Deep learning classification of reading disability with regional brain volume features

•Deformation-based deep learning was used to classify reading disability.•Autoencoder pretraining optimized neural network classification accuracy.•Reading disability classification precision (0.75) and recall (0.78) was observed.•Brain regions were differentially predictive of cases and controls.•C...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:NeuroImage (Orlando, Fla.) Ročník 273; s. 120075
Hlavní autori: Joshi, Foram, Wang, James Z., Vaden, Kenneth I., Eckert, Mark A.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States Elsevier Inc 01.06.2023
Elsevier Limited
Elsevier
Predmet:
Accuracy
Brain
Brain - diagnostic imaging
Brain morphology
Brain research
Child
Classification
Comprehension
Convolutional neural network
Cortex
Data
Data compression
Decoding
Deep Learning
Disability
Discussion groups
Dyslexia
Dyslexia - diagnostic imaging
Humans
Individual differences
Language
Learning
Learning disabilities
Medical imaging
Morphology
Neural networks
Neuroimaging
Neuroimaging - methods
Occipital lobe
People with disabilities
Phenotypic variations
Phonology
Reading comprehension
Reading disabilities
Reading disability
Regions
Specific learning disorder in reading
Superior temporal sulcus
Support vector machines
Temporal lobe
Specific learning disorder in reading
Reading disability
Dyslexia
Brain morphology
Convolutional neural network
ISSN:1053-8119, 1095-9572, 1095-9572
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•Deformation-based deep learning was used to classify reading disability.•Autoencoder pretraining optimized neural network classification accuracy.•Reading disability classification precision (0.75) and recall (0.78) was observed.•Brain regions were differentially predictive of cases and controls.•Classification probability related to non-word and real word reading abilities. Developmental reading disability is a prevalent and often enduring problem with varied mechanisms that contribute to its phenotypic heterogeneity. This mechanistic and phenotypic variation, as well as relatively modest sample sizes, may have limited the development of accurate neuroimaging-based classifiers for reading disability, including because of the large feature space of neuroimaging datasets. An unsupervised learning model was used to reduce deformation-based data to a lower-dimensional manifold and then supervised learning models were used to classify these latent representations in a dataset of 96 reading disability cases and 96 controls (mean age: 9.86 ± 1.56 years). A combined unsupervised autoencoder and supervised convolutional neural network approach provided an effective classification of cases and controls (accuracy: 77%; precision: 0.75; recall: 0.78). Brain regions that contributed to this classification accuracy were identified by adding noise to the voxel-level image data, which showed that reading disability classification accuracy was most influenced by the superior temporal sulcus, dorsal cingulate, and lateral occipital cortex. Regions that were most important for the accurate classification of controls included the supramarginal gyrus, orbitofrontal, and medial occipital cortex. The contribution of these regions reflected individual differences in reading-related abilities, such as non-word decoding or verbal comprehension. Together, the results demonstrate an optimal deep learning solution for classification using neuroimaging data. In contrast with standard mass-univariate test results, results from the deep learning model also provided evidence for regions that may be specifically affected in reading disability cases.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1053-8119
1095-9572
1095-9572
DOI:10.1016/j.neuroimage.2023.120075