arXiv Machine Learning
MovieSTAGE: Scene, Transition, and Global Encoding for Movie-fMRI ADHD Classification
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 10
FedDOSE: Federated Learning Framework Decomposing Site Effects for Modeling Brain Dynamic Functional Connectivity
arXiv:2608. 07393v1 Announce Type: new Abstract: Functional Magnetic Resonance Imaging ( fMRI ) data are often pooled into collaborative multi-site consortia, as deep learning models for analyses require large datasets to generalize well.
arXiv AI
Sep 21
Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI
Rhamba is a region‑aware pretraining framework for resting‑state fMRI that combines anatomically guided masking with hybrid Attention‑Mamba architectures. The study pretrained models on the ABIDE dataset using three masking strategies (Any, Majority, Pure) and evaluated four architectural variants, finding that the Mamba‑Attention (MA) hybrid achieved the best average AUROC on downstream schizophrenia and ADHD classification tasks. Explainable AI via Integrated Gradients highlighted that performance depends on the interaction between masking strategy and architecture rather than a single dominant configuration.
arXiv Computer Vision
Sep 25
It's the Geometry, Not the Model: Effective Rank and Subspace Alignment in Functional Connectivity Classification
The study investigates how the geometry of resting‑state functional connectivity (FC) influences classification of brain phenotypes and cross‑site transfer, rather than focusing on model design. It finds that FC variation across subjects is concentrated in a small effective subspace, and that differences in subspace orientation across cohorts can limit transfer even when effective ranks are similar. By projecting onto leading components at the effective‑rank scale, most classification performance is retained, and the alignment of site‑specific subspaces predicts transfer performance. "whyItMatters":"The findings highlight that aligning effective subspaces across sites is crucial for improving generalization of FC‑based classifiers, offering a geometric diagnostic for cross‑site harmonization efforts."
arXiv Computer Vision
Sep 10
M2LG-DG: A Multi-modal Local-Global Domain Generalization Framework for Cross-site Major Depressive Disorder Classification
arXiv:2609.09186v1 Announce Type: new Abstract: Classification models based on resting-state functional magnetic resonance imaging (rs-fMRI) often show lower performance at imaging sites not included...
arXiv Machine Learning
Jul 21
RegionFM: Interpretable Region-Based Brain MRI Classification Using Foundation Model Embeddings
arXiv:2607. 16325v1 Announce Type: cross Abstract: Foundation models provide powerful representations for brain MRI analysis, but their predictions remain difficult to interpret in anatomically meaningful terms.
arXiv Machine Learning
Jul 9
STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning
arXiv:2607. 06629v1 Announce Type: new Abstract: Brain age -- the age inferred from a physiological recording -- is an emerging biomarker whose deviation from chronological age tracks neurological and psychiatric burden, and EEG is an attractive substrate for it because it is cheap, portable, and temporally rich.