Centre d'Information et de documentation du CRA Rhône-Alpes
CRA
Informations pratiques
-
Adresse
Centre d'information et de documentation
du CRA Rhône-Alpes
Centre Hospitalier le Vinatier
bât 211
95, Bd Pinel
69678 Bron CedexHoraires
Lundi au Vendredi
9h00-12h00 13h30-16h00Contact
Tél: +33(0)4 37 91 54 65
Mail
Fax: +33(0)4 37 91 54 37
-
Résultat de la recherche
2 recherche sur le mot-clé 'Deep learning'
Affiner la recherche Générer le flux rss de la recherche
Partager le résultat de cette recherche Faire une suggestion
Eye Tracking Biomarkers for Autism Spectrum Disorder Detection using Machine Learning and Deep Learning Techniques: Review / R. ASMETHA JEYARANI in Research in Autism Spectrum Disorders, 108 (October 2023)
[article]
Titre : Eye Tracking Biomarkers for Autism Spectrum Disorder Detection using Machine Learning and Deep Learning Techniques: Review Type de document : Texte imprimé et/ou numérique Auteurs : R. ASMETHA JEYARANI, Auteur ; Radha SENTHILKUMAR, Auteur Article en page(s) : p.102228 Mots-clés : Autism Spectrum Disorder Eye tracking Deep learning Machine learning Biomarker Index. décimale : PER Périodiques Résumé : Eye tracking is a promising tool for Autism Spectrum Disorder (ASD) detection in both children and adults. An important aspect of social communication is keeping eye contact, which is something that people with ASD frequently struggle with. Eye tracking can assess the duration of eye contact and the frequency and direction of gaze movements, offering quantifiable indicators of social communication deficits. People with ASD may also demonstrate other abnormalities in visual processing, such as an increased concentration on detail, sensory sensitivity, and trouble with complicated visual activities. These variations can be measured via Eye tracking, which offers critical information for the planning of therapy and diagnosis. The primary objective of this work is to provide a thorough description of the most recent studies that use Eye tracking combined with various Machine Learning (ML) and Deep Learning (DL) models for the detection of ASD. This will provide insights into the identification, and behavioral assessment, and distinguish between autistic people and those who are Typically Developing (TD). A detailed review of the various ML and DL models with their datasets and performance criteria is presented. Different types of eye movement datasets with diagnostic standards and eye tracker devices are also discussed. Finally, the study addresses the potential of gaze prediction in ASD patients for the design of interventions. En ligne : https://doi.org/10.1016/j.rasd.2023.102228 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=514
in Research in Autism Spectrum Disorders > 108 (October 2023) . - p.102228[article] Eye Tracking Biomarkers for Autism Spectrum Disorder Detection using Machine Learning and Deep Learning Techniques: Review [Texte imprimé et/ou numérique] / R. ASMETHA JEYARANI, Auteur ; Radha SENTHILKUMAR, Auteur . - p.102228.
in Research in Autism Spectrum Disorders > 108 (October 2023) . - p.102228
Mots-clés : Autism Spectrum Disorder Eye tracking Deep learning Machine learning Biomarker Index. décimale : PER Périodiques Résumé : Eye tracking is a promising tool for Autism Spectrum Disorder (ASD) detection in both children and adults. An important aspect of social communication is keeping eye contact, which is something that people with ASD frequently struggle with. Eye tracking can assess the duration of eye contact and the frequency and direction of gaze movements, offering quantifiable indicators of social communication deficits. People with ASD may also demonstrate other abnormalities in visual processing, such as an increased concentration on detail, sensory sensitivity, and trouble with complicated visual activities. These variations can be measured via Eye tracking, which offers critical information for the planning of therapy and diagnosis. The primary objective of this work is to provide a thorough description of the most recent studies that use Eye tracking combined with various Machine Learning (ML) and Deep Learning (DL) models for the detection of ASD. This will provide insights into the identification, and behavioral assessment, and distinguish between autistic people and those who are Typically Developing (TD). A detailed review of the various ML and DL models with their datasets and performance criteria is presented. Different types of eye movement datasets with diagnostic standards and eye tracker devices are also discussed. Finally, the study addresses the potential of gaze prediction in ASD patients for the design of interventions. En ligne : https://doi.org/10.1016/j.rasd.2023.102228 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=514 Single-participant structural similarity matrices lead to greater accuracy in classification of participants than function in autism in MRI / M. J. LEMING in Molecular Autism, 12 (2021)
[article]
