FNNDSC Weekly Newsletter - Week 67
Hope everyone had a great Labor Day Weekend!
To all observing Rosh Hashanah, Happy New Year!
Upcoming Events
September 8th 10:00 AM - 11:00 AM: FNNDSC Lecture Series | Ina Fiterau, PhD, Assistant Professor
September 7th 8:40 AM -10:55 AM: Dr. Ellen Grant, TRABIT Keynote and Round Table Discussion
Please register here: TRABIT conference (trabit-network.github.io)
Applications due September 14th: Thrasher Research Fund- Diversity in Early Career Awards
Please visit their website at https://www.thrasherresearch.org/diversity to learn more about their commitment to diversity. More information about their Early Career Award Program can be found at https://www.thrasherresearch.org/early-career-award?lang=eng.
Various Dates: Newborn Brain Society - Fetal Neurology Webinar Series Helpful Links â–´ Research Computing Data Management â–´ Research Computing Self Portal â–´ Research Announcements & News â–´ Office of Sponsored Programs Updates â–´ Funding Opportunities and Links â–´ Staff Resources - Covid-19 â–´ Covid Vaccine FAQs
Publications Genomic frontiers in congenital heart disease.
Morton SU, Quiat D, Seidman JG, Seidman CE. Nat Rev Cardiol. PMID: 34272501
Yetisir F, Abaci Turk E, Guerin B, Gagoski BA, Grant PE, Adalsteinsson E, Wald LL. Magn Reson Med. PMID: 34240759
Ricci L, Tamilia E, Alhilani M, Alter A, Scott Perry Μ, Madsen JR, Peters JM, Pearl PL, Papadelis C. Clin Neurophysiol. PMID: 34034087
Larsen RJ, Gagoski B, Morton SU, Ou Y, Vyas R, Litt J, Grant PE, Sutton BP. NMR Biomed. PMID: 33913194
Iandolo G, Chourasia N, Ntolkeras G, Madsen JR, Papadelis C, Grant E, Pearl PL, Taffoni F, Tamilia E. Diagnostics (Basel). PMID: 34359317
Vasung L, Zhao C, Barkovich M, Rollins CK, Zhang J, Lepage C, Corcoran T, Velasco-Annis C, Yun HJ, Im K, Warfield SK, Evans AC, Huang H, Gholipour A, Grant PE. Cereb Cortex. PMID: 33836056
FNNDSC Lecture Series This Week
Date/Time: Wednesday, September 8th at 10:00 AM
Presenter: Ina Fiterau, PhD
Title: Disease Trajectory Modeling from Heterogeneous, Multimodal Data
Abstract: Modeling multimodal data is particularly important in healthcare applications. Chronic conditions such as osteoarthritis, congenital heart disease and Alzheimer's disease affect a significant segment of the population. According to the CDC, almost 45% of all Americans suffer from at least one chronic condition. Longitudinal studies that monitor subjects over extended periods of time help determine the relationships between risk factors and disease evolution, key to quantifying the effectiveness of treatment and palliative care. The studies comprise multimodal data such as demographics, time series, medical images genetic information. All are collected across multiple institutions, multiple patient populations and multiple visits. Essentially, the collection process induces heterogeneity at all levels: there is high irregularly, inter-subject variability and potentially changing collection protocols. Reliable disease trajectory models, constructed through retrospective statistical analysis of this multimodal longitudinal data, are necessary to inform patients and facilitate clinical decisions.
We address the methodological gap by tightly integrating multimodal data and leveraging the different sources of information, including domain expertise, to extract salient features. Our hybrid models optimize multi-component objectives, specialized to the task and for the available data. Moreover, they include hybrid layers, built with `neurons' that are designed to cope with multiple inputs of distinct types, such as attributes encoded as discrete features provided together with their associated images. We also use various mechanisms to conditionally route samples through the neural networks depending on their cross modal characteristics. We use generative models to enable weak supervision through domain-specific heuristics. We also introduce structured sparsity and manifold learning in normalizing flows, a class of deep generative models that achieve both feature learning and tractable marginal likelihood estimation. This allows us to e efficiently construct representations of images that adhere to specific patterns, such as medical images of different organs. I'll demonstrate the performance of our models in attaining state of the art results on tasks such as Alzheimer's disease forecasting, detecting heart conditions and in-hospital mortality prediction.
Biography:
Ina Fiterau is an Assistant Professor in the College of Information and Computer Sciences at UMass Amherst. She has completed a PhD in Machine Learning from Carnegie Mellon University (Fall 2015), and a Postdoc at Stanford University (Fall 2018). Ina is currently expanding her research on interpretable models, in part by applying deep learning to obtain salient representations from biomedical unstructured data, including time series, text and images. She is the recipient of the Marr Prize for Best Paper at ICCV 2015 and of Star Research Award at the Annual Congress of the Society of Critical Care Medicine 2016. Madalina has co-organized the NeurIPS workshop on Machine Learning in Healthcare.
Zoom meeting information:
Join from your computer or mobile device: https://bostonchildrens.zoom.us/j/97624611409?pwd=eXkvQWNCQW9ORW16WWEvMmRRRlkwQT09
Password: 603128
Or dial in from your telephone: Internally: x28882 Externally: 646-558-8656 (Primary) 408-638-0968 (If you are unable to dial into the primary number)
Or iPhone one-tap: +16465588656,,97624611409# or +14086380968,,97624611409#
EWS link: https://zoom.us/wc/97624611409/join
Meeting ID: 976 2461 1409
HAVE SOMETHING TO SHARE?
If you have something that you would like to see featured in the next newsletter, please contact Winona Bruce-Baiden at: winona.bruce-baiden@childrens.harvard.edu
Comments