South Korean startup Lunit, developer of two FDA-approved AI models for healthcare, made public this week on the country’s Kosdaq stock market.
The move marks the maturity of the Seoul-based company, which was founded in 2013 and has been part of the Creation of NVIDIA program that nurtures cutting-edge startups.
Lunit’s AI software for chest X-rays and mammograms is used at 600 healthcare sites in 40 countries. In its home market alone, approximately 4 million chest X-rays per year are analyzed by Lunit AI models.
Lunit has partnered with GE Healthcare, Fujifilm, Philips and Guardant Health to deploy its AI products. Last year, it won FDA clearance for two AI tools: one that scans mammograms for signs of breast cancer and another that triages critical chest x-ray results. It has also received CE marking in Europe for these, as well as a third model that analyzes tumors in cancerous tissue samples.
“By going public, which is just one step in our long journey, I strongly believe that we will succeed and achieve our mission of beating cancer with AI,” said Brandon Suh, CEO of Lunit.
Lunit raised $60 million in venture capital late last year, and its current market capitalization is around $320 million, based on its last closing price. Following its recent regulatory approvals, the startup is expanding its presence in the United States and the European Union. It is also developing additional AI models for 3D mammography.
Forging partnerships to deploy AI for radiology and oncology
Lunit offers four AI products to help radiologists and pathologists detect cancer and provide care:
- CXR OVERVIEW: Trained on a dataset of 3.5 million cases, this tool detects 10 of the most common signs on chest X-rays with 97-99% accuracy.
- MMG OVERVIEW: This product reduces the risk of doctors overlooking breast cancer during screening mammograms by 50%.
- SCOPE: Demonstrating 94% Accuracy, This AI Can Identify 50% More Patients Eligible for Immunotherapy by Analyzing Tissue Slide Images of Over 15 Cancer Types, Including Lung, Breast and Colorectal Cancer .
- SCOPE PD-L1: Trained on more than one million annotated cell images, the tool makes it possible to precisely quantify the expression levels of PD-L1, a protein that influences the immune response.
GE Healthcare made eight AI algorithms of INSIGHT CXR available through its chest care suite to flag chest x-ray abnormalities, including pneumonia, tuberculosis and lung nodules.
Fuji film integrated INSIGHT CXR into their AI-powered product for analyzing chest X-rays. Lunit AI connects to X-ray machines and Fujufilm’s PACS imaging system, and is already used at more than 130 locations across Japan to detect chest nodules, collapsed lungs, and fluids or other foreign substances in lungs.
Phillipsalso adopts INSIGHT CXR, making the software accessible to users of its X-ray diagnostic solutions. And Guardian of healtha liquid biopsy company, made a $26 million strategic investment in Lunit to support the company’s innovation in precision oncology with Lunit SCOPE tissue analysis products.
Accelerate insights with NVIDIA AI
Lunit develops its AI models using various NVIDIA Tensor Core GPUsincluding NVIDIA A100 GPUs, in the cloud. Its customers can deploy Lunit’s AI with an NVIDIA GPU-powered server on-premises or in the cloud – or in a medical imaging device using the NVIDIA Jetson state-of-the-art AI platform.
The company also uses NVIDIA TensorRT software to optimize its trained AI models for real-world deployment.
“The goal here is to optimize our AI in real user settings – for specific NVIDIA GPUs that leverage AI,” said Donggeun Yoo, head of research at Lunit.
Over the years, Lunit has presented its work at the NVIDIA GTC and as an NVIDIA Inception member at the prestigious RSNA conference for radiology.
“It was very helpful for us to build our credibility as a startup,” Yoo said. “I think joining Inception helped spark the biggest recognitions that followed from the healthcare industry.”
To subscribe to NVIDIA Health News.