Neonatal encephalopathy prediction of poor outcome with diffusion-weighted imaging connectome and fixel-based analysis.
Neonatal encephalopathy prediction of poor outcome with diffusion-weighted imaging connectome and fixel-based analysis.
复制标题
通过扩散加权成像连接组和基于FIXEL的分析，新生儿脑病预测不良结果。
DOI：
10.1038/s41390-021-01550-2
复制
发表时间：
2022-05
影响因子：
3.6
通讯作者：
Tan, Sidhartha
中科院分区：
文献类型：
--
作者：
Jeong, Jeong-Won;Lee, Min-Hee;Fernandes, Nithi;Deol, Saihaj;Mody, Swati;Arslanturk, Suzan;Chinnam, Ratna B.;Tan, Sidhartha
新生儿脑病需要更好的最终预后生物标志物。为了确定与2年预后相关的最有效的新生儿成像标志物，我们回顾性地对足月新生儿脑病新生儿出生后4周获得的MRI进行了弥散加权成像连接组（DWIC）和固定体分析（FBA）。24例MRI患儿中有15例采用弥散束造影，其中5例患儿运动结果正常、异常或死亡。除一人外，其余15人都接受了低温治疗。在异常运动组和死亡组中，DWIC发现19条白质通路纤维取向分布严重破坏。使用随机森林分类，这些中断预测随访结果的准确率为89% - 99%。与正常音调组相比，异常运动组和死亡组的这些通路完整性降低（p < 10−6）。采用分级监督多视图典型相关，仅描述分析的5个维度中的3个，将异常运动和死亡与正常音调组明显区分开来。这项研究表明，利用早期DWIC和FBA进行预测的机器学习模型可能是在具有临床结果的大型MRI数据集中开发生物标志物的一种可能方法。
Better biomarkers of eventual outcome are needed for neonatal encephalopathy. To identify the most potent neonatal imaging marker associated with 2-year outcomes, we retrospectively performed diffusion-weighted imaging connectome (DWIC) and fixel-based analysis (FBA) on MRI obtained in the first four weeks of life in term neonatal encephalopathy newborns. Diffusion tractography was available in 15 out of 24 babies with MRI, 5 each with normal, abnormal motor outcome, or death. All fifteen except one underwent hypothermia as initial treatment. In abnormal motor and death groups, DWIC found 19 white matter pathways with severely disrupted fiber orientation distributions. Using random forest classification, these disruptions predicted the follow-up outcomes with 89%−99% accuracy. These pathways showed reduced integrity in abnormal motor and death vs. normal tone groups (p < 10−6). Using ranked supervised multi-view canonical correlation and depicting just 3 of the 5 dimensions of the analysis, the abnormal motor and death were clearly differentiated from each other and the normal tone group. This study suggests that a machine-learning model for prediction using early DWIC and FBA could be a possible way of developing biomarkers in large MRI datasets having clinical outcomes.
登录
查看更多内容
DOI：
10.1016/j.nicl.2018.01.003
发表时间：
2018
期刊：
NeuroImage. Clinical
影响因子：
--
作者：
Pannek K;Fripp J;George JM;Fiori S;Colditz PB;Boyd RN;Rose SE
通讯作者：
Rose SE
DOI：
10.1007/978-3-319-46720-7_24
发表时间：
2016-10-01
期刊：
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
影响因子：
--
作者：
Aydogan, Dogu Baran;Shi, Yonggang
通讯作者：
Shi, Yonggang
DOI：
10.1073/pnas.1418198112
发表时间：
2015-05-26
影响因子：
11.1
作者：
Reveley, Colin;Seth, Anil K.;Ye, Frank Q.
通讯作者：
Ye, Frank Q.
影响因子：
5.7
作者：
Raffelt DA;Tournier JD;Smith RE;Vaughan DN;Jackson G;Ridgway GR;Connelly A
通讯作者：
Connelly A
影响因子：
2.5
作者：
Dudink, Jeroen;Kerr, Jenny L.;Counsell, Serena J.
通讯作者：
Counsell, Serena J.