scholarly journals Regression‐based machine‐learning approaches to predict task activation using resting‐state fMRI

2019 ◽  
Vol 41 (3) ◽  
pp. 815-826 ◽  
Author(s):  
Alexander D. Cohen ◽  
Ziyi Chen ◽  
Oiwi Parker Jones ◽  
Chen Niu ◽  
Yang Wang
2020 ◽  
Vol 2020 ◽  
pp. 1-5
Author(s):  
Hufei Yu ◽  
Shucai Huang ◽  
Xiaojie Zhang ◽  
Qiuping Huang ◽  
Jun Liu ◽  
...  

Methamphetamine is a highly addictive drug of abuse, which will cause a series of abnormal consequences mentally and physically. This paper is aimed at studying whether the abnormalities of regional homogeneity (ReHo) could be effective features to distinguish individuals with methamphetamine dependence (MAD) from control subjects using machine-learning methods. We made use of resting-state fMRI to measure the regional homogeneity of 41 individuals with MAD and 42 age- and sex-matched control subjects and found that compared with control subjects, individuals with MAD have lower ReHo values in the right medial superior frontal gyrus but higher ReHo values in the right temporal inferior fusiform. In addition, AdaBoost classifier, a pretty effective ensemble learning of machine learning, was employed to classify individuals with MAD from control subjects with abnormal ReHo values. By utilizing the leave-one-out cross-validation method, we got the accuracy more than 84.3%, which means we can almost distinguish individuals with MAD from the control subjects in ReHo values via machine-learning approaches. In a word, our research results suggested that the AdaBoost classifier-neuroimaging approach may be a promising way to find whether a person has been addicted to methamphetamine, and also, this paper shows that resting-state fMRI should be considered as a biomarker, a noninvasive and effective assistant tool for evaluating MAD.


Author(s):  
Chen Niu ◽  
Alexander D. Cohen ◽  
Xin Wen ◽  
Ziyi Chen ◽  
Pan Lin ◽  
...  

2021 ◽  
Vol 352 ◽  
pp. 109084
Author(s):  
Valeria Saccà ◽  
Alessia Sarica ◽  
Andrea Quattrone ◽  
Federico Rocca ◽  
Aldo Quattrone ◽  
...  

Data in Brief ◽  
2020 ◽  
Vol 29 ◽  
pp. 105213 ◽  
Author(s):  
Pradyumna Lanka ◽  
D. Rangaprakash ◽  
Sai Sheshan Roy Gotoor ◽  
Michael N. Dretsch ◽  
Jeffrey S. Katz ◽  
...  

2019 ◽  
Vol 33 (1) ◽  
pp. 123-134 ◽  
Author(s):  
Jue Wang ◽  
Hai-Jiang Meng ◽  
Gong-Jun Ji ◽  
Ying Jing ◽  
Hong-Xiao Wang ◽  
...  

Abstract Both functional magnetic resonance imaging (fMRI) and transcranial magnetic stimulation (TMS) have been used to non-invasively localize the human motor functional area. These locations can be clinically used as stimulation target of TMS treatment. However, it has been reported that the finger tapping fMRI activation and TMS hotspot were not well-overlapped. The aim of the current study was to measure the distance between the finger tapping fMRI activation and the TMS hotspot, and more importantly, to compare the network difference by using resting-state fMRI. Thirty healthy participants underwent resting-state fMRI, task fMRI, and then TMS hotspot localization. We found significant difference of locations between finger tapping fMRI activation and TMS hotspot. Specifically, the finger tapping fMRI activation was more lateral than the TMS hotspot in the premotor area. The fMRI activation peak and TMS hotspot were taken as seeds for resting-state functional connectivity analyses. Compared with TMS hotspot, finger tapping fMRI activation peak showed more intensive functional connectivity with, e.g., the bilateral premotor, insula, putamen, and right globus pallidus. The findings more intensive networks of finger tapping activation than TMS hotspot suggest that TMS treatment targeting on the fMRI activation area might result in more remote effects and would be more helpful for TMS treatment on movement disorders.


Sign in / Sign up

Export Citation Format

Share Document