What question did this study set out to answer?

This study aims to identify neuroimaging biomarkers and assess the impact of preprocessing techniques on fMRI data for diagnosing mental disorders.

Neuroimaging Biomarkers for Brain Disorder Diagnosis Using Advanced Learning Techniques

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates neuroimaging biomarker accuracy in brain disorders, suggesting optimal preprocessing strategies for diagnosis.

This study aims to identify neuroimaging biomarkers and assess the impact of preprocessing techniques on fMRI data for diagnosing mental disorders.
Used resting-state fMRI data for analysis of functional connectivity in Bipolar Disorder and Alzheimer’s Disease.
Applied two preprocessing pipelines: one combining Statistical Parametric Mapping with the CONN toolbox and another using the MELODIC software.
Employed Support Vector Machines, Random Forests, and the Deep Learning model AlexNet for classification tasks.
Connbox-SPM preprocessing with AlexNet achieves 78.2% accuracy in Bipolar Disorder.
Connbox-SPM preprocessing with AlexNet reaches 82.4% accuracy in Alzheimer’s Disease.
Preprocessing choices significantly influence classification performance and functional connectivity representation.

Ion et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates neuroimaging biomarker accuracy in brain disorders, suggesting optimal preprocessing strategies for diagnosis.

This study aims to identify neuroimaging biomarkers and assess the impact of preprocessing techniques on fMRI data for diagnosing mental disorders.
Used resting-state fMRI data for analysis of functional connectivity in Bipolar Disorder and Alzheimer’s Disease.
Applied two preprocessing pipelines: one combining Statistical Parametric Mapping with the CONN toolbox and another using the MELODIC software.
Employed Support Vector Machines, Random Forests, and the Deep Learning model AlexNet for classification tasks.
Connbox-SPM preprocessing with AlexNet achieves 78.2% accuracy in Bipolar Disorder.
Connbox-SPM preprocessing with AlexNet reaches 82.4% accuracy in Alzheimer’s Disease.
Preprocessing choices significantly influence classification performance and functional connectivity representation.

Ion et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark