Brain anatomical architecture supports its functional activity and complex cognitive processes. However, how the structure–function (SF) relationship establishes and develops during early life, as well as its underlying mechanisms, remain largely unclear. To address these questions, we leveraged multimodal MRI data from two large-scale public databases, the developing Human Connectome Project (dHCP) and the Baby Connectome Project (BCP), to characterize the spatiotemporal dynamics of SF coupling from the perinatal period to toddlerhood. Our results revealed that SF coupling at birth exhibited a spatial variation along the sensorimotor-association cortical axis. During the perinatal period (26–44 postmenstrual weeks), SF coupling strengthened drastically and followed three distinct developmental trajectories across the cortex, with sensorimotor and visual areas showing the fastest growth and the earliest plateau. After birth, SF coupling shifted toward a weakening pattern across the cortex during infancy and toddlerhood (1–28 months). These developmental changes of SF coupling were more strongly associated with the maturation of functional connectivity, which first converged toward the local structural architecture prenatally and then diverged postnatally through the expansion of global inter-modular pathways. Furthermore, SF coupling at birth, the developmental transition point, exhibited a significant association with individual differences in cognition and language outcomes at 18 months of age. Collectively, these findings offer valuable insights into the organizational principles underlying structural and functional network development during early life as well as the complex evolving relationship between them.
Cancer management remains fragmented across its continuum, from late-stage diagnosis and salvage therapies to non-personalized surveillance. Here, we present Oncoformer, a unified multimodal transformer model trained on the China Oncology Multimodal Prediction and Surveillance Study (COMPASS) cohort (3.67 million individuals, 17.7 million clinical visits) and validated on independent external cohorts, including the UK Biobank. Oncoformer integrates longitudinal electronic health records with chest X-ray imaging to address multiple clinical tasks: pan-cancer diagnosis (area under the receiver operating characteristic curve [AUROC] = 0.956), future cancer prediction up to 1 year before diagnosis (AUROC = 0.869), tumor stage inference (mean AUROC > 0.90), patient-specific treatment-response forecasting, and recurrence-free survival stratification across ten cancer types (all p < 0.01). Staging predictions were independently validated against postoperative pathological endpoints and shown to converge on core cancer genomic pathways. By translating routine clinical data into a dynamic view of cancer evolution, Oncoformer provides a framework for risk-informed cancer prediction and treatment stratification using routine clinical data.
Fei Liu, Kai Wang, Hui Xu et al.· Cell· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.