Integrative Imaging & Molecular Diagnostics Lab
Our lab is focused on the development and application of novel machine learning and deep learning approaches for medical imaging analysis and precision oncology. This can lead to discovery of imaging-based biomarkers for several clinical applications including cancer detection and diagnosis, treatment response and prognosis prediction, which have the potential to transform cancer care.
Our work spans across multiple imaging domains and modalities including radiology as well as histopathology image data. These data sets are linked with clinical outcomes to address a specific unmet clinical need. Further, we integrate imaging with matched genomic/molecular data to gain more insight into cancer biology.
Artificial intelligence (AI) including machine learning and deep learning plays a critical role in these endeavors. We are developing new methods to make these sophisticated models more robust, reproducible, and interpretable, all of which are key elements of successful AI applications in medicine.
Our research is multidisciplinary by nature. We work closely with a team of expert clinicians including oncologists, surgeons, radiologists, and pathologists at Stanford and beyond. Our goal is to translate new technology and imaging biomarkers to clinical practice, which can guide personalized management and therapy selection, ultimately improving outcomes for cancer patients.
Our lab has been supported by multiple NIH R01 grants from the National Cancer Institute (R01 CA193730, R01 CA222512, R01 CA233578) and the National Institute of Dental and Craniofacial Research (R01 DE030894). Additionally, our work is supported by the Stanford Institute for Human-Centered Artificial Intelligence (HAI). My earlier research was supported by an NIH Pathway to Independence Award (K99/R00 CA166186) from 2012 to 2017.