no code implementations • 29 Nov 2022 • Zafar Iqbal, Usman Mahmood, Zening Fu, Sergey Plis
In this paper, we demonstrate that a model trained on the time direction of functional neuro-imaging data could help in any downstream task, for example, classifying diseases from healthy controls in fMRI data.
no code implementations • 22 May 2022 • Usman Mahmood, Daniel Pimentel-Alarcón
This paper introduces {\em fusion subspace clustering}, a novel method to learn low-dimensional structures that approximate large scale yet highly incomplete data.
no code implementations • 4 Feb 2022 • Usman Mahmood, Zening Fu, Vince Calhoun, Sergey Plis
To bridge this gap, we developed dynamic effective connectivity estimation via neural network training (DECENNT), a novel model to learn an interpretable directed and dynamic graph induced by the downstream classification/prediction task.
1 code implementation • 7 Dec 2021 • Usman Mahmood, Zening Fu, Vince Calhoun, Sergey Plis
Functional connectivity (FC) studies have demonstrated the overarching value of studying the brain and its disorders through the undirected weighted graph of fMRI correlation matrix.
no code implementations • 1 Nov 2021 • Usman Mahmood, Zening Fu, Vince Calhoun, Sergey Plis
The supervised training of the model as a classifier between patients and controls results in a model that generates directed connectivity graphs and highlights the components of the time-series that are predictive for each subject.
no code implementations • 1 Nov 2021 • Usman Mahmood, Zening Fu, Vince Calhoun, Sergey Plis
Since almost every DL model is an ensemble of multiple networks, we take our high-level embeddings from two different networks of a model --a convolutional and a graph network--.
no code implementations • ICLR Workshop GTRL 2021 • Usman Mahmood, Zening Fu, Vince Calhoun, Sergey Plis
Functional connectivity (FC) studies have demonstrated the benefits of investigating the brain and its disorders through the undirected weighted graph of fMRI correlation matrix.
no code implementations • 4 Mar 2021 • Usman Mahmood, Robik Shrestha, David D. B. Bates, Lorenzo Mannelli, Giuseppe Corrias, Yusuf Erdi, Christopher Kanan
Artificial intelligence (AI) has been successful at solving numerous problems in machine perception.
1 code implementation • 29 Jul 2020 • Usman Mahmood, Md Mahfuzur Rahman, Alex Fedorov, Noah Lewis, Zening Fu, Vince D. Calhoun, Sergey M. Plis
In this paper we present a novel self supervised training schema which reinforces whole sequence mutual information local to context (whole MILC).
no code implementations • 16 Nov 2019 • Usman Mahmood, Md Mahfuzur Rahman, Alex Fedorov, Zening Fu, Sergey Plis
In this paper, we demonstrate a self-supervised pre-training method that enables us to pre-train directly on fMRI dynamics of healthy control subjects and transfer the learning to much smaller datasets of schizophrenia.
no code implementations • 2 Aug 2018 • Daniel L. Pimentel-Alarcón, Usman Mahmood
Subspace clustering achieves this through a union of linear subspaces.