Learning Temporal Higher-order Patterns to Detect Anomalous Brain Activity

Ali Behrouz, Farnoosh Hashemi
Proceedings of the 3rd Machine Learning for Health Symposium, PMLR 225:39-51, 2023.

Abstract

Due to recent advances in machine learning on graphs, representing the connections of the human brain as a network has become one of the most pervasive analytical paradigms. However, most existing graph machine learning-based methods suffer from a subset of five critical limitations: They are (1) designed for simple pair-wise interactions while recent studies on the human brain show the existence of higher-order dependencies of brain regions, (2) designed to perform on pre-constructed networks from time-series data, which limits their generalizability, (3) designed for classifying brain networks, limiting their ability to reveal underlying patterns that might cause the symptoms of a disease or disorder, (4) designed for learning of static patterns, missing the dynamics of human brain activity, and (5) designed in supervised setting, relying their performance on the existence of labeled data. To address these limitations, we present , an end-to-end anomaly detection model that automatically learns the structure of the hypergraph representation of the brain from neuroimage data. uses a tetra-stage message-passing mechanism along with an attention mechanism that learns the importance of higher-order dependencies of brain regions. We further present a new adaptive hypergraph pooling to obtain brain-level representation, enabling to detect the neuroimage of people living with a specific disease or disorder. Our experiments on Parkinson{’}s Disease, Attention Deficit Hyperactivity Disorder, and Autism Spectrum Disorder show the efficiency and effectiveness of our approaches in detecting anomalous brain activity.

Cite this Paper


BibTeX
@InProceedings{pmlr-v225-behrouz23a, title = {Learning Temporal Higher-order Patterns to Detect Anomalous Brain Activity}, author = {Behrouz, Ali and Hashemi, Farnoosh}, booktitle = {Proceedings of the 3rd Machine Learning for Health Symposium}, pages = {39--51}, year = {2023}, editor = {Hegselmann, Stefan and Parziale, Antonio and Shanmugam, Divya and Tang, Shengpu and Asiedu, Mercy Nyamewaa and Chang, Serina and Hartvigsen, Tom and Singh, Harvineet}, volume = {225}, series = {Proceedings of Machine Learning Research}, month = {10 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v225/behrouz23a/behrouz23a.pdf}, url = {https://proceedings.mlr.press/v225/behrouz23a.html}, abstract = {Due to recent advances in machine learning on graphs, representing the connections of the human brain as a network has become one of the most pervasive analytical paradigms. However, most existing graph machine learning-based methods suffer from a subset of five critical limitations: They are (1) designed for simple pair-wise interactions while recent studies on the human brain show the existence of higher-order dependencies of brain regions, (2) designed to perform on pre-constructed networks from time-series data, which limits their generalizability, (3) designed for classifying brain networks, limiting their ability to reveal underlying patterns that might cause the symptoms of a disease or disorder, (4) designed for learning of static patterns, missing the dynamics of human brain activity, and (5) designed in supervised setting, relying their performance on the existence of labeled data. To address these limitations, we present , an end-to-end anomaly detection model that automatically learns the structure of the hypergraph representation of the brain from neuroimage data. uses a tetra-stage message-passing mechanism along with an attention mechanism that learns the importance of higher-order dependencies of brain regions. We further present a new adaptive hypergraph pooling to obtain brain-level representation, enabling to detect the neuroimage of people living with a specific disease or disorder. Our experiments on Parkinson{’}s Disease, Attention Deficit Hyperactivity Disorder, and Autism Spectrum Disorder show the efficiency and effectiveness of our approaches in detecting anomalous brain activity.} }
Endnote
%0 Conference Paper %T Learning Temporal Higher-order Patterns to Detect Anomalous Brain Activity %A Ali Behrouz %A Farnoosh Hashemi %B Proceedings of the 3rd Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2023 %E Stefan Hegselmann %E Antonio Parziale %E Divya Shanmugam %E Shengpu Tang %E Mercy Nyamewaa Asiedu %E Serina Chang %E Tom Hartvigsen %E Harvineet Singh %F pmlr-v225-behrouz23a %I PMLR %P 39--51 %U https://proceedings.mlr.press/v225/behrouz23a.html %V 225 %X Due to recent advances in machine learning on graphs, representing the connections of the human brain as a network has become one of the most pervasive analytical paradigms. However, most existing graph machine learning-based methods suffer from a subset of five critical limitations: They are (1) designed for simple pair-wise interactions while recent studies on the human brain show the existence of higher-order dependencies of brain regions, (2) designed to perform on pre-constructed networks from time-series data, which limits their generalizability, (3) designed for classifying brain networks, limiting their ability to reveal underlying patterns that might cause the symptoms of a disease or disorder, (4) designed for learning of static patterns, missing the dynamics of human brain activity, and (5) designed in supervised setting, relying their performance on the existence of labeled data. To address these limitations, we present , an end-to-end anomaly detection model that automatically learns the structure of the hypergraph representation of the brain from neuroimage data. uses a tetra-stage message-passing mechanism along with an attention mechanism that learns the importance of higher-order dependencies of brain regions. We further present a new adaptive hypergraph pooling to obtain brain-level representation, enabling to detect the neuroimage of people living with a specific disease or disorder. Our experiments on Parkinson{’}s Disease, Attention Deficit Hyperactivity Disorder, and Autism Spectrum Disorder show the efficiency and effectiveness of our approaches in detecting anomalous brain activity.
APA
Behrouz, A. & Hashemi, F.. (2023). Learning Temporal Higher-order Patterns to Detect Anomalous Brain Activity. Proceedings of the 3rd Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 225:39-51 Available from https://proceedings.mlr.press/v225/behrouz23a.html.

Related Material