Titre : Single-participant structural similarity matrices lead to greater accuracy in classification of participants than function in autism in MRI Type de document : Texte imprimé et/ou numérique Auteurs : M. J. LEMING, Auteur ; Simon BARON-COHEN, Auteur ; J. SUCKLING, Auteur Article en page(s) : 34 p. Langues : Anglais (eng) Mots-clés : Autism Deep learning Functional connectivity Structural similarity Index. décimale : PER Périodiques Résumé : BACKGROUND: Autism has previously been characterized by both structural and functional differences in brain connectivity. However, while the literature on single-subject derivations of functional connectivity is extensively developed, similar methods of structural connectivity or similarity derivation from T1 MRI are less studied. METHODS: We introduce a technique of deriving symmetric similarity matrices from regional histograms of grey matter volumes estimated from T1-weighted MRIs. We then validated the technique by inputting the similarity matrices into a convolutional neural network (CNN) to classify between participants with autism and age-, motion-, and intracranial-volume-matched controls from six different databases (29,288 total connectomes, mean age = 30.72, range 0.42-78.00, including 1555 subjects with autism). We compared this method to similar classifications of the same participants using fMRI connectivity matrices as well as univariate estimates of grey matter volumes. We further applied graph-theoretical metrics on output class activation maps to identify areas of the matrices that the CNN preferentially used to make the classification, focusing particularly on hubs. LIMITATIONS: While this study used a large sample size, the majority of data was from a young age group; furthermore, to make a viable machine learning study, we treated autism, a highly heterogeneous condition, as a binary label. Thus, these results are not necessarily generalizable to all subtypes and age groups in autism. RESULTS: Our models gave AUROCs of 0.7298 (69.71% accuracy) when classifying by only structural similarity, 0.6964 (67.72% accuracy) when classifying by only functional connectivity, and 0.7037 (66.43% accuracy) when classifying by univariate grey matter volumes. Combining structural similarity and functional connectivity gave an AUROC of 0.7354 (69.40% accuracy). Analysis of classification performance across age revealed the greatest accuracy in adolescents, in which most data were present. Graph analysis of class activation maps revealed no distinguishable network patterns for functional inputs, but did reveal localized differences between groups in bilateral Heschl's gyrus and upper vermis for structural similarity. CONCLUSION: This study provides a simple means of feature extraction for inputting large numbers of structural MRIs into machine learning models. Our methods revealed a unique emphasis of the deep learning model on the structure of the bilateral Heschl's gyrus when characterizing autism. En ligne : http://dx.doi.org/10.1186/s13229-021-00439-5 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=459
in Molecular Autism > 12 (2021) . - 34 p.[article] Single-participant structural similarity matrices lead to greater accuracy in classification of participants than function in autism in MRI [Texte imprimé et/ou numérique] / M. J. LEMING, Auteur ; Simon BARON-COHEN, Auteur ; J. SUCKLING, Auteur . - 34 p.
Langues : Anglais (eng)
in Molecular Autism > 12 (2021) . - 34 p.
Mots-clés : Autism Deep learning Functional connectivity Structural similarity Index. décimale : PER Périodiques Résumé : BACKGROUND: Autism has previously been characterized by both structural and functional differences in brain connectivity. However, while the literature on single-subject derivations of functional connectivity is extensively developed, similar methods of structural connectivity or similarity derivation from T1 MRI are less studied. METHODS: We introduce a technique of deriving symmetric similarity matrices from regional histograms of grey matter volumes estimated from T1-weighted MRIs. We then validated the technique by inputting the similarity matrices into a convolutional neural network (CNN) to classify between participants with autism and age-, motion-, and intracranial-volume-matched controls from six different databases (29,288 total connectomes, mean age = 30.72, range 0.42-78.00, including 1555 subjects with autism). We compared this method to similar classifications of the same participants using fMRI connectivity matrices as well as univariate estimates of grey matter volumes. We further applied graph-theoretical metrics on output class activation maps to identify areas of the matrices that the CNN preferentially used to make the classification, focusing particularly on hubs. LIMITATIONS: While this study used a large sample size, the majority of data was from a young age group; furthermore, to make a viable machine learning study, we treated autism, a highly heterogeneous condition, as a binary label. Thus, these results are not necessarily generalizable to all subtypes and age groups in autism. RESULTS: Our models gave AUROCs of 0.7298 (69.71% accuracy) when classifying by only structural similarity, 0.6964 (67.72% accuracy) when classifying by only functional connectivity, and 0.7037 (66.43% accuracy) when classifying by univariate grey matter volumes. Combining structural similarity and functional connectivity gave an AUROC of 0.7354 (69.40% accuracy). Analysis of classification performance across age revealed the greatest accuracy in adolescents, in which most data were present. Graph analysis of class activation maps revealed no distinguishable network patterns for functional inputs, but did reveal localized differences between groups in bilateral Heschl's gyrus and upper vermis for structural similarity. CONCLUSION: This study provides a simple means of feature extraction for inputting large numbers of structural MRIs into machine learning models. Our methods revealed a unique emphasis of the deep learning model on the structure of the bilateral Heschl's gyrus when characterizing autism. En ligne : http://dx.doi.org/10.1186/s13229-021-00439-5 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=459