INSIGHT: Combining Fixation Visualisations and Residual Neural Networks for Dyslexia Classification From Eye-Tracking Data
Jazyk angličtina Země Anglie, Velká Británie Médium print
Typ dokumentu časopisecké články
Grantová podpora
TL05000177
Technologická Agentura České Republiky
PubMed
39843401
PubMed Central
PMC11754147
DOI
10.1002/dys.1801
Knihovny.cz E-zdroje
- Klíčová slova
- AI‐based diagnosis, ResNet18, deep learning, dyslexia, eye movement, eye tracking, fixation data classification,
- MeSH
- čtení MeSH
- dítě MeSH
- dyslexie * patofyziologie diagnóza klasifikace MeSH
- lidé MeSH
- neuronové sítě (počítačové) * MeSH
- oční fixace * fyziologie MeSH
- pohyby očí fyziologie MeSH
- technologie sledování pohybu očí * MeSH
- Check Tag
- dítě MeSH
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
Current diagnostic methods for dyslexia primarily rely on traditional paper-and-pencil tasks. Advanced technological approaches, including eye-tracking and artificial intelligence (AI), offer enhanced diagnostic capabilities. In this paper, we bridge the gap between scientific and diagnostic concepts by proposing a novel dyslexia detection method, called INSIGHT, which combines a visualisation phase and a neural network-based classification phase. The first phase involves transforming eye-tracking fixation data into 2D visualisations called Fix-images, which clearly depict reading difficulties. The second phase utilises the ResNet18 convolutional neural network for classifying these images. The INSIGHT method was tested on 35 child participants (13 dyslexic and 22 control readers) using three text-reading tasks, achieving a highest accuracy of 86.65%. Additionally, we cross-tested the method on an independent dataset of Danish readers, confirming the robustness and generalizability of our approach with a notable accuracy of 86.11%. This innovative approach not only provides detailed insight into eye movement patterns when reading but also offers a robust framework for the early and accurate diagnosis of dyslexia, supporting the potential for more personalised and effective interventions.
Zobrazit více v PubMed
Asvestopoulou, T. , Manousaki V., Psistakis A., et al. 2019. “Towards a Robust and Accurate Screening Tool for Dyslexia With Data Augmentation Using GANs.” In 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 775–782. Athens, Greece: IEEE. 10.1109/BIBE.2019.00145. DOI
Bednářová, J. 2015. “Diagnostika schopností a dovedností v oblasti čtení a psaní. Varianta pro pedagogy škol a školní poradenská pracoviště, 3.—4. ročník. Pedagogickopsychologická poradna Brno.”
Bishop, C. M. 2006. Pattern Recognition and Machine Learning. Berlin, Heidelberg, Germany: Springer. 10.5555/1162264. DOI
Brodersen, K. H. , Ong C. S., Stephan K. E., and Buhmann J. M.. 2010. “The Balanced Accuracy and Its Posterior Distribution.” In 20th International Conference on Pattern Recognition, 3121–3124. Istanbul, Turkey: IEEE. 10.1109/ICPR.2010.764. DOI
Caravolas, M. , Mikulajová M., and Kucharská A.. 2019. “Developmental Dyslexia in Czech and Slovak.” In Developmental Dyslexia Across Languages and Writing Systems, edited by Verhoeven L., Perfetti C., and Pugh K., 96–117. Cambridge, UK: Cambridge University Press.
Dosovitskiy, A. , Beyer L., Kolesnikov A., et al. 2021. “An Image Is Worth 16 × 16 Words: Transformers for Image Recognition at Scale.” International Conference on Learning Representations (ICLR): 1–22. https://arxiv.org/pdf/2010.11929v2.pdf.
Gabrieli, J. D. E. 2009. “Dyslexia: A New Synergy Between Education and Cognitive Neuroscience.” Science 325: 280–283. 10.1126/science.1171999. PubMed DOI
Goodfellow, I. , Bengio Y., and Courville A.. 2016. Deep Learning. Cambridge, MA: MIT Press. https://www.deeplearningbook.org/.
Habib, M. 2000. “The Neurological Basis of Developmental Dyslexia: An Overview and Working Hypothesis.” Brain 123, no. 12: 2373–2399. 10.1093/brain/123.12.2373. PubMed DOI
He, K. , Zhang X., Ren S., and Sun J.. 2016. “Deep Residual Learning for Image Recognition.” In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. Las Vegas, USA: IEEE. 10.1109/CVPR.2016.90. DOI
Hollenstein, N. , Barrett M., and Björnsdóttir M.. 2022. “The Copenhagen Corpus of Eye Tracking Recordings From Natural Reading of Danish Texts.” In Proceedings of the Thirteenth Language Resources and Evaluation Conference, 1712–1720. Marseille, France: European Language Resources Association. https://aclanthology.org/2022.lrec‐1.182.
Holmqvist, K. , Nyström M., Andersson R., Dewhurst R., Jarodzka H., and van de Weijer J.. 2015. Eye Tracking: A Comprehensive Guide to Methods and Measures. Oxford, UK: Oxford Press.
