I am pleased to announce the release of my latest open-source addition: BatchTriDFusion v1.0.0.
Rather than running a single workflow at a time, BatchTriDFusion enables parallel execution of TriDFusion (3DF) workflows, with the number of instances optimized to your GPU memory. This allows researchers to scale AI and imaging projects without being constrained by hardware bottlenecks.
What makes it powerful?
Speed at scale: process large cohorts in a fraction of the time.
Hardware-aware: every GPU counts, whether small or large.
Consistent outputs and unified TriDFusion (3DF) workflow results are delivered in a ready-to-analyze table.
Simple to run, set the protocol, control parallelism, and monitor progress with ease.
In practice, this means that cohorts of thousands of studies can be processed in parallel with the TriDFusion (3DF) AI workflow across multiple systems, dramatically reducing analysis time while ensuring reproducible results.
Perfect for research teams handling large imaging cohorts who want to accelerate outcomes and make the most of their available hardware.
If you use TriDFusion (3DF) please cite it:
Lafontaine D, Schmidtlein CR, Kirov A, Reddy RP, Krebs S, Schöder H, Humm JL. TriDFusion (3DF) image viewer. EJNMMI Phys. 2022 Oct 18;9(1):72. doi: 10.1186/s40658-022-00501-y. PMID: 36258098; PMCID: PMC9579267.
Daniel Lafontaine