Autism spectrum disorder recognition based on multi-view ensemble learning with multi-site fMRI

Kang, Li; Chen, Jin; Huang, Jianjun; Jiang, Jingwan

doi:10.1007/s11571-022-09828-9

Cited by 9 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further research in single nodes and in subgroups must be performed, while the study sample is to be extended. Finally, the upgrade of the scanner to Prisma while the study was carried may have introduced data variance which can reduce the classification accuracy in the data as shown in projects applying classifiers on fMRI data in multi-side projects ( 87 ).…”

Section: Discussionmentioning

confidence: 99%

Brain network changes in adult victims of violence

Shymanskaya

Kohn²,

Habel³

et al. 2023

Front. Psychiatry

View full text Add to dashboard Cite

IntroductionStressful experiences such as violence can affect mental health severely. The effects are associated with changes in structural and functional brain networks. The current study aimed to investigate brain network changes in four large-scale brain networks, the default mode network, the salience network, the fronto-parietal network, and the dorsal attention network in self-identified victims of violence and controls who did not identify themselves as victims.Materials and methodsThe control group (n = 32) was matched to the victim group (n = 32) by age, gender, and primary psychiatric disorder. Sparse inverse covariance maps were derived from functional resting-state measurements and from T1 weighted structural data for both groups.ResultsOur data underlined that mostly the salience network was affected in the sample of self-identified victims. In self-identified victims with a current psychiatric diagnosis, the dorsal attention network was mostly affected underlining the potential role of psychopathological alterations on attention-related processes.ConclusionThe results showed that individuals who identify themselves as victim demonstrated significant differences in all considered networks, both within- and between-network.

show abstract

Section: Discussionmentioning

confidence: 99%

Brain network changes in adult victims of violence

Shymanskaya

Kohn²,

Habel³

et al. 2023

Front. Psychiatry

View full text Add to dashboard Cite

show abstract

“…In the recent paper by Kang et al [26], the authors proposed a different approach to the analysis of timeseries and subsequent classification of data from the ABIDE I dataset. The authors used a long short-term memory (LSTM) network to extract correlations and features from cerebral ROIs, and then they classified these features with a deep neural network after applying data augmentation techniques.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Multi-Site MRI Data Harmonization with an Adversarial Learning Approach: Implementation to the Study of Brain Connectivity in Autism Spectrum Disorders

et al. 2023

View full text Add to dashboard Cite

Magnetic resonance imaging (MRI) nowadays plays an important role in the identification of brain underpinnings in a wide range of neuropsychiatric disorders, including Autism Spectrum Disorders (ASD). Characterizing the hallmarks in these pathologies is not a straightforward task and machine learning (ML) is certainly one of the most promising tools for addressing complex and non-linear problems. ML algorithms and, in particular, deep neural networks (DNNs), need large datasets in order to be properly trained and thus ensure generalization capabilities on new data. Large datasets can be obtained by collecting images from different centers, thus bringing unavoidable biases in the analysis due to differences in hardware and scanning protocols between different centers. In this work, we dealt with the issue of multicenter MRI data harmonization by comparing two different approaches: the analytical ComBat-GAM procedure, whose effectiveness is already documented in the literature, and an originally developed site-adversarial deep neural network (ad-DNN). The latter aims to perform a classification task while simultaneously searching for site-relevant patterns in order to make predictions free from site-related biases. As a case study, we implemented DNN and ad-DNN classifiers to distinguish subjects with ASD with respect to typical developing controls based on functional connectivity measures derived from data of the multicenter ABIDE collection. The classification performance of the proposed ad-DNN, measured in terms of the area under the ROC curve (AUC), achieved the value of AUC = 0.70±0.03, which is comparable to that obtained by a DNN on data harmonized according to the analytical procedure (AUC = 0.71±0.01). The relevant functional connectivity alterations identified by both procedures showed an agreement between each other and with the patterns of neuroanatomical alterations previously detected in the same cohort of subjects.

show abstract

“…A cluster of articles [83,85,88,90,93,95,99,101,104,106,111,113,114] focuses on using advanced computational techniques, including machine learning, deep learning, and graph analysis, to classify and diagnose autism. These articles represent the growing interest in leveraging data-driven approaches to understand and categorize individuals with ASD.…”

Section: Machine Learning and Graph Analysis For Asd Classificationmentioning

confidence: 99%

“…Articles [90,95,99,111] delved into the application of graph neural networks and connectivity analysis for diagnosing autism. These methods considered the interrelationships and patterns within functional brain networks, offering insights into the brain's role in autism.…”

Section: Graph Neural Network and Connectivity Analysismentioning

confidence: 99%

See 1 more Smart Citation

An Umbrella Review of the Fusion of fMRI and AI in Autism

Giansanti

2023

Diagnostics

View full text Add to dashboard Cite

The role of functional magnetic resonance imaging (fMRI) is assuming an increasingly central role in autism diagnosis. The integration of Artificial Intelligence (AI) into the realm of applications further contributes to its development. This study’s objective is to analyze emerging themes in this domain through an umbrella review, encompassing systematic reviews. The research methodology was based on a structured process for conducting a literature narrative review, using an umbrella review in PubMed and Scopus. Rigorous criteria, a standard checklist, and a qualification process were meticulously applied. The findings include 20 systematic reviews that underscore key themes in autism research, particularly emphasizing the significance of technological integration, including the pivotal roles of fMRI and AI. This study also highlights the enigmatic role of oxytocin. While acknowledging the immense potential in this field, the outcome does not evade acknowledging the significant challenges and limitations. Intriguingly, there is a growing emphasis on research and innovation in AI, whereas aspects related to the integration of healthcare processes, such as regulation, acceptance, informed consent, and data security, receive comparatively less attention. Additionally, the integration of these findings into Personalized Medicine (PM) represents a promising yet relatively unexplored area within autism research. This study concludes by encouraging scholars to focus on the critical themes of health domain integration, vital for the routine implementation of these applications.

show abstract

Autism spectrum disorder recognition based on multi-view ensemble learning with multi-site fMRI

Cited by 9 publications

References 27 publications

Brain network changes in adult victims of violence

Brain network changes in adult victims of violence

Multi-Site MRI Data Harmonization with an Adversarial Learning Approach: Implementation to the Study of Brain Connectivity in Autism Spectrum Disorders

An Umbrella Review of the Fusion of fMRI and AI in Autism

Contact Info

Product

Resources

About