Deep Labeling of fMRI Brain Networks Using Cloud Based Processing

TL;DR

This paper presents a cloud-based deep learning pipeline for automated labeling of resting state fMRI brain networks, improving efficiency and reproducibility in clinical neuroimaging analysis.

Contribution

It introduces an end-to-end cloud workflow integrating FSL and deep neural networks for RSN classification, demonstrating high accuracy across multiple architectures.

Findings

Achieved >98% accuracy with three neural network architectures

Demonstrated feasibility of cloud-based fMRI analysis pipeline

Compared performance of MLP, 2D CNN, and 3D CNN models

Abstract

Resting state fMRI is an imaging modality which reveals brain activity localization through signal changes, in what is known as Resting State Networks (RSNs). This technique is gaining popularity in neurosurgical pre-planning to visualize the functional regions and assess regional activity. Labeling of rs-fMRI networks require subject-matter expertise and is time consuming, creating a need for an automated classification algorithm. While the impact of AI in medical diagnosis has shown great progress; deploying and maintaining these in a clinical setting is an unmet need. We propose an end-to-end reproducible pipeline which incorporates image processing of rs-fMRI in a cloud-based workflow while using deep learning to automate the classification of RSNs. We have architected a reproducible Azure Machine Learning cloud-based medical imaging concept pipeline for fMRI analysis integrating the popular FMRIB Software Library (FSL) toolkit. To demonstrate a clinical application using a large dataset, we compare three neural network architectures for classification of deeper RSNs derived from processed rs-fMRI. The three algorithms are: an MLP, a 2D projection-based CNN, and a fully 3D CNN classification networks. Each of the net-works was trained on the rs-fMRI back-projected independent components giving >98% accuracy for each classification method.