AI Science Tracker
EN

Wright State University

1 discovery from 2022

Discoveries

Machine Learning for Aiding Blood Flow Velocity Estimation Based on Angiography

Source check: Source checked. Not independent scientific confirmation.

Finding: MLP, CNN and LSTM models estimated blood-flow velocity fields from angiographic projection images and were compared with optical-flow/PIV measurements in an in-vitro dye-flow rig (5,071 points). The MLP reported lower mean absolute error than LASSO; this controlled proof-of-concept does not establish patient diagnosis or clinical utility.

Technology: MLP, CNN and LSTM regress blood-flow velocity fields from angiographic projection images.

Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
MLP, CNN and LSTM regress blood-flow velocity fields from angiographic projection images.
Test and result
The MLP, CNN and LSTM velocity estimates were compared with 5,071 PIV/optical-flow points; MLP mean absolute error was reported as 5×10⁻⁴ versus 3×10⁻³ for LASSO.
Limitation / still unknown
Evidence is limited to the controlled in-vitro rig; patient diagnosis and clinical utility were not tested. The publisher-hosted PDF denied access (HTTP 403), and Crossref listed no affiliation, so the record states that the affiliation was not provided.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.preprints.org/manuscript/202209.0460/v1/download · https://api.crossref.org/works/10.20944/preprints202209.0460.v1

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: linked separately.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 3/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.