XML English Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:

Nazari A, Alavimajd H, Shakeri N, Bakhshandeh M, Faghihzadeh E, Marzbani H. Prediction of Brain Connectivity Map in Resting-State Fmri Data Using Shrinkage Estimator. BCN. 2017;
URL: http://bcn.iums.ac.ir/article-1-1040-fa.html
Prediction of Brain Connectivity Map in Resting-State Fmri Data Using Shrinkage Estimator. مجله علوم اعصاب پایه و بالینی. 1395;

URL: http://bcn.iums.ac.ir/article-1-1040-fa.html

Purpose of the study: In recent years, brain functional connectivity studies is extended using the advanced statistical methods. Functional connectivity is identified by synchronous activation in a spatially distinct region of the brain in resting-state functional MRI data. For this purpose there are several methods such as seed-based correlation analysis, that is based on temporal correlation between different ROIs or between brain's voxels of prior seed.
Methods: In this paper, test-retest rs-fMRI data of 21 healthy subjects are analyzed to predict second replication connectivity map using first replication data. A potential estimator is "Raw estimator" that uses the first replication data from each subject to predict the second replication connectivity map of the same subject. The second estimator, "Mean estimator" uses the average of all sample subject connectivity to estimate correlation map. By shrinking raw estimator towards the average connectivity map of all subject's first replicate, shrinkage estimator is made. Prediction performance of second replication correlation map is evaluated by Mean Squared Error criteria (MSE).
Results: Using seed-based correlation analysis and choose Precentral gyrus as the ROI over 21 subjects in the study, on average MSE for raw, mean and shrinkage estimator are 0.2169, 0.1118 and 0.1103, respectively. Also percent reduction of MSE for shrinkage and mean estimator in comparison with raw estimator is 49.14 and 48.45, respectively.
Conclusion: Shrinkage approach has the positive effect on the prediction of functional connectivity. When data has a large between session variability, prediction of connectivity map can be improved by shrinking towards population mean. 
نوع مطالعه: Original | موضوع مقاله: Computational Neuroscience
دریافت: ۱۳۹۶/۷/۱۵ | پذیرش: ۱۳۹۶/۱۲/۸ | انتشار: ۱۳۹۷/۲/۳

ارسال نظر درباره این مقاله : نام کاربری یا پست الکترونیک شما:
کد امنیتی را در کادر بنویسید

کلیه حقوق این وب سایت متعلق به Basic and Clinical Neuroscience می باشد.

طراحی و برنامه نویسی : یکتاوب افزار شرق

© 2018 All Rights Reserved | Basic and Clinical Neuroscience

Designed & Developed by : Yektaweb