Hutzler, F. , Kronbichler M., Jacobs A. M., and Wimmer H.. 2006. “Perhaps Correlational but Not Causal: No Effect of Dyslexic Readers' Magnocellular System on Their Eye Movements During Reading.” Neuropsychologia 44, no. 4: 637–648. 10.1016/j.neuropsychologia.2005.06.006. PubMed DOI
Hutzler, F. , and Wimmer H.. 2004. “Eye Movements of Dyslexic Children When Reading in a Regular Orthography.” Brain and Language 89: 235–242. 10.1016/S0093-934X(03)00401-2. PubMed DOI
Jothi Prabha, A. , and Bhargavi R.. 2020. “Predictive Model for Dyslexia From Fixations and Saccadic Eye Movement Events.” Computer Methods and Programs in Biomedicine 195: 1–13. 10.1016/j.cmpb.2020.105538. PubMed DOI
Jothi Prabha, A. , Bhargavi R., and Deepa Rani D. V.. 2023. “Prediction of Dyslexia Severity Levels From Fixation and Saccadic Eye Movement Using Machine Learning.” Biomedical Signal Processing and Control 79: 1–10. 10.1016/j.bspc.2022.104094. DOI
Kasprowski, P. 2024. “Utilizing Gaze Self Similarity Plots to Recognize Dyslexia When Reading.” In ETRA' 24: Proceedings of the 2024 Symposium on Eye Tracking Research and Applications, 1–5. Glasgow, United Kingdom: Association for Computing Machinery. 10.1145/3649902.3656494. DOI
Livingston, E. M. , Siegel L. S., and Ribary U.. 2018. “Developmental Dyslexia: Emotional Impact and Consequences.” Australian Journal of Learning Difficulties 23, no. 2: 107–135. 10.1080/19404158.2018.1479975. DOI
Lyon, G. R. , Shaywitz S. E., and Shaywitz B. A.. 2003. “A Definition of Dyslexia.” Annals of Dyslexia 53: 1–14. 10.1007/s11881-003-0001-9. DOI
Martinez‐Conde, S. 2006. “Fixational Eye Movements in Normal and Pathological Vision.” Progress in Brain Research 154: 151–176. 10.1016/s0079-6123(06)54008-7. PubMed DOI
Martinez‐Conde, S. , Macknik S. L., and Hubel D. H.. 2004. “The Role of Fixational Eye Movements in Visual Perception.” Nature Reviews Neuroscience 5, no. 3: 229–240. 10.1038/nrn1348. PubMed DOI
Nerušil, B. , Polec J., Škunda J., and Kačur J.. 2021. “Eye Tracking Based Dyslexia Detection Using a Holistic Approach.” Scientific Reports 11: 15687. 10.1038/s41598-021-95275-1. PubMed DOI PMC
Nicolson, R. I. , Fawcett A. J., and Dean P.. 2001. “Developmental Dyslexia: The Cerebellar Deficit Hypothesis.” Trends in Neurosciences 24, no. 9: 508–511. 10.1016/S0166-2236(00)01896-8. PubMed DOI
Nilsson Benfatto, M. , Öqvist Seimyr G., Ygge J., Pansell T., Rydberg A., and Jacobson C.. 2016. “Screening for Dyslexia Using Eye Tracking During Reading.” PLoS One 11, no. 12: e0165508. 10.1371/journal.pone.0165508. PubMed DOI PMC
Peterson, R. L. , and Pennington B. F.. 2012. “Developmental Dyslexia.” Lancet 379, no. 9830: 1997–2007. 10.1016/S0140-6736(12)60198-6. PubMed DOI PMC
Raatikainen, P. , Hautala J., Loberg O., Kärkkäinen T., Leppänen P., and Nieminen P.. 2021. “Detection of Developmental Dyslexia With Machine Learning Using Eye Movement Data.” Array 12: 100087. 10.1016/j.array.2021.100087. DOI
Ramus, F. 2001. “Outstanding Questions About Phonological Processing in Dyslexia.” Dyslexia 7: 197–216. 10.1002/dys.205. PubMed DOI
Rayner, K. 1998. “Eye Movements in Reading and Information Processing: 20 Years of Research.” Psychological Bulletin 124, no. 3: 372–422. 10.1037/0033-2909.124.3.372. PubMed DOI
Rello, L. , and Ballesteros M.. 2015. “Detecting Readers With Dyslexia Using Machine Learning With Eye Tracking Measures.” In W4A 2015—12th Web for all Conference. New York: Assocation for Computing Machinery. 10.1145/2745555.2746644. DOI
Rivero‐Contreras, M. , Engelhardt P. E., and Saldaña D.. 2021. “An Experimental Eye‐Tracking Study of Text Adaptation for Readers With Dyslexia: Effects of Visual Support and Word Frequency.” Annals of Dyslexia 71: 170–187. 10.1007/s11881-021-00217-1. PubMed DOI
Sakoe, H. , and Chiba S.. 1978. “Dynamic Programming Algorithm Optimization for Spoken Word Recognition.” IEEE Transactions on Acoustics, Speech, and Signal Processing 26, no. 1: 43–49. 10.1109/TASSP.1978.1163055. DOI
Sedmidubsky, J. , Dostalova N., Svaricek R., and Culemann W.. 2025. “ETDD70: Eye‐Tracking Dataset for Classification of Dyslexia Using AI‐Based Methods.” In Similarity Search and Applications. SISAP 2024. Lecture Notes in Computer Science, edited by Chávez E., Kimia B., Lokoč J., Patella M., and Sedmidubsky J., Vol. 15268. Cham: Springer. 10.1007/978-3-031-75823-2_3. DOI
Sedmidubsky, J. , P. Elias, Budikova P., and Zezula P.. 2021. “Content‐based Management of Human Motion Data: Survey and Challenges.” IEEE Access 9, 64241–64255. 10.1109/ACCESS.2021.3075766. DOI
Sedmidubsky, J. , and Zezula P.. 2021. “Efficient Combination of Classifiers for 3D Action Recognition.” Multimedia Systems 27, no. 5: 941–952. 10.1007/s00530-021-00767-9. DOI
Shaywitz, B. A. , Shaywitz S. E., Pugh K. R., et al. 2001. “The Neurobiology of Dyslexia.” Clinical Neuroscience Research 1, no. 4: 291–299. 10.1016/S1566-2772(01)00015-9. DOI
Smyrnakis, I. , Andreadakis V