Our mission is to create methods to fit the science and not make science fit the methods.

Specifically, we are interested in the following questions that have clinical relevance:

  1. Neurodegeneration – How can we develop software frameworks that can assist neurology practitioners in various real-world settings?
  2. Digital pathology – How can we build clinical-grade software tools to complement the pathologist workflow?

We are also interested in the following frameworks that have computational relevance:

  1. Multimodal learning – Efficient design of generalist AI models that can process multiple modalities of data.
  2. Representation learning – Construction of efficient neural models on high resolution data to process local and contextual information

Joining our laboratory

We form small teams comprising individuals with complementary expertise and work persistently to build comprehensive solutions.

Important: If you are interested in joining us, then we encourage you to contact an active lab member (click on Team) and talk about your interests.

Funding

We are grateful for funding from the American Heart Association, the National Institute on Aging, the National Heart, Lung, and Blood Institute, the National Cancer Institute, the Artificial Intelligence and Technology Collaboratories (AITC) for Aging Research program, and the National Institute of Diabetes and Digestive and Kidney Diseases. We also thank the Karen Toffler Charitable Trust, Johnson & Johnson Enterprise Innovation Inc., and Visterra Inc., for funding our work.

Teaching

– Machine learning (MS650)

– Guest lectures (BF831; HM817; FC713; EC500)

News

May 2024

New paper! Domain generalization for Alzheimer's disease assessment, published in Human Brain Mapping.

April 2024

New award! Lingyi Xu wins the 2024 Boston University Women's Guild Award.

April 2024

New paper! Graph attention-based fusion for digital pathology, published in IEEE Transactions on Medical Imaging.

April 2024

New paper! Graph perceiver network for digital pathology, published in the American Journal of Pathology.

March 2024

Lindsey Claus got matched to Vascular Surgery at the University of Pennsylvania.

March 2024

Divya Veerapaneni got matched to Neurology at the UT Southwestern Medical Center.

February 2024

New paper! Survival analysis on subchondral bone length for total knee replacement, published in Skeletal Radiology.

January 2024

New papers! The Journal of the American Heart Association's special issue on digital health showcases multiple papers from our team.

October 2023

New paper! Fusion of low-level voice descriptors for dementia, published in the Journal of Alzheimer's Disease.

... see all News