Meta‐Analysis Informed Functional Connectomes Representations for Depression Identification

• Published in: Journal of magnetic resonance imaging Vol. 62; no. 5; pp. 1358 - 1368
• Main Authors: Wang, Xinyi, Xue, Li, Dai, Zhongpeng, Shao, Junneng, Zhang, Yujie, Tian, Shui, Yan, Rui, Chen, Zhilu, Yao, Zhijian, Lu, Qing
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.11.2025; Wiley Subscription Services, Inc
• Subjects: Accuracy; Adult; Algorithms; Brain - diagnostic imaging; Brain - physiopathology; Cohen's d; Connectome - methods; Correlation analysis; Datasets; depression; Depression - diagnostic imaging; Female; Females; Field strength; functional connectomes representation; Functional magnetic resonance imaging; Humans; Image Processing, Computer-Assisted; machine learning framework; Magnetic Resonance Imaging - methods; Male; Males; Medical imaging; Mental depression; Meta-analysis; Middle Aged; Neuroimaging; Neuroimaging - methods; Performance evaluation; Permutations; Principal Component Analysis; Principal components analysis; Random noise; Representations; Reproducibility of Results; resting‐state magnetic resonance imaging; Retrospective Studies; Robust control; Sensitivity and Specificity; Statistical analysis; Statistical tests; functional connectomes representation; depression; meta‐analysis; machine learning framework; resting‐state magnetic resonance imaging
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.29801

ABSTRACT Background Meta‐analyses in neuroimaging have gained popularity. However, their clinical utility remains uncertain. Convergent masks, containing repeated clusters from publications, are often focal and small, and voxel‐wise features can lead to the curse of dimensionality, limiting discriminative ability in clinical diagnosis. Purpose To develop a functional connectome representation (FCR) by integrating meta‐analytic neuroimaging data and to evaluate its performance in identifying depression. Study Type Retrospective. Subjects The principal data set included 151 patients with depression (male/female, 72/79) and 105 healthy controls (male/female, 48/57). An external test data set comprised 109 patients (male/female, 44/65) and 54 healthy controls (male/female, 15/39). Field Strength/Sequence 3.0 T T1‐weighted imaging, resting‐state functional MRI with echo‐planar sequence. Assessment We performed the community detection algorithm and principal component analysis to develop the FCR. The model's performance based on the FCR was evaluated in terms of accuracy, specificity, and sensitivity. Effect sizes (Cohen's d) for FCR components were calculated between patients and healthy controls. Model robustness was assessed by analyzing the association between accuracy and the degree of shuffled features in the permutation test. Statistical Tests Chi‐squared test, two‐sample t‐test, effect sizes (Cohen's d), permutation tests for accuracy validation, and correlation analysis. Significance was determined at p < 0.05. Results Effect sizes (Cohen's d) for each of the 39 principal components to quantify the magnitude of differences between depressed patients and healthy controls, ranged from d = −0.22 to d = 0.84. The FCR‐based diagnostic model achieved an accuracy of 89.42% (principal data set) and 83.35% (external data set). Permutation tests (n = 1000) indicated that the model's accuracy was significantly higher than chance level. A significant negative correlation was observed between random noise and accuracy (r = −0.093). Data Conclusion The FCR effectively discriminates between depressed patients and healthy controls, exhibiting strong diagnostic performance, generalization, and robustness, supporting its potential utility in clinical depression identification. Evidence Level Level 3. Technical Efficacy Stage 2.