We bring people together to create new ways of seeing.
CAI2R creates technologies for better acquisition, reconstruction, and analysis of medical images.
Our innovations advance research in biomedicine and our best technologies become leading-edge tools in clinical radiology.
CAI2R (pronounced care) is a National Center for Biomedical Imaging and Bioengineering supported by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) and operated by NYU Langone Health.
A Unique Model for Academic Medical Research
Research and development in biomedical imaging are extraordinarily complex. We assemble translational research teams that meet the challenge.
CAI2R research leads the field in fast imaging, machine learning for image acquisition and reconstruction, ultraflexible biomorphic hardware, complementing MRI data with novel sensing strategies, mapping of tissue microstructure, and artificial intelligence methods for early detection of disease.
Our Center brings together basic scientists, engineers, clinical radiologists, physicians, computer scientists, and specialists from the medical imaging industry. We form innovative research partnerships with institutions in medicine, academia, and tech.
CAI2R innovations advance knowledge, diagnosis, and therapy of neurological conditions, musculoskeletal conditions, cardiovascular conditions, and cancer. Our research is focused on scientific and clinical applications of new biomedical imaging technologies.
A combination of radiologists and AI reduced overdiagnosis and more accurately identified breast cancer in ultrasound exams.
Florian Knoll, incoming chair of imaging at University of Erlangen–Nuremberg, talks about his background, not being greedy, and why he does what he does.
Scientists combine particle physics and neuroscience to visualize a key element of the nervous system.
A project by the Diffusion Study Group of the International Society for Magnetic Resonance in Medicine (ISMRM)
Compare machine learning performance across classifiers and datasets.
A convolutional neural network for anatomically-guided PET reconstruction.
A compact, stand-alone device for tracking and correcting patient motion in MRI exams.
Machine learning optimization of k-space sampling for accelerated MRI.
By the Numbers
years since founding