Brain multigraph prediction using topology-aware adversarial graph neural network

Bessadok A., Mahjoub M. A., Rekık I.

MEDICAL IMAGE ANALYSIS, cilt.72, 2021 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 72
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1016/j.media.2021.102090
  • Dergi Adı: MEDICAL IMAGE ANALYSIS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Biotechnology Research Abstracts, Compendex, EMBASE, INSPEC, MEDLINE
  • Anahtar Kelimeler: Brain multigraph prediction, Generative adversarial learning, Geometric deep learning, Adversarial autoencoders
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

Brain graphs (i.e, connectomes) constructed from medical scans such as magnetic resonance imaging (MRI) have become increasingly important tools to characterize the abnormal changes in the human brain. Due to the high acquisition cost and processing time of multimodal MRI, existing deep learning frameworks based on Generative Adversarial Network (GAN) focused on predicting the missing multi-modal medical images from a few existing modalities. While brain graphs help better understand how a particular disorder can change the connectional facets of the brain, synthesizing a target brain multigraph (i.e, multiple brain graphs) from a single source brain graph is strikingly lacking. Additionally, existing graph generation works mainly learn one model for each target domain which limits their scalability in jointly predicting multiple target domains. Besides, while they consider the global topological scale of a graph (i.e., graph connectivity structure), they overlook the local topology at the node scale (e.g., how central a node is in the graph). To address these limitations, we introduce topology-aware graph GAN architecture (topoGAN), which jointly predicts multiple brain graphs from a single brain graph while preserving the topological structure of each target graph. Its three key innovations are: (i) designing a novel graph adversarial auto-encoder for predicting multiple brain graphs from a single one, (ii) clus-tering the encoded source graphs in order to handle the mode collapse issue of GAN and proposing a cluster-specific decoder, (iii) introducing a topological loss to force the prediction of topologically sound tar-get brain graphs. The experimental results using five target domains demonstrated the outperformance of our method in brain multigraph prediction from a single graph in comparison with baseline approaches. (c) 2021 Elsevier B.V. All rights reserved.