Analysis of the Over-Connectivity in Autistic Brains Using the Maximum Spanning Tree: Application on the Multi-Site and Heterogeneous ABIDE Dataset

Benabdallah, Fatima Zahra; Maliani, Ahmed Drissi El; Lotfi, Dounia

doi:10.1109/wincom50532.2020.9272441

Cited by 6 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the sake of comparison with the state-of-the-art, we used ABIDE I, since its pre-processed version was vastly used in many recent works all concerned with early ASD detection [ 9 , 30 ]. Moreover, we have also used this same database with other strategies in previous works to detect autism [ 9 , 10 ]. We also tested different options for creating the base data, creating nine combinations based on three atlases and three connectivity computing methods.…”

Section: Discussionmentioning

confidence: 99%

“…This made it possible to exploit the benefits other fields could attain using deep learning, as the results show. Note that without deep learning, the best result achieved in the literature of autism detection attained only 70% [ 9 , 10 , 11 , 24 ] with the whole ABIDE I dataset. However, in the present paper, we were able to achieve 90% accuracy using the RGB-mimicking to build the 3D matrices.…”

Section: Discussionmentioning

confidence: 99%

“…Then, the enhanced matrices are extracted based on high-weight and low-weight connections using the maximum spanning tree and the minimum spanning tree, respectively, as shown on the left side of Figure 1 . Therefore, the enhanced matrices represent the theories of over-connectivity and under-connectivity, already proven to exist between the brain regions [ 9 , 10 ].…”

Section: Materials and Methodsmentioning

confidence: 99%

“…On the other hand, functional resting-state networks start to emerge before birth and become evident at 26 weeks prenatal age [ 8 ]. These networks capture neural interactions and have enabled the detection of autism with an accuracy between 60 and 70% in a heterogeneous setting using machine learning methods [ 9 , 10 , 11 ]. With the application of deep learning, the accuracy of detection has been shown to further improve reaching 80% [ 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Convolutional Neural Network-Based Connectivity Enhancement Approach for Autism Spectrum Disorder Detection

2023

Self Cite

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) represents an ongoing obstacle facing many researchers to achieving early diagnosis with high accuracy. To advance developments in ASD detection, the corroboration of findings presented in the existing body of autism-based literature is of high importance. Previous works put forward theories of under- and over-connectivity deficits in the autistic brain. An elimination approach based on methods that are theoretically comparable to the aforementioned theories proved the existence of these deficits. Therefore, in this paper, we propose a framework that takes into account the properties of under- and over-connectivity in the autistic brain using an enhancement approach coupled with deep learning through convolutional neural networks (CNN). In this approach, image-alike connectivity matrices are created, and then connections related to connectivity alterations are enhanced. The overall objective is the facilitation of early diagnosis of this disorder. After conducting tests using information from the large multi-site Autism Brain Imaging Data Exchange (ABIDE I) dataset, the results show that this approach provides an accurate prediction value reaching up to 96%.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Materials and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Convolutional Neural Network-Based Connectivity Enhancement Approach for Autism Spectrum Disorder Detection

2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some studies do not use an independent data set for testing, while others use an independent test set, but the training data and test data come from the same site [34]. ABIDE I aggregates fMRI data of autism collected from laboratories all over the world, the fMRI data is heterogeneous [35]. We divide the filtered data into training set and testing set, our model performs independent testing with multi-site heterogeneous data.…”

Section: Discussionmentioning

confidence: 99%

Autism detection based on multiple time scale model

Qin¹,

Zhu²,

Ye³

et al. 2022

J. Neural Eng.

View full text Add to dashboard Cite

Objective.Current autism clinical detection relies on doctor observation and filling of clinical scales, which is subjective and easily misdetection. Existing autism research of functional magnetic resonance imaging (fMRI) over-compresses the time-scale information and has poor generalization ability. This study extracts multiple time scale brain features of fMRI, providing objective detection. Approach. We first use least absolute shrinkage and selection operator (LASSO) to build a sparse network and extract features with a time scale of 1. Then, we use hidden markov model (HMM) to extract features that describe the dynamic changes of the brain, with a time scale of 2. Additionally, to analyze the features of the potential network activity of autism from a higher time scale, we use long short-term memory (LSTM) to construct an auto-encoder to re-encode the original data and extract the features of the at a higher time scale, with a time scale of T, and T is the time length of fMRI. We use Recursive Feature Elimination (RFE) for feature selection for three different time scale features, merge them into multiple time scale features, and finally use one-dimensional convolution neural network (1DCNN) for classification. Main results. Compared with well-established models, our method has achieved better results. The accuracy of our method is 76.0%, and the area under the roc curve is 0.83, tested on the completely independent data, so our method has better generalization ability. Significance. This research analyzes fMRI sequences from multiple time scale to detect autism, and it also provides a new framework and research ideas for subsequent fMRI analysis.

show abstract

A CNN Based 3D Connectivity Matrices Features for Autism Detection: Application on ABIDE I

Benabdallah

Maliani

2021

Ubiquitous Networking

View full text Add to dashboard Cite

Analysis of the Over-Connectivity in Autistic Brains Using the Maximum Spanning Tree: Application on the Multi-Site and Heterogeneous ABIDE Dataset

Cited by 6 publications

References 14 publications

A Convolutional Neural Network-Based Connectivity Enhancement Approach for Autism Spectrum Disorder Detection

A Convolutional Neural Network-Based Connectivity Enhancement Approach for Autism Spectrum Disorder Detection

Autism detection based on multiple time scale model

A CNN Based 3D Connectivity Matrices Features for Autism Detection: Application on ABIDE I

Contact Info

Product

Resources

About