Mapping the Brain's "Wiring": Unsupervised Learning on High-Dimensional fMRI Data to get the Brain networks

#brain #functional-neuroimaging #machine-learning #k-means #unsupervised-learning
Share

In the world of functional Neuroimaging, the focus has historically been on "Gray Matter" (the brain's processors), often ignoring the "White Matter" (the communication cables). This talk introduces WhiFuN, a pipeline designed to extract meaningful signal from these under-explored regions using unsupervised machine learning. We will start by framing Resting-State fMRI as a massive time-series dataset, where each 3D pixel (voxel) in the brain contains a temporal signal of brain activity (movie of the 3D Brain). By calculating Functional Connectivity, essentially the Pearson correlation between these signals, we can treat the brain as a complex graph. The core of the talk will detail how we use K-means clustering on voxel-wise connectivity matrices to identify latent brain networks. We will dive into the engineering challenges of this approach, specifically how to decide the value of K. Finally, we will look at the results: how these data-driven networks allow us to identify group differences and behavioral associations, effectively turning raw, noisy 4D imagery into a structured feature set for clinical analysis.


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • 2 Civic Center Drive
  • East Brunswick, New Jersey
  • United States 08816
  • Room Number: Meeting Rooms 2,3
  • Contact Event Host
  • Starts 24 May 2026 04:00 AM UTC
  • Ends 15 August 2026 04:00 AM UTC
  • No Admission Charge

  Speakers

Pratik Jain

Topic:

Mapping the Brain's "Wiring": Unsupervised Learning on High-Dimensional fMRI Data to get the Brain networks

Biography:

Pratik Jain, Ph.D. Candidate | Developer of WhiFuN | Science Educator
Pratik Jain is a doctoral researcher at NJIT and Rutgers, specializing in next-generation functional MRI (fMRI) methodologies. His work shifts the focus of functional neuroimaging toward white matter, exploring its critical role in distributed neural communication. He is the creator of WhiFuN, an open-source pipeline that empowers researchers to conduct rigorous group-level analysis of white-matter functional networks in the brain.
Pratik’s expertise bridges computational neuroscience and machine learning; his recent projects include identifying subjects via functional "fingerprinting" and identifying the best brain atlases for diagnosing schizophrenia. With a background in Electrical Engineering (M.S., Indian Institute of Technology Mandi), he brings a signal-processing lens to large-scale neuroimaging. A passionate science communicator, Pratik shares his expertise in functional neuroimaging, MATLAB, image processing, and Machine learning with a global audience via his YouTube channel (https://www.youtube.com/@pratikian).




Agenda

Hybrid event, in-person or online:
2:30 Introduction
Technical Talks
Question and Answer
Networking
4:30 Conclusion