stiffness maps to viewer Picture Archiving and Communication System (PACS)." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98111

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).

RIGOR™ Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: radar.healthai.com/precedent/device/K202170