AI Science Tracker
EN

An end-to-end AI-based framework for automated discovery of rapid CEST/MT MRI acquisition protocols and molecular parameter quantification (AutoCEST)

Martinos Center, Massachusetts General Hospital and Harvard Medical School; Max Planck Institute for Biological Cybernetics; University Hospital Erlangen · 10 Jul 2021 · medicine

Discovery

An end-to-end AI-based framework for automated discovery of rapid CEST/MT MRI acquisition protocols and molecular parameter quantification (AutoCEST)

Source check: Source checked. Not independent scientific confirmation.

Finding: AutoCEST jointly optimizes CEST/MT acquisition schedules and a deep reconstruction network. Phantom measurements showed concentration error of 2.42 ± 2.53 mM (r=0.992), versus 65.19 ± 34.48 mM with an unoptimized schedule; mouse-brain imaging is a proof of concept, not clinical validation.

Technology: AutoCEST differentiable acquisition-schedule optimization and deep neural reconstruction

Publication: Peer-reviewed paper · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
A differentiable system jointly optimizes CEST/MT acquisition schedules and a deep neural network for parameter reconstruction.
Test and result
Generated schedules took 35–71 seconds; phantom concentration maps closely matched known values and mouse-brain maps showed expected tissue patterns.
Limitation / still unknown
Validation is limited to chemical-exchange phantoms and one in-vivo mouse-brain setting; no clinical validation is reported.
Evidence sources and annotation context

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

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC9305180/?report=xml

Source checked · editorial details

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

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary full-text Methods and Results and arXiv v1 reviewed; version chronology checked..

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 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.