Topic: Deep Learning and Big Data Exploration for Preventive and Precision Medicine in Radiology
Speaker: Dr. Le Lu
Date: August 27, 15:00-16:00 pm
Venue: Room 416, Yifu Science Museum, Beihang University
Abstract: Recent progresses have been evident on employing deep learning principles upon large quantities (e.g., at hospital scale) of clinical imaging and text databases. However, in modern academic hospitals, there are tremendous amounts of unstructured patient data scattered among different clinical databases (PACS, BTRIS, RIS, CRIS, etc.), which mostly remain non-indexable, non-searchable to a semantic degree and are not useful means yet to tackle the quantitative precision healthcare challenge at scale. In this talk, I will review some of our recent research work in two aspects: 1) a general view on the research studies and insights for three key problems to solve: detection (computer-aided diagnosis/detection), semantic and anatomical segmentation (for precision quantitative imaging), and “big data, weak label” robust deep learning paradigms; 2) organizing and exploiting a large quantity of clinically significant image findings by learning a deep feature representation, and building deep semantic hierarchical (ontology-preserving) lesion similarity embedding over more than 10 thousand patient studies, to permit personalized precision medicine in radiology.
Biography of the Speaker:
Dr. Le Lu is the executive director of Bethesda Research Lab of PAII Inc., the US research arm by one of the world's largest insurance companies. He founded the deep learning for medical imaging and clinical informatics group at NVIDIA in 2017 and was a senior research manager until June 2018. Before that, he was a staff scientist at National Institutes of Health Clinical Center, Bethesda, Maryland during 2013-2017. He solved on various core R&D problems with critical technical contributions for Siemens colonic polyp and lung nodule CADx systems, vessel, and bone imaging at Siemens Corporate Research and Siemens Healthcare from 2006 to 2013 where his last post was a senior staff scientist. He has authored or co-authored 140 peer-reviewed papers, invented 26 granted and pending US/WO/PCT patents and 37 inventions. He helped his trainees win two research trainee awards at RSNA 2016/2018, the young scientist "runner-up" award at MICCAI 2017 and the young researcher "test of time" publication award at MICCAI 2018, NSF/NDSEG/NSERC fellowships. During his career at NIH, He made instrumental contributions on the public releases of several large-scale radiology datasets, including NIH-ChestXray14 and NIH-DeepLesion databases. He also edited a book on“Deep Learning and Convolutional Neural Networks for Medical Image Computing”by Springer in 2017. He was mentored by Harry Shum, Kentaro Toyama and Zhengyou Zhang at Microsoft Research, and received his Ph.D. in computer science from Johns Hopkins University in 2007, advised by Gregory Hager. He won the NIH Mentor of the Year award in 2015 and NIH Clinical Center Director's award for "research excellence and significant patient care impacts" in 2017. He serves the Area chair for AAAI 2020, WACV 2020, CVPR 2020, 2019, 2017, ICIP 2017; MICCAI 2018, 2016, 2015, Demo chair of CVPR 2017; Industrial Track Chair for IEEE ICHI 2019; and won two outstanding reviewer awards at CVPR 2018, BMVC 2017.
School of Biological Science and Medical Engineering
