K-numberK251682
Device nameMuscleView 2.0
ApplicantSpringbok, Inc. (Dba Springbok Analytics)
Product codeLNH
Device classClass II
Decision dateSep 9, 2025
DecisionSubstantially Equivalent
Regulation892.1000
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

MuscleView 2.0 is a software-only diagnostic device that uses locked AI/machine learning algorithms to automatically segment muscle, bone, fat, and other anatomical structures from MRI data. It generates volumetric and dimensional metrics of regions of interest and enables comparison against a Virtual Control Group derived from reference population data. The device is intended for use in adults and pediatric patients aged 18 and older to assist trained clinicians in visualization and quantification of musculoskeletal structures.

Technological characteristics

MuscleView 2.0 expands the predicate device (MuscleView 1.0) from lower extremity segmentation (hips to ankles) to full-body coverage including upper body regions (neck to hips) and adds adipose tissue segmentation (subcutaneous, visceral, intramuscular, and hepatic fat). It incorporates quantitative comparison with a Virtual Control Group and derives additional metrics including Z-scores and composite scores. The AI model remains locked and deterministic with no exposed modifiable parameters.

Test standards cited

Not stated in this summary. The document references FDA guidance on software functions (June 14, 2023) and cybersecurity (September 27, 2023) but does not cite specific ISO, IEC, or ASTM consensus standards.

Substantial equivalence argument

The subject device performs the same function as the predicate—automatic AI-based segmentation of musculoskeletal structures from MRI data to generate quantitative metrics for clinician review—and is intended for the same user population and imaging modalities (1.5T and 3.0T MRI from GE, Siemens, Philips). Although it extends anatomical coverage and adds new derived metrics, performance testing on 148 independent test subjects across diverse demographics and imaging vendors demonstrated segmentation accuracy (via dice similarity coefficient and volume difference) within interobserver variability ranges for nearly all 172 regions of interest, matching the gold standard of expert manual annotation. This performance parity across healthy and patient populations, combined with similar intended use and safety profile, supports substantial equivalence despite expanded functionality.

Extracted by AI from the official FDA summary PDF →
Source

View the full FDA submission: accessdata.fda.gov

Researching this as a predicate?
Want a transparent AI-ranking score, AI-discovered related predicates, ongoing safety and warning-letter monitoring, full predicate chain lineage, and a drafted SE rationale — all saved to your own project? That's what an account adds.
Start free trial →

Everything you need for a 510(k) submission. Nothing you don't.

14-day free trial. No setup. Cancel anytime.

Start free trial →
Building an AI or ML-enabled device? Predicate search, PCCP tracking, and AI-specific FDA intelligence — built exclusively for AI/ML devices. Try AIFDA Intel →