Graph-Guided Deep Embedding Clustering for Brain Atlases
Summary of the linked study; findings refer to that study’s own comparisons.
This fMRI Atlas page is a curated research summary, not the original study. The question, method, evidence and finding above summarize the authors’ report; results have not been independently reproduced here. See the original paper for methods, authorship and full results.
Evidence boundary: Atlas quality and downstream utility are reported for the evaluated cohorts and baselines; clinical use is not established by this directory entry.
Page reviewed: .
DCA constructs brain atlases at voxel resolution, using fMRI features to tailor parcels to individual subjects. A pretrained autoencoder supplies the embeddings, while a spatial graph guides clustering so that each parcel stays connected. Users can choose the number of parcels and the brain region to partition. The work also introduces AtlaScore, a benchmark for comparing atlas quality and downstream utility.
Summary of the original paper, revised September 20, 2025 (v2).
Masked fMRI reconstruction pretrains a Swin-UNETR encoder. Its voxel embeddings define soft cluster assignments and edge weights on a local spatial graph. Spectral clustering supplies targets that refine the assignments and learnable centroids.
@inproceedings{wang2025dca,
title={DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases},
author={Wang, Mo and Peng, Kaining and Tang, Jingsheng and Wen, Hongkai and Liu, Quanying},
year={2025},
booktitle={Advances in Neural Information Processing Systems},
volume={38},
doi={10.52202/085713-3450},
url={https://papers.nips.cc/paper_files/paper/2025/hash/954729c2c57c32cab97c4f868dbb4d3e-Abstract-Conference.html}
}