United Imaging Healthcare needed to speed up compute-intensive MR image acquisition and reconstruction so hospitals could shorten scan times, improve image quality, and make MR procedures available to more patients.
Reported impact
United Imaging reduced MR image reconstruction time by nearly 95 percent, increased computational speed by more than 10x with additional 3x algorithm acceleration, and enabled clinical teams to shorten patient time in scanners while expanding access to MR procedures.
United Imaging Healthcare built an AI-enabled MR imaging stack on NVIDIA accelerated computing to move reconstruction from a slow HPC bottleneck into a practical clinical workflow. Streaming sensor data from its MR systems is fed into proprietary reconstruction algorithms that run on NVIDIA data center GPUs, while the NVIDIA CUDA Toolkit is used to optimize those algorithms across environments. The team also uses cuSolver to accelerate the matrix-heavy image-reconstruction steps that previously took too long for clinical needs. NVIDIA AI Enterprise provided enterprise software support, DevTech guidance, and migration help as United Imaging product teams brought the scanner to market. Combined with the company's AI-assisted compressed sensing approach, this architecture cuts reconstruction time dramatically while preserving image quality and supporting broader access to MR imaging.
Streaming MR sensor data enters United Imaging's proprietary reconstruction pipeline, GPU-accelerated algorithms and cuSolver process the matrix-heavy workloads, optimized CUDA-based code generates reconstructed images faster, and the results are delivered back to clinical teams with shorter patient time in the scanner.
NVIDIA engineers tailored an algorithm that increased computational speed by more than 10X and significantly reduced the time required for MR reconstruction.
They deployed NVIDIA AI and accelerated computing solutions in an AI-enabled magnetic resonance (MR) scanner to reduce patient time in MR machines while increasing access to MR procedures.
United Imaging Health also used cuSolver, NVIDIA's high-performance matrix computation library, to accelerate the reconstruction of MR images.
United Imaging Healthcare's team reduced image construction time by nearly 95 percent.
Using NVIDIA data center GPUs, their products and engineering teams increased the performance and speed of their HPC algorithms, necessary for streaming sensor data to image pipelines.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
NVIDIA Sample Sep 22, 2026 DELFI Diagnostics DELFI Diagnostics needed to speed genomic analysis for cancer screening and therapeutic monitoring, but CPU-bound alignment and somatic variant-calling steps created turnaround-time and cost bottlenecks that limited how… 10–20 business days DeepSomatic · MutectCaller · NVIDIA Parabricks NVIDIA Sample Jul 10, 2026 Astellas Pharma Inc. Astellas needed to shorten the slow handoff between experimental scientists and computational chemists in early drug discovery so more researchers could use structure prediction and affinity screening without waiting on… More than 50 regular users and over 2,000 total users within four months NVIDIA BioNeMo · NVIDIA Boltz-2 NIM · NVIDIA DGX H100/H200 NVIDIA Sample Apr 23, 2026 Biofy Hospitals needed pathogen identification and antibiotic-resistance analysis much faster than five-day culture and antibiogram workflows, but CPU-bound genomic processing and limited AI expertise made it hard to turn… 100,000+ synthetic DNA sequences generated by the biology model Abby · H100 Tensor Core GPUs · NVIDIA CUDA-accelerated libraries 