We are pleased to announce that the QIAI Lab has been awarded a second grant from the NIH, a U01 under NCI’s Informatics Technologies for Cancer Research and Management (ITCR) program. The grant entitled “Distributed computation of predictive models for precision medicine in cancer” will focus on developing methods and tools for training AI models relevant to cancer through federated computational methods that do not require any data sharing and that will propel multi-institutional collaborations for creating more robust AI models. The ITRC program is a very large network of centers developing enabling data science technologies to advance cancer discovery, and the QIAI Lab's involvement in this network will permit it to have a voice in developing emerging standardized approaches to data analysis in cancer problems as well as to deliver enabling technologies to the community that will accelerate creation of AI applications.
We are please to announce that the QIAI Lab is part of a team that was awarded a U24 grant under NCI’s Oncology Co-Clinical Imaging Research Resources to Encourage Consensus on Quantitative Imaging Methods and Precision Medicine, which is a new network of sites developing innovative methods to enable co-clinical (animal/human) trials. The grant is entitled “Integrating omics and quantitative imaging data in co-clinical trials to predict treatment response in triple negative breast cancer.” The ePAD technology (http://epad.stanford.edu) developed by the QIAI Lab is central to this grant by bringing quantitative image analysis methods to small animal imaging and unifying quantitative assessment of cancer on images in both animal and human studies to catalyze research in the co-clinical trials paradigm.
We are pleased to announce that ePAD project (http://epad.stanford.edu) of the QIAI Lab, "ePAD: A platform to enable machine learning and AI application development in medical imaging" (B-0906) has been selected to receive the Best Scientific Paper Presentation Award at the 2019 European Congress of Radiology in Imaging Informatics, https://www.myesr.org/congress
We have recently developed methods for distributed computation of deep learning models in JAMIA. This may break the barrier to leveraging multi-institutional data and enable creating more robust deep learning models. Check it out
On May 10, 2017, Dr. Assaf Hoogi, a Postdoctoral Scholar in the Dr. Rubin's laboratory received the prestigeous Larry Clarke QIN Young Investigator Travel Award for is outstanding and innovative work in adaptive methods for image segmentation and career vision for advancing quantitative imaging.
A scientific paper by Zeshan Hussain (Graduate Student in Dr. Rubin's laboratory) and Dr. Francisco Gimenez (recently graduated from Dr. Rubin's laboratory) was selected for a spotlight talk at NIPS 2016 (http://www.nipsml4hc.ws/), entitled, "Differential Data Augmentation Techniques for Medical Imaging Classification Tasks"