Zang YF papers

Med Image Anal. 2026 Jan 17;110:103949. doi: 10.1016/j.media.2026.103949. Online ahead of print.

ABSTRACT

Functional magnetic resonance imaging (fMRI) allows real-time observation of brain activity through blood oxygen level-dependent (BOLD) signals and is extensively used in studies related to sex classification, age estimation, behavioral measurements prediction, and mental disorder diagnosis. However, the application of deep learning techniques to brain fMRI analysis is hindered by the small sample size of fMRI datasets. Transfer learning offers a solution to this problem, but most existing approaches are designed for large-scale 2D natural images. The heterogeneity between 4D fMRI data and 2D natural images makes direct model transfer infeasible. This study proposes a novel geometric mapping-based fMRI transfer learning method that enables transfer learning from 2D natural images to 4D fMRI brain images, bridging the transfer learning gap between fMRI data and natural images. The proposed Multi-scale Multi-domain Feature Aggregation (MMFA) module extracts effective aggregated features and reduces the dimensionality of fMRI data to 3D space. By treating the cerebral cortex as a folded Riemannian manifold in 3D space and mapping it into 2D space using surface geometric mapping, we make the transfer learning from 2D natural images to 4D brain images possible. Moreover, the topological relationships of the cerebral cortex are maintained with our method, and calculations are performed along the Riemannian manifold of the brain, effectively addressing signal interference problems. The experimental results based on the Human Connectome Project (HCP) dataset demonstrate the effectiveness of the proposed method. Our method achieved state-of-the-art performance in sex classification, age estimation, and behavioral measurement prediction tasks. Moreover, we propose a cascaded transfer learning approach for depression diagnosis, and proved its effectiveness on 23 depression datasets. In summary, the proposed fMRI transfer learning method, which accounts for the structural characteristics of the brain, is promising for applying transfer learning from natural images to brain fMRI images, significantly enhancing the performance in various fMRI analysis tasks.

PMID:41576824 | DOI:10.1016/j.media.2026.103949

Neuroimage. 2026 Jan 20:121743. doi: 10.1016/j.neuroimage.2026.121743. Online ahead of print.

ABSTRACT

Personalized repetitive transcranial magnetic stimulation (rTMS) increasingly relies on resting-state functional magnetic resonance imaging (fMRI) to select stimulation sites, yet most pipelines depend on user-defined thresholds and atlas masks, which can shift individualized targets. We propose a watershed-based approach, implemented in a graphical user interface, that performs threshold-independent segmentation of functional images to support rTMS target localization. As a proof-of-concept, we focused on Alzheimer's disease-related circuits within the default mode network, designating the posterior cingulate cortex (PCC) as the deep effective region and the inferior parietal lobule (IPL) as the superficial stimulation target. In a cohort of 21 healthy participants, quantitative comparison with a conventional threshold-based, mask-constrained peak strategy revealed high concordance for PCC peaks but a median spatial displacement of 6.0 mm (95% CI: 0.0-12.7 mm) for IPL targets. Qualitative examples further illustrate that watershed segmentation reduces bias from neighboring functional clusters, truncation by atlas boundaries, and ambiguity among multiple local peaks. By decoupling target definition from user-chosen thresholds and packaging the method in an accessible toolbox, this framework offers a generalizable tool for individualized fMRI-guided rTMS.

PMID:41570954 | DOI:10.1016/j.neuroimage.2026.121743

World J Gastrointest Surg. 2025 Nov 27;17(11):112341. doi: 10.4240/wjgs.v17.i11.112341.

ABSTRACT

This letter presents a critical analysis of the study by Zhao et al, which proposed a therapeutic strategy for difficult common bile duct stones focusing on the "ice-breaking sign" as a pivotal radiological feature. Based on magnetic resonance cholangiopancreatography with three-dimensional reconstruction, the diagnostic criteria for this sign were established by identifying an abrupt narrowing at the distal bile duct caused by impacted stones, analogous to the morphology of an ice-breaking vessel. Specifically, the proximal bile duct (hepatic hilar side) exhibited significant dilatation upstream of the stenosis, while the distal segment (duodenal papillary side) presented with stricture or occlusion. This study was the first to introduce the radiological marker termed the "ice-breaking sign", providing a novel dimension for the evaluation of refractory common bile duct stones. However, notable limitations were also present in this study. The interpretation of the ice-breaking sign depended largely on subjective assessments by physicians, even though a multidisciplinary consensus approach was employed. Objective quantification criteria, such as specific thresholds for the degree of stenosis, were not established. Furthermore, being a single-center study, it might have influenced the reproducibility of findings across different centers. Future studies should explore the pathophysiological mechanisms of the "ice-breaking sign" in greater depth, increase the sample size, and conduct multicenter research to validate its clinical universality and guiding significance for treatment strategies.

PMID:41357635 | PMC:PMC12679030 | DOI:10.4240/wjgs.v17.i11.112341

Transl Psychiatry. 2025 Nov 10. doi: 10.1038/s41398-025-03715-7. Online ahead of print.

ABSTRACT

Hemispheric lateralization, recognized as a pivotal feature in both the structural and functional organization of the human brain, may undergo alterations in specific psychiatric disorders. However, the time-varying patterns of hemispheric lateralization in individuals with major depressive disorder (MDD) and the relationship between these patterns and gene expression profiles remain largely unexplored thus far. Using a large multi-site resting-state functional magnetic resonance imaging (rs-fMRI) data encompassing 2611 participants (1660 MDD patients and 1341 healthy controls), we examined MDD-related abnormalities in dynamic laterality and its association with clinical symptoms, meta-analytic cognitive functions, and neurotransmitter receptor profiles, respectively. And the biological basis behind these changes was investigated through gene enrichment analysis and cell-specific analysis. Here we found revealed pronounced fluctuations in lateralization primarily in the regions in default mode network, attention network and control network in MDD patients when compared to healthy controls. In addition, these fluctuations exhibited significant correlations with higher-order cognition terms and the distributions of disease related neurotransmitters. Further, through gene enrichment and cell-specific analysis, we identified a molecular genetic basis for these changes, highlighting synaptic function-related genes and neuronal cells. Collectively, these results demonstrated robust altered brain lateralization patterns in MDD and its molecular genetic basis, providing new clues to understand the pathophysiology of MDD.

PMID:41257981 | DOI:10.1038/s41398-025-03715-7