Researchers1 from the NYU School of Medicine made use of NYU High Performance Computing (HPC) resources and Google’s deep learning artificial intelligence algorithm to advance the understanding of lung cancer and mutations in tumors. Using Google’s Inception v3 (an open-source algorithm) and the HPC neural network, they were able to accurately differentiate between two different types of lung cancer, adenocarcinoma and squamous cell carcinoma. Under a microscope, the two types of cancer appear almost identical. The breakthrough achieved using AI and HPC resources substantially increases the accuracy of identifying these variations and thus improve the quality of treatment.
The research, originally published in Nature in September 2017, and its implications for the future of cancer and other types of medical research and treatment was covered extensively in a recent Wired article. NYU’s Research Technology group has committed to a major investment in high performance computing resources dedicated to artificial intelligence-powered research.
- Nicolas Coudray, Paolo Santiago Ocampo, Theodore Sakellaropoulos, Navneet Narula, Matija Snuderl, David Fenyö, Andre L. Moreira, Narges Razavian, and Aristotelis Tsirigos
- “Google AI Tool Identifies A Tumor’s Mutations From An Image” (Wired)
- Abstract: “Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning” (Nature)
- NYU IT High Performance Computing resources (NYU IT website)
- Navigating Research Technology at NYU (NYU website)