发表机构
The University of Queensland; Mawlana Bhashani Science and Technology University（昆士兰大学; 毛拉纳·巴沙尼科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MAC-Net提出协变量感知的多任务深度学习框架，通过隔离tfMRI特征与参与者变量，在6,500名参与者数据上优于基线，实现可复现的认知功能估计。
AI 中文摘要
从神经信号进行客观认知评估支持神经康复，但基于任务态fMRI（tfMRI）的个体水平预测仍然困难，因为神经特征与大量人口统计学和扫描仪相关变异共存。我们提出了多任务激活与对比网络（MAC-Net），一种协变量感知的深度学习框架，用于从区域tfMRI建模个体认知功能。通过将tfMRI特征隔离到专用神经通路，并将参与者变量限制在终端晚期融合通路中，MAC-Net在特征学习期间防止主导协变量抑制高维临床表示。在家庭感知交叉验证下，评估了6,500名青少年大脑认知发展研究参与者的基线数据，MAC-Net与线性模型、随机森林和替代深度架构进行了基准比较。N-back加货币激励延迟配置在流体、晶体和总认知上实现了0.174、0.238和0.277的R²值，优于仅协变量基线（0.178）和替代深度模型（0.217）。N-back是最具信息量的范式，而纳入停止信号任务略微降低了性能。通过积分梯度、DeepLIFT和输入梯度的特征归因高度一致，定位了与工作记忆相关的额叶、顶叶和扣带回区域。这些发现表明，协变量感知的多任务建模产生了可复现的认知功能估计，为临床转化建立了稳健的神经工程框架。
英文摘要
Objective cognitive assessment from neural signals supports neurorehabilitation, but individual-level prediction from task-based fMRI (tfMRI) remains difficult because neural features coexist with substantial demographic and scanner-related variation. We present the Multi-task Activation and Contrast Network (MAC-Net), a covariate-aware deep learning framework for modeling individual cognitive function from regional tfMRI. By isolating tfMRI features into a dedicated neural pathway and restricting participant variables to a terminal late-fusion pathway, MAC-Net prevents dominant covariates from suppressing high-dimensional clinical representations during feature learning. Evaluating baseline data from 6,500 Adolescent Brain Cognitive Development Study participants under family-aware cross-validation, MAC-Net was benchmarked against linear models, random forests, and alternative deep architectures. The N-back plus Monetary Incentive Delay configuration achieved $R^{2}$ values of 0.174, 0.238, and 0.277 for fluid, crystallized, and total cognition, outperforming covariate-only baselines (0.178) and alternative deep models (0.217). N-back was the most informative paradigm, whereas incorporating the Stop Signal Task marginally degraded performance. Feature attributions via Integrated Gradients, DeepLIFT, and Input Gradient were highly concordant, localizing working-memory-related frontal, parietal, and cingulate regions. These findings demonstrate that covariate-aware multi-task modeling yields reproducible cognitive-function estimations, establishing a robust neural engineering framework for clinical translation.
Comments13 pages, 4 figures, 2 supplementary tables. This work has been submitted to the IEEE Transactions on Neural Systems and Rehabilitation Engineering for possible publication
