Lingyu Xu1, Yaya Liu2, Jie Yu3, Xinjuan Li3, Xuan Yu3, Huiyi Cheng4, Jun Li5. 1. School of Computer Engineering and Science, Shanghai University, Shanghai, China; Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai, China. 2. School of Computer Engineering and Science, Shanghai University, Shanghai, China. Electronic address: liu_yaya@t.shu.edu.cn. 3. School of Computer Engineering and Science, Shanghai University, Shanghai, China. 4. South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou, China. 5. South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou, China; Key Lab for Behavioral Economic Science & Technology, South China Normal University, Guangzhou, China. Electronic address: jun.li@coer-scnu.org.
Abstract
BACKGROUND: Functional near-infrared spectroscopy (fNIRS) was used to investigate spontaneous hemodynamic fluctuations in the bilateral temporal cortices for typically developing (TD) children and children with autism spectrum disorder (ASD). NEW METHOD: This paper proposed an approach to estimate the global time-varying behavior of brain activity through the measurement on change in first-order statistical properties directly from fNIRS time series. Then, a deep learning model combining the long-short term memory (LSTM) and convolutional neural network (CNN) was constructed based on the integration strategy with improved bagging algorithm, with the purpose to explore the potential patterns of temporal variation for ASD identification. RESULTS: Based on the theory of stationarity, analysis on the global time-varying behavior of hemodynamic fluctuations in oxy-hemoglobin (HbO2) and deoxy-hemoglobin (Hb) demonstrated that children with ASD showed weaker internal logic, but stronger memory and persistence to random shocks than TD children. Differentiating between ASD and TD with the proposed deep learning approach resulted in high accurate classification with sensitivity of 97.1 % and specificity of 94.3 %. COMPARISON WITH EXISTING METHODS: Using fNIRS time series of Hb from single optical channel, we achieved a better classification accuracy of 95.7 % that was about 8 % higher than previous methods with similar data. CONCLUSIONS: The characterization on time-varying behavior of brain activity holds promise for better understanding the underlying causes to ASD. And the deployed deep learning framework with an integration manner has the potential for screening children with risk of ASD.
BACKGROUND: Functional near-infrared spectroscopy (fNIRS) was used to investigate spontaneous hemodynamic fluctuations in the bilateral temporal cortices for typically developing (TD) children and children with autism spectrum disorder (ASD). NEW METHOD: This paper proposed an approach to estimate the global time-varying behavior of brain activity through the measurement on change in first-order statistical properties directly from fNIRS time series. Then, a deep learning model combining the long-short term memory (LSTM) and convolutional neural network (CNN) was constructed based on the integration strategy with improved bagging algorithm, with the purpose to explore the potential patterns of temporal variation for ASD identification. RESULTS: Based on the theory of stationarity, analysis on the global time-varying behavior of hemodynamic fluctuations in oxy-hemoglobin (HbO2) and deoxy-hemoglobin (Hb) demonstrated that children with ASD showed weaker internal logic, but stronger memory and persistence to random shocks than TD children. Differentiating between ASD and TD with the proposed deep learning approach resulted in high accurate classification with sensitivity of 97.1 % and specificity of 94.3 %. COMPARISON WITH EXISTING METHODS: Using fNIRS time series of Hb from single optical channel, we achieved a better classification accuracy of 95.7 % that was about 8 % higher than previous methods with similar data. CONCLUSIONS: The characterization on time-varying behavior of brain activity holds promise for better understanding the underlying causes to ASD. And the deployed deep learning framework with an integration manner has the potential for screening children with risk of ASD.
Authors: Parisa Moridian; Navid Ghassemi; Mahboobeh Jafari; Salam Salloum-Asfar; Delaram Sadeghi; Marjane Khodatars; Afshin Shoeibi; Abbas Khosravi; Sai Ho Ling; Abdulhamit Subasi; Roohallah Alizadehsani; Juan M Gorriz; Sara A Abdulla; U Rajendra Acharya Journal: Front Mol Neurosci Date: 2022-10-04 Impact factor: 6.261
Authors: James C McPartland; Matthew D Lerner; Anjana Bhat; Tessa Clarkson; Allison Jack; Sheida Koohsari; David Matuskey; Goldie A McQuaid; Wan-Chun Su; Dominic A Trevisan Journal: J Autism Dev Disord Date: 2021-05-27