Subtle Medical Enhances AI Imaging with NVIDIA Technology

Mar 20, 2025
Subtle Medical has integrated NVIDIA's GPU architecture to advance AI-driven medical imaging, improving efficiency and image quality.
Subtle Medical Enhances AI Imaging with NVIDIA Technology

Subtle Medical has integrated NVIDIA's latest GPU architecture to enhance its AI-driven medical imaging solutions, announced in a press release. This collaboration focuses on improving ultra-low-dose imaging and lesion visualization, addressing critical challenges in radiology such as high radiation doses and long scan times.

Subtle Medical's GenAI solutions, powered by NVIDIA's DGX systems and TensorRT/Triton, enable up to a 75% reduction in radiation dose while maintaining image quality. The integration also allows for up to 5x faster scans, reducing patient wait times and increasing scanner throughput. These advancements are crucial for improving diagnostic precision and operational efficiency in healthcare facilities.

The partnership with NVIDIA has also led to significant improvements in AI model training and deployment speeds, with up to 6x faster training and 4.4x faster inference speeds. This technological synergy is set to transform patient care by providing faster and safer imaging solutions, particularly benefiting pediatric and elderly patients who are more vulnerable to long scan times and radiation exposure.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.