NVIDIA Inception Startups Use AI to Close Breast Cancer Care Gaps

Breast cancer care faces significant bottlenecks, including missed screenings, a projected shortage of tens of thousands of radiologists, and treatment decisions delayed by weeks-long genomic assays. NVIDIA Inception startups are deploying AI applications to address these friction points across imaging, risk assessment, and treatment planning.

Accelerating Imaging and Screening

iSono Health offers the FDA-cleared ATUSA platform, a wearable, automated 3D quantitative ultrasound system. It captures a standardized breast volume in approximately two minutes per breast, compared to up to 45 minutes for conventional handheld ultrasound. The system, trained on over 1.5 million ultrasound frames, is claimed to be 28% more sensitive than handheld 2D ultrasound and is commercially available in several U.S. states.

Whiterabbit.ai provides FDA-cleared WRDensity software for assessing breast density and WRRisk for estimating long-term cancer risk. The company is developing AI to help radiologists detect more cancers while automating the screening of negative mammograms, aiming to reduce the burden on a strained workforce and lower healthcare costs.

Enhancing Treatment Decisions

Ataraxis AI builds clinical intelligence that predicts patient outcomes and therapy responses using digital pathology slides and standard clinical variables. Its models predict whether presurgical chemotherapy will shrink tumors and estimate five-year recurrence risk post-surgery. Validated across more than 10 institutions, these models run on NVIDIA GPUs using PyTorch and NVIDIA CUDA.

SimBioSys creates AI-powered 3D models of breast tumors and soft tissue to guide surgeries and treatment plans. Using NVIDIA MONAI and CUDA-X libraries, the platform integrates multimodal data—including imaging, pathology, and genomics—to generate insights beyond individual data points, helping physicians make faster decisions.