CoChat

Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging

Open access
Zahia, Sofia, Garcia-Zapirain, Begonya, Saralegui, Ibone, Fernandez-Ruanova, Begoña · 2020 · Computer Methods and Programs in Biomedicine
Cited by 67

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Abstract

BACKGROUND AND OBJECTIVES: Dyslexia is a disorder of neurological origin which affects the learning of those who suffer from it, mainly children, and causes difficulty in reading and writing. When undiagnosed, dyslexia leads to intimidation and frustration of the affected children and also of their family circles. In case no early intervention is given, children may reach high school with serious achievement gaps. Hence, early detection and intervention services for dyslexic students are highly important and recommended in order to support children in developing a positive self-esteem and reaching their maximum academic capacities. This paper presents a new approach for automatic recognition of children with dyslexia using functional magnetic resonance Imaging. METHODS: Our proposed system is composed of a sequence of preprocessing steps to retrieve the brain activation areas during three different reading tasks. Conversion to Nifti volumes, adjustment of head motion, normalization and smoothing transformations were performed on the fMRI scans in order to bring all the subject brains into one single model which will enable voxels comparison between each subject. Subsequently, using Statistical Parametric Maps (SPMs), a total of 165 3D volumes containing brain activation of 55 children were created. The classification of these volumes was handled using three parallel 3D Convolutional Neural Network (3D CNN), each corresponding to a brain activation during one reading task, and concatenated in the last two dense layers, forming a single architecture devoted to performing optimized detection of dyslexic brain activation. Additionally, we used 4-fold cross validation method in order to assess the generalizability of our model and control overfitting. RESULTS: Our approach has achieved an overall average classification accuracy of 72.73%, sensitivity of 75%, specificity of 71.43%, precision of 60% and an F1-score of 67% in dyslexia detection. CONCLUSIONS: The proposed system has demonstrated that the recognition of dyslexic children is feasible using deep learning and functional magnetic resonance Imaging when performing phonological and orthographic reading tasks.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.cmpb.2020.105726

