Proceedings of the National Academy of Sciences of the United States of America ( IF 9.4 ) Pub Date : 2021-04-13 , DOI: 10.1073/pnas.2021852118 Gokce Sarar 1, 2 , Bhaskar Rao 2 , Thomas Liu 3, 4, 5
Although individual subjects can be identified with high accuracy using correlation matrices computed from resting-state functional MRI (rsfMRI) data, the performance significantly degrades as the scan duration is decreased. Recurrent neural networks can achieve high accuracy with short-duration (72 s) data segments but are designed to use temporal features not present in the correlation matrices. Here we show that shallow feedforward neural networks that rely solely on the information in rsfMRI correlation matrices can achieve state-of-the-art identification accuracies (
中文翻译:
使用浅层前馈神经网络的功能连接组指纹识别 [神经科学]
虽然可以使用从静息状态功能 MRI (rsfMRI) 数据计算的相关矩阵以高精度识别个体受试者,但随着扫描持续时间的减少,性能显着下降。循环神经网络可以通过短时 (72 s) 数据段实现高精度,但旨在使用相关矩阵中不存在的时间特征。在这里,我们展示了仅依赖 rsfMRI 相关矩阵中的信息的浅层前馈神经网络可以实现最先进的识别精度。