Stereology neuron counts correlate with deep learning estimates in the human hippocampal subregions.

Stereology neuron counts correlate with deep learning estimates in the human hippocampal subregions.
复制标题

DOI:
10.1038/s41598-023-32903-y
复制
发表时间:
2023-04-11
期刊:
影响因子:
4.6
通讯作者:
Augustinack, Jean C. C.
Augustinack, Jean C. C.
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Oltmer, Jan;Rosenblum, Emma W. W.;Williams, Emily M. M.;Roy, Jessica;Llamas-Rodriguez, Josue;Perosa, Valentina;Champion, Samantha N. N.;Frosch, Matthew P. P.;Augustinack, Jean C. C.

文献摘要

参考文献

相似文献

海马各亚区在专业化和对细胞死亡的脆弱性方面有所不同。神经元死亡和海马萎缩是阿尔茨海默病进展的标志。相对较少的研究已经检查了神经元的损失,在人类大脑中使用体视学。我们描述了一个自动化的高通量深度学习管道,以分割海马锥体神经元,在人类海马子域内生成锥体神经元估计值,并将我们的结果与体视学神经元计数相关联。基于7个案例和168个分区,我们使用开源CellPose算法对深度学习参数进行了审查,以从背景中分割海马锥体神经元,并展示了自动去除假阳性分割。通过深度学习管道和手动分割分割的神经元之间的Dice评分没有差异(独立样本t检验:t(28)= 0.33,p = 0.742)。深度学习神经元估计与每个子区域的手动体视学计数强烈相关(斯皮尔曼相关性(n = 9):r(7)= 0.97,p < 0.001),并且对于每个分区单独地(斯皮尔曼相关性(n = 168):r(166)= 0.90,p <0.001)。高吞吐量深度学习管道为现有标准提供验证。这种深度学习方法可能有利于未来的研究,以跟踪基线和弹性健康老化到最早的疾病进展。
Hippocampal subregions differ in specialization and vulnerability to cell death. Neuron death and hippocampal atrophy have been a marker for the progression of Alzheimer’s disease. Relatively few studies have examined neuronal loss in the human brain using stereology. We characterize an automated high-throughput deep learning pipeline to segment hippocampal pyramidal neurons, generate pyramidal neuron estimates within the human hippocampal subfields, and relate our results to stereology neuron counts. Based on seven cases and 168 partitions, we vet deep learning parameters to segment hippocampal pyramidal neurons from the background using the open-source CellPose algorithm, and show the automated removal of false-positive segmentations. There was no difference in Dice scores between neurons segmented by the deep learning pipeline and manual segmentations (Independent Samples t-Test: t(28) = 0.33, p = 0.742). Deep-learning neuron estimates strongly correlate with manual stereological counts per subregion (Spearman’s correlation (n = 9): r(7) = 0.97, p < 0.001), and for each partition individually (Spearman’s correlation (n = 168): r(166) = 0.90, p <0 .001). The high-throughput deep-learning pipeline provides validation to existing standards. This deep learning approach may benefit future studies in tracking baseline and resilient healthy aging to the earliest disease progression.
DOI: 10.1371/journal.pone.0177544
发表时间: 2017
期刊: PloS one
影响因子: 3.7
作者:
Araújo T;Aresta G;Castro E;Rouco J;Aguiar P;Eloy C;Polónia A;Campilho A
通讯作者: Campilho A
DOI: 10.1016/j.compag.2008.02.007
发表时间: 2008-10-01
影响因子: 8.3
作者:
Igathinathane, C.;Pordesimo, L. O.;Methuku, S. R.
通讯作者: Methuku, S. R.
DOI: 10.1017/s1041610297004973
发表时间: 1997-01-01
影响因子: 7
作者:
Braak, H;Braak, E
通讯作者: Braak, E
DOI: 10.1016/j.xcrm.2021.100400
发表时间: 2021-09-21
期刊: Cell reports. Medicine
影响因子: --
作者:
Hong R;Liu W;DeLair D;Razavian N;Fenyö D
通讯作者: Fenyö D
DOI: 10.1093/jnen/62.1.55
发表时间: 2003-01-01
影响因子: 3.2
作者:
Hof, PR;Bussière, T;Morrison, JH
通讯作者: Morrison, JH