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 7 references

Research works printed but not linked: 43

  1. Handler, 2011, Section on ophthalmology, council on children with disabilities, american academy of ophthalmology, american association for pediatric ophthalmology and strabismus, American Association of Certified Orthoptists, 2010
  2. Hodgetts, 1998, Normal reading despite limited eye movements, J. AAPOS, 2, 182, 10.1016/S1091-8531(98)90011-8 · doi:10.1016/s1091-8531(98)90011-8
  3. Galaburda, 1985, Developmental dyslexia: four consecutive patients with cortical anomalies, Ann. Neurol., 18, 222, 10.1002/ana.410180210 · DOI · Paper page
  4. Snowling, 2011, Evidence-based interventions for reading and language difficulties: Creating a virtuous circle, Br. J. Educ. Psychol., 81, 1, 10.1111/j.2044-8279.2010.02014.x · DOI · Paper page
  5. Nicolson, 2001, Dyslexia development and the cerebellum, Trends Neurosci., 24, 508, 10.1016/S0166-2236(00)01896-8 · DOI · Paper page
  6. Roach, 2004, Attentional modulation of visual processing in adult dyslexia a spatial-cuing deficit, Psychol. Sci., 15, 650, 10.1111/j.0956-7976.2004.00735.x · DOI
  7. Facoetti, 2006, The relationship between visuo-spatial attention and non word reading in developmental dyslexia, Cognit. Neuropsychol., 23, 841, 10.1080/02643290500483090 · DOI · Paper page
  8. Bosse, 2007, Developmental dyslexia: the visual attentions pan deficit hypothesis, Cognition, 104, 198, 10.1016/j.cognition.2006.05.009 · DOI · Paper page
  9. Lobier, 2012, The visual attention span deficit in dyslexia is visual and not verbal, Cortex, 48, 768, 10.1016/j.cortex.2011.09.003 · DOI · Paper page
  10. Wang, 2019, Structural and functional abnormality of the putamen in children with developmental dyslexia, Neuropsychologia, 130, 26, 10.1016/j.neuropsychologia.2018.07.014 · DOI
  11. Livingstone, 1991, Physiological and anatomical evidence fora magnocellular defect in developmental dyslexia, Proc. Natl. Acad. Sci. USA, 88, 7943, 10.1073/pnas.88.18.7943 · DOI · Paper page
  12. Stein, 1997, To see but not to read ; the magnocellular theory of dyslexia, Trends Neurosci., 20, 147, 10.1016/S0166-2236(96)01005-3 · DOI · Paper page
  13. Vidyasagar, 2009, Dyslexia: a deficit in visuo-spatial attention,not in phonological processing, Trends Cognit. Sci., 14, 57, 10.1016/j.tics.2009.12.003 · DOI · Paper page
  14. Saralegui, 2014, Reading networks in children with dyslexia compared to children with ocular motility disturbances revealed by fMRI, Front. Hum. Neurosci., 8, 936, 10.3389/fnhum.2014.00936 · DOI
  15. A. Payan, G. Montana, Predicting alzheimer’s disease: a neuroimaging study with 3d convolutional neural networks, 2015, arXiv preprint: 1502.02506 · arXiv
  16. E. Hosseini-Asl, G. Gimel’farb, A. El-Baz, Alzheimer’s dis- ease diagnostics by a deeply supervised adaptable 3d convolutional network, 2016, arXiv preprint: 1607.00556 · arXiv
  17. Choi, 2016, Fast and robust segmentation of the striatum using deep convolutional neural networks, Journal of Neuro- science Methods, 274, 146
  18. Ghafoorian, 2017, Deep multi-scale location- aware 3d convolutional neural networks for automated detection of lacunes of presumed vascular origin, NeuroImage: Clinical, 10.1016/j.nicl.2017.01.033 · DOI · Paper page
  19. Bahrami, 2016, Convolutional neural network for reconstruction of 7t-like images from 3t MRI using appearance and anatomical features, 39, 10.1007/978-3-319-46976-8_5 · DOI
  20. Ashish, 2012, Scikit-learn: machine learning in python, J. Mach. Learn. Res., 12, 2825
  21. Chougrad, 2018, Deep convolutional neural networks for breast cancer screening, Comput. Methods Programs Biomed., 157, 19, 10.1016/j.cmpb.2018.01.011 · DOI · Paper page
  22. Al-masni, 2018, Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system, Computer methods and programs in biomedicine, 157, 85, 10.1016/j.cmpb.2018.01.017 · DOI · Paper page
  23. Zhu, 2019, Deep learning for identifying radiogenomic associations in breast cancer, Comput. Biol. Med., 109, 85, 10.1016/j.compbiomed.2019.04.018 · DOI · Paper page
  24. Hu, 2019, Automatic segmentation of left ventricle from cardiac MRI via deep learning and region constrained dynamic programming, Neurocomputing, 347, 139, 10.1016/j.neucom.2019.02.008 · DOI
  25. Avendi, 2016, A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI, Med. Image Anal., 30, 108, 10.1016/j.media.2016.01.005 · DOI · Paper page
  26. Al-Masni, 2018, Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks, Comput. Methods Programs Biomed., 162, 221, 10.1016/j.cmpb.2018.05.027 · DOI · Paper page
  27. Zahia, 2018, Tissue classification and segmentation of pressure injuries using convolutional neural networks, Comput. Methods Programs Biomed., 159, 51, 10.1016/j.cmpb.2018.02.018 · DOI
  28. Burlina, 2019, Automated detection of erythema migrans and other confounding skin lesions via deep learning, Comput. Biol. Med., 105, 151, 10.1016/j.compbiomed.2018.12.007 · DOI
  29. Jednoróg, 2014, Cognitive subtypes of dyslexia are characterized by distinct patterns of grey matter volume, Brain Struct. Funct., 219, 1697, 10.1007/s00429-013-0595-6 · DOI
  30. Penny, 2003, Variational Bayesian inference for fMRI time series, NeuroImage, 19, 727, 10.1016/S1053-8119(03)00071-5 · DOI · Paper page
  31. Qureshi, 2019, Evaluation of functional decline in Alzheimer’s dementia using 3d deep learning and group ICA for rs-fMRI measurements, Front. Aging Neurosci., 11, 10.3389/fnagi.2019.00008 · DOI
  32. Khosla, 2019, Ensemble learning with 3d convolutional neural networks for functional connectome-based prediction, NeuroImage, 10.1016/j.neuroimage.2019.06.012 · DOI · Paper page
  33. Gao, 2017, Classification of CT brain images based on deep learning networks, Comput. Methods Programs Biomed., 138, 49, 10.1016/j.cmpb.2016.10.007 · DOI · Paper page
  34. Zou, 2017, 3d CNN based automatic diagnosis of attention deficit hyperactivity disorder using functional and structural MRI, IEEE Access, 5, 23626, 10.1109/ACCESS.2017.2762703 · DOI · Paper page
  35. Sarikaya, 2017, Detection and localization of robotic tools in robot-assisted surgery videos using deep neural networks for region proposal and detection, IEEE Trans. Med. Imaging, 36, 1542, 10.1109/TMI.2017.2665671 · DOI · Paper page
  36. Han, 2014, Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning, IEEE Trans. Geosci. Remote Sens., 53, 3325, 10.1109/TGRS.2014.2374218 · DOI · Paper page
  37. Al-Masni, 2018, Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks, Comput. Methods Programs Biomed., 162, 221, 10.1016/j.cmpb.2018.05.027 · DOI · Paper page
  38. Dolz, 2018, 3d fully convolutional networks for subcortical segmentation in MRI: a large-scale study, NeuroImage, 170, 456, 10.1016/j.neuroimage.2017.04.039 · DOI · Paper page
  39. Gu, 2018, Automatic lung nodule detection using a 3d deep convolutional neural network combined with a multi-scale prediction strategy in chest CTs, Comput. Biol. Med., 103, 220, 10.1016/j.compbiomed.2018.10.011 · DOI · Paper page
  40. Jiang, 2019, Attentive and ensemble 3d dual path networks for pulmonary nodules classification, Neurocomputing
  41. Qureshi, 2019, 3d-CNN based discrimination of schizophrenia using resting-state fMRI, Artif. Intell. Med., 10.1016/j.artmed.2019.06.003 · DOI · Paper page
  42. Oh, 2019, Classification of schizophrenia and normal controls using 3d convolutional neural network and outcome visualization, Schizophrenia Res., 212, 186, 10.1016/j.schres.2019.07.034 · DOI · Paper page
  43. Tamboer, 2016, Machine learning and dyslexia: Classification of individual structural neuro-imaging scans of students with and without dyslexia, NeuroImage, 11, 508, 10.1016/j.nicl.2016.03.014 · DOI

Cited by

See all 67

Metadata

Authors
Zahia, S., Garcia-Zapirain, B., Saralegui, I., & Fernandez-Ruanova, B.
Venue
Computer Methods and Programs in Biomedicine
Publisher
Elsevier BV
Published
2020-12
Volume
197
Pages
105726
ISSN
0169-2607 (ISSN-L)
OpenAlex
W3080168576
Cited by
67
References
7
FWCI
12.61
Type
journal article
Language
en
Open access
hybrid
Licence
Funders
Eusko Jaurlaritza

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging. https://app.cochat.ai/papers/10.1016/j.cmpb.2020.105726
The paper
Zahia, S., Garcia-Zapirain, B., Saralegui, I., & Fernandez-Ruanova, B. (2020). Dyslexia detection using 3D convolutional neural networks and functional magnetic resonance imaging. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2020.105726

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.