基于fNIRS的自闭症分类中的时间泛化性：跨时间窗口迁移基准
Temporal Generalization in fNIRS-Based Autism Classification: A Cross-Time-Window Transfer Benchmark
查看机构详情
- University of Colorado Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）
- University of Washington School of Medicine（华盛顿大学医学院）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对基于fNIRS的自闭症分类中的时间分布偏移问题，构建跨时间窗口迁移基准，发现域对抗等策略可在无目标受试者数据时实现较高准确率，为实际部署提供了路线图。
中文摘要 AI 辅助
功能近红外光谱（fNIRS）是自闭症谱系障碍（ASD）分类的极具前景的模态，但现有方法假设评估在时间上对齐。实际中，由于血流动力学延迟和神经血管耦合的差异，最优观测窗口因受试者而异，产生时间分布偏移，导致性能下降。我们将此形式化为跨时间窗口迁移问题，引入了在生物运动试次中改变窗口长度（2.5-10秒）和偏移的方案。利用fNIRS记录的地形图表示，我们在留一受试者交叉验证（N=124）下，对两种零样本基线和八种适应策略下的三种视觉架构进行了基准测试。关键发现：（1）零样本跨窗口准确率接近随机水平（54%-69%）；（2）约5%的受试者特定微调可恢复90%-96%，而受试者特定上限达到97%-100%，表明受试者间变异性是主要障碍；（3）域对抗和自监督策略在无目标受试者数据时达到78%-90%；（4）从短至2.5秒的窗口中可恢复判别信息。这些发现为在实际时间变异性下部署基于fNIRS的ASD分类器提供了实用路线图。
英文摘要
Functional near-infrared spectroscopy (fNIRS) is a promising modality for autism spectrum disorder (ASD) classification, yet existing approaches assume temporally aligned evaluation. In practice, the optimal observation window varies across subjects due to differences in hemodynamic delay and neurovascular coupling, creating a temporal distribution shift that degrades performance. We formalize this as a \textit{cross-time-window transfer problem}, introducing a protocol that varies window length (2.5--10\,s) and offset within biological motion trials. Using topographic map representations of fNIRS recordings, we benchmark three vision architectures under two zero-shot baselines and eight adaptation strategies under leave-one-subject-out cross-validation ($N{=}124$). Key findings: (1) zero-shot cross-window accuracy is near chance (54--69\%); (2) ${\approx}5\%$ subject-specific fine-tuning recovers 90--96\%, while a subject-specific upper bound reaches 97--100\%, identifying inter-subject variability as the dominant barrier; (3) domain-adversarial and self-supervised strategies achieve 78--90\% without target-subject data; and (4) discriminative information is recoverable from windows as short as 2.5\,s. These findings provide a practical roadmap for deploying fNIRS-based ASD classifiers under realistic temporal variability.
