illustration of DNA strand and abstract shapes on a computer screen on a green gradient background

Medical, health, and genomics

Digital pathology helps decode tumor microenvironments for precision immunotherapy. GigaPath is a novel vision transformer that can scale to gigapixel whole-slide images by adapting dilated attention for digital pathology. In joint work with Providence and UW, we’re sharing Prov-GigaPath, the first whole-slide pathology foundation model pretrained on large-scale real-world data, for advancing clinical research and discovery.

GigaPath: Whole-Slide Foundation Model for Digital Pathology

Research Forum Ep2 | Panel | Transforming the Natural Sciences with AI

Research Forum 2 | Panel Discussion: Transforming the Natural Sciences with AI

white icons of first aid kit, DNA strand, laptop monitor with overlapping eye, and microscope on a blue and green gradient background

Scaling early detection of esophageal cancer with AI

female doctor / nurse reviewing a tablet

Microsoft Health Futures

Current selections

Sort by: Most recent

Clear selections

Search within these results

Content Types

Published Date

Video

Unlocking IoT Data for Research in Healthcare

November 4, 2020 | Dustin Burson, Nate Malubay

Discuss the challenges IoT data presents in Healthcare and how we (Health Cloud & Data) have addressed them. We will also walk through an end to end example using common, off the shelf personal health…

32:56

Publication

Interpretation of morphogen gradients by a synthetic bistable circuit

Paul Grant, Gregory Szep, Om Patange, Jacob Halatek, Valerie Coppard, Attila Csikasz-Nagy, Jim Haseloff, James C. W. Locke, Neil Dalchau, Andrew Phillips

Nature Communications | November 2020, Vol 11(5545)

Project Project

Publication

Spatio-Temporal Attention and Magnification for Classification of Parkinson’s Disease from Videos Collected via the Internet

Mohammad Rafayet Ali, Javier Hernandez, E. Ray Dorsey, Ehsan Hoque, Daniel McDuff

International Conference on Automatic Face and Gesture Recognition | November 2020

Video

Distinct Population of Sudden Unexpected Infant Death Based on Age

October 30, 2020 | Juan Lavista Ferres, Tatiana Anderson, Richard Johnston, Jan-Marino Ramirez, Edwin Mitchell

Distinct population of sudden unexpected infant death based on age

02:39

Video

Using Internet search terms to forecast opioid-related deaths in Connecticut

October 29, 2020 | Sumit Mukherjee

02:17

Publication

Sense and Accessibility: Understanding People with Physical Disabilities’ Experiences with Sensing Systems

Shaun Kane, Anhong Guo, Meredith Ringel Morris

ASSETS 2020 | October 2020

Best Paper Nominee

Project

Publication

Assured Autonomy: Path Toward Living With Autonomous Systems We Can Trust

Ufuk Topcu, Nadya Bliss, Nancy Cooke, Missy L. Cummings, Ashley J. Llorens, Howard E. Shrobe, Lenore Zuck

October 2020

A Computing Community Consortium (CCC) workshop report, 28 pages.

Publication

Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars

Daniel McDuff, Javier Hernandez, Erroll Wood, Xin Liu, Tadas Baltrusaitis

October 2020

Project

Publication

HLA tapasin independence: broader peptide repertoire and HIV control.

Arman A. Bashirova, Mathias Viard, Vivek Naranbhai, Alba Grifoni, Wilfredo Garcia-Beltran, Marjan Akdag, Yuko Yuki, Xiaojiang Gao, Colm O’hUigin, Malini Raghavan, Steven Wolinsky, Jay H. Bream, Priya Duggal, Jeremy Martinson, Nelson L. Michael, Gregory D. Kirk, Susan P. Buchbinder, David Haas, James J. Goedert, Steven G. Deeks, Jacques Fellay, Bruce Walker, Philip Goulder, Peter Cresswell, Tim Elliott, Alessandro Sette, Jonathan M. Carlson, Mary Carrington

Proceedings of the National Academy of Sciences of the United States of America | October 2020, Vol 117(45): pp. 28232-28238

Project

Video

Domain-specific language model pretraining for biomedical natural language processing

October 15, 2020 | Hoifung Poon, Jianfeng Gao

Pretraining large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. However, most pretraining efforts focus on general-domain corpora, such as in newswire and web text.…

01:08:49

Medical, health, and genomics

Highlights