Welcome to the MGHPCC Virtual Booth

Boston University

AI for Dementia Assessment

Vijaya Kolachalama is an expert in computational biomedicine. His group makes extensive use of BU’s Shared Computing Cluster housed at the MGHPCC in research applying machine learning approaches to dementia assessment.

The Kolachalama Group seeks to create “methods to fit the science and not make science fit the methods.”

Specifically, they are interested in the following clinically relevant questions:
1. Neurodegeneration—How can we develop software frameworks that can assist dementia screening in various real-world settings?
2. Digital pathology—How can we build clinical-grade software tools to complement the clinical workflow?

The team is also interested in the following computationally relevant frameworks:
1. Domain generalization—Development of deep neural networks that can generalize well across multiple data cohorts.
2. Representation learning—Construction of efficient neural models on high-resolution data to process local and contextual information.

In this video members of the Kolachalama Group introduce their work using machine learning to diagnose Alzheimer’s.

https://vkola-lab.github.io/
Vijaya Kolachalama, Phd
Associate Professor, Computational Biomedicine, School of Medicine, Boston University

Consortium

Featured projects

SC23 Project
Computing Social Capital
SC23 Project
Neural Networks & Earthquakes
SC23 Project
NeuraChip
SC23 Project
The Rhode Island Coastal Hazards Analysis, Modeling, and Prediction System
SC23 Project
Energy Transport and Ultrafast Spectroscopy Lab
SC23 Project
URI Center for Computational Research
SC23 Project
UMass – URI Unity Cluster
SC23 Project
Computational Molecular Ecology
SC23 Project
Cyber-Physical Communication Network Security
SC23 Project
Remote Sensing of Earth Systems
SC23 Project
Genome Forecasting
SC23 Project
SC23 Student Cluster Competition
SC23 Project
OSN 1 – Accessing Storage
SC23 Project
Campus Champions
SC23 Project
Harvard FASRC
SC23 Project
SEQer – Sequence Evaluation in Realtime
SC23 Project
ACAS X: A Family of Next-Generation Collision Avoidance Systems
SC23 Project
A Future of Unmanned Aerial Vehicles
Knowledge Base
Climate Health and Air Pollution in India
NASA Arctic-Boreal Vulnerability Experiment (ABoVE)
The Center for Scientific Computing and Data Science Research (CSCDR)
AI Computing and the AI Jumpstart Cluster
AI for Dementia Assessment
Measuring Nationwide Park Access
Quantifying Risk, Resilience, and Uncertainty with Machine Learning and HPC
Refugee Migration and Return on Social Media
Modeling Molecular Dynamics for Drug Delivery
Expanding Computing Education Pathways (ECEP) Alliance
Machine Learning and Wastewater
Candidate Driver Analysis of Multi-omics Data (CaDrA)
OpenCilk
Wearable Health Technology
Deepfake Caricatures
Invisible Tags
ElectroVoxels: Modular Self-reconfigurable Robots
Color Changing Objects
The Mass Open Cloud Alliance (MOC Alliance)
Open Cloud Testbed (OCT)
Ecosystem for Research Networking (ERN)
SC23 Project
OSN 2 – Deploying Storage
ACCESS Support (MATCH)
ConnectCI
Ask.CI
The UMass-URI Gravity Research Consortium (U2GRC)
Billion Object Platform
Predicting Kinetic Solvent Effects
Predicting Reaction Barrier Heights
Aviation Weather Decision Support Laboratory Tour
Sensorimotor Technology Realization in Immersive Virtual Environments (STRIVE)
Conclave Cloud Dataverse: Protected Computing in the Datacenter
Large-Scale Brain Mapping
AI for HPC Analytics
Offshore Precipitation Capability (OPC) System
The Forensic Video Exploitation and Analysis (FOVEA) Tool Suite
Next Generation Aircraft Collision Avoidance System ACAS X
Learning-Task Informed Abstractions
Research Software Engineering
LLSC Articles and Publications
Software for Unreliable Quantum Computers
FlyNet
Simulating Large Biomolecular Assemblies
Lichtman Lab – Center for Brain Science
Black Hole Initiative
Lincoln Laboratory Supercomputing Center (LLSC)
linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram