Integrated brain connectivity analysis with fMRI, DTI, and sMRI powered by interpretable graph neural networks

Medical Image Analysis, Год журнала: 2025, Номер 103, С. 103570 - 103570

Опубликована: Апрель 9, 2025

Язык: Английский

---

SPDGCN-KD: Knowledge Distillation-Based SPD Graph Convolutional Network for ADHD Diagnosis with Imbalanced fMRI Data

Опубликована: Янв. 10, 2025

Язык: Английский

---

Learnable Brain Connectivity Structures for Identifying Neurological Disorders

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Год журнала: 2024, Номер 32, С. 3084 - 3094

Опубликована: Янв. 1, 2024

Brain networks/graphs have been widely recognized as powerful and efficient tools for identifying neurological disorders. In recent years, various graph neural network models developed to automatically extract features from brain networks. However, a key limitation of these is that the inputs, namely networks/graphs, are constructed using predefined statistical metrics (e.g., Pearson correlation) not learnable. The lack learnability restricts flexibility approaches. While statistically-specific networks can be highly effective in recognizing certain diseases, their performance may exhibit robustness when applied other types To address this issue, we propose novel module called Structure Inference (termed BSI), which seamlessly integrated with multiple downstream tasks within unified framework, enabling end-to-end training. It flexible learn most beneficial underlying structures directly specific tasks. proposed method achieves classification accuracies 74.83% 79.18% on two publicly available datasets, respectively. This suggests an improvement at least 3% over best-performing existing methods both addition its excellent performance, interpretable, results generally consistent previous findings.

Язык: Английский

---

Assisted diagnosis of neuropsychiatric disorders based on functional connectivity: A survey on application and performance evaluation of graph neural network

Expert Systems with Applications, Год журнала: 2024, Номер 265, С. 125922 - 125922

Опубликована: Дек. 7, 2024

Язык: Английский

---

ORC-GNN: A novel open set recognition based on graph neural network for multi-class classification of psychiatric disorders

Information Fusion, Год журнала: 2024, Номер unknown, С. 102887 - 102887

Опубликована: Дек. 1, 2024

Язык: Английский

---