Top-notch medical AI technology at the tip of your fingers
Lunit’s AIs are trained by a huge collection of de-identified clinical data from Lunit’s partner hospitals, 18 in total number of partnerships. The total number of images that has been directly used in its research has reached over 1 million well-curated high-quality case images. With the given image data, the AI algorithms are then specifically trained to detect target diseases or radiologic findings, including lung cancer, tuberculosis, pneumonia, pneumothorax, and breast cancer for chest x-ray and mammograms.
Based on this top-notch AI technology, Lunit is to introduce , a cloud-based imaging AI platform that is currently available to the public at https://insight.lunit.io/. The platform delivers Lunit’s state-of-the-art AI models; the first one to be unveiled is the chest x-ray solution. Lunit’s chest x-ray solution detects major chest abnormalities, lung nodule/mass, consolidation, and pneumothorax, with an unprecedented high level of accuracy 一 97% standalone accuracy in nodule detection, 99% for consolidation and pneumothorax.
According to the National Lung Screening Trial (NLST), one of the largest clinical trials conducted on lung cancer screening, 26.5% of lung cancer cases were shown to be missed by chest x-ray. Worldwide, more than 1 billion chest x-ray exams are performed every year. Decreasing the proportion of missed cases even by 10% would translate into significant clinical benefit.
What’s foremost remarkable is how Lunit’s AI solutions have been proven to significantly increase the diagnostic performance of its users up to 20%, from non-radiology physicians to radiology experts. Lunit’s solutions are designed to augment the diagnostic performance level of its users as the “second reader,” not replace them.
“Lunit’s vision is to develop advanced software for medical data analysis and interpretation that goes beyond the level of human vision,” said Anthony S. Paek, CEO of Lunit. “In presenting Lunit INSIGHT, we hope to contribute in opening a new era of medical practice, by helping and empowering healthcare professionals to make more accurate, consistent, and efficient clinical decisions for the patients.”
Users can upload their medical images via online, at Lunit INSIGHT webpage. AI analysis results appear in just a few seconds, including not only the level of abnormality, but also the visualization of the AI’s attention map. Lunit’s solutions will also be presented integrated into the systems of various companies including Nuance, EnvoyAI, and Infinitt Healthcare.
“Featured” in RSNA; development in process for mammography solution
Lunit was chosen as “featured” exhibitor of RSNA in a consecutive two year since its initial presentation last year. This year, Lunit’s exhibition booth is part of the “machine learning showcase,” along with Google Cloud, NVIDIA, and other top exhibitors. On Tuesday, 28 November, Brandon B. Suh, Chief Medical Officer, will give a presentation, “Lunit INSIGHT: Toward Beyond-Human-Level AI for Medical Imaging Modalities,” at Machine Learning Theater. A press conference and demonstration at Lunit booth will be followed shortly after the presentation.
In order to launch meaningful AI solutions that has high clinical impact, proper clinical validation is an important part of the process. “Large-scale multi-center reader studies are set to be conducted in early 2018,” said Suh, Chief Medical Officer of Lunit. “These are the studies with multiple leading hospitals in Korea and the US for Lunit’s chest x-ray and mammography solutions; publication of the results are targeted for late 2018.” FDA approval for Lunit’s chest x-ray and mammography solutions are expected to be achieved by end of 2018.
Other than the chest x-ray solution, Lunit’s mammography solution to detect suspicious breast cancer lesions is in its final stages of development. Lunit INSIGHT for Mammography is expected to be publically released by the first quarter of 2018. Lunit is also doing research in developing solutions for digital breast tomosynthesis, chest CT, and coronary CT angiography.
Founded in 2013, Lunit develops advanced medical image analytics and novel imaging biomarkers via cutting-edge deep learning technology, in order to empower healthcare practitioners to make more accurate, consistent, and efficient clinical decisions. Lunit was chosen as Top AI startups in healthcare industry by CB Insights in 2017 and also was listed as “Top 5 AI startups for social impact” by Nvidia. Lunit is based in Seoul, South Korea.