Artificial Intelligence

Clinicians routinely acquire data from numerous sources for disease characterization, including imaging, pathology, genomics and electrophysiology. While “big data” potentially harbors cues on disease behavior and patient outcome, the paucity of analytic and biomedical informatics tools to harness and unlock quantitative, disease-related insight from vast sets of biomedical data results in these cohorts remaining under-exploited and uninterrogated. There is a critical need to quantify information and determine relationships across multiple scales, modalities and functionalities – from gene and protein expression to spectroscopy, digital pathology and radiographic imaging.

The areas of artificial intelligence (A.I.) and health informatics are a burgeoning strategic focus within the Department of Biomedical Engineering. Faculty and students are developing and applying a variety of analytic tools to imaging, digital pathology, genomics, proteomics and electrophysiological data to help physicians solve key clinical and translational problems. This includes developing, evaluating and applying novel quantitative image analysis, computer vision, signal processing, segmentation, multi-modal co-registration tools, pattern recognition and machine learning tools for disease diagnosis, prognosis and theragnosis in the context of oncological and non-oncological conditions. 

The cross-cutting, interdisciplinary field of A.I. and health informatics identifies, explores and implements effective uses of data and information. Key innovations here include designing unique A.I. tools that can capture biologically relevant and clinically intuitive measurements via radiomics, pathomics and radiogenomics, as well as other multimodal data analytic techniques. This allows us to gain value and knowledge from routinely acquired clinical big data, including deeper insights into disease processes and mechanisms, and thus empower clinicians and patients in decision-making and pave the way toward precision medicine.

Affiliated Labs and Centers

Faculty