Siemens Healthineers needed to speed up radiation-oncology model development and reduce the time clinicians spend contouring organs at risk so treatment planning could scale with rising cancer demand.
Reported impact
Siemens Healthineers automated organ contouring in radiation therapy, helped clinicians focus on other patient-care tasks, and built a training platform that supports hundreds of daily experiments and more than 45 approved AI applications.
Siemens Healthineers uses its Sherlock AI supercomputer to industrialize machine-learning development for radiation oncology, especially the organ-contouring step that slows treatment planning. Sherlock combines NVIDIA HGX-1 and HGX-2 servers loaded with NVIDIA Tesla V100 GPUs, NVLink interconnects, 3 petabytes of NVMe storage, and a 100 Gbps Mellanox InfiniBand fabric so researchers can keep GPUs saturated and run more than 600 deep-learning experiments each day. The cluster trains AI models behind syngo.via RT Image Suite, including AutoContouring models built on more than 4.5 million images. Once trained, those models automatically outline 47 organs for radiation-oncology workflows, giving clinicians faster starting points for therapy planning while the same platform supports more than 45 approved AI applications across the broader imaging portfolio.
Curated medical images and related clinical data are used to train AutoContouring models on the Sherlock cluster, and the trained models are delivered through syngo.via RT Image Suite to automatically outline organs during radiation-therapy planning.
AI-assisted AutoContouring helps save time and improve standardization in organs-at-risk contouring.
So far, Sherlock has led to the development of more than 45 AI-powered applications approved for clinical use.
The system provides 24 PetaFlops of processing performance and 3 PetaBytes of NVMe storage, connected over a high-speed 100 Gbps Mellanox InfiniBand network, and is used to run over 600 deep learning experiments daily.
Trained on over 4.5 million images using the Sherlock supercomputer, the AI tool automatically outlines 47 organs.
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 