US 11,989,883 B2
Functional connectivity matrix processing system and device based on feature selection using filtering method
Jingsong Li, Hangzhou (CN); Jun Li, Hangzhou (CN); Baochen Wang, Hangzhou (CN); Zhuoxin Li, Hangzhou (CN); Yu Tian, Hangzhou (CN); and Tianshu Zhou, Hangzhou (CN)
Assigned to ZHEJIANG LAB, Hangzhou (CN)
Filed by ZHEJIANG LAB, Zhejiang (CN)
Filed on Jul. 27, 2023, as Appl. No. 18/360,796.
Claims priority of application No. 202211070002.9 (CN), filed on Sep. 2, 2022.
Prior Publication US 2024/0078678 A1, Mar. 7, 2024
Int. Cl. G06T 7/11 (2017.01); G06T 7/00 (2017.01)
CPC G06T 7/0014 (2013.01) [G06T 2207/10088 (2013.01); G06T 2207/30016 (2013.01)] 10 Claims
OG exemplary drawing
 
1. A functional connectivity matrix processing system based on feature selection using a filtering method, comprising:
a subject acquisition and preprocessing module configured to acquire a preprocessed resting state brain functional magnetic resonance image of a subject and a disease diagnosis result;
a brain region time series extraction module configured to extract time series of each brain region in the preprocessed resting state brain functional magnetic resonance image of each subject by using a brain image atlas;
a Pearson correlation coefficient calculation module configured to calculate a Pearson correlation coefficient of the time series of every two brain regions for each subject to obtain a Pearson correlation coefficient matrix of each brain region;
a vectorization matrix module configured to vectorize the Pearson correlation coefficient matrix of each brain region for each subject to obtain a vectorized Pearson correlation coefficient matrix COR;
a quantitative correlation index calculation module configured to calculate a quantitative correlation index Si between each feature in all the vectorized Pearson correlation coefficient matrices CORs and the disease diagnosis result by using a filtering method, and to select a functional connectivity feature CORsel with high correlation with the disease diagnosis result and a corresponding quantitative correlation index RELEsel based on a preset threshold;
a feature conversion module configured to perform weighting processing on the selected functional connectivity feature CORsel by using the corresponding quantitative correlation index RELEsel with high correlation with the disease diagnosis result to obtain a functional connectivity matrix FC; and
a matrix prediction module configured to obtain a prediction result from the functional connectivity matrix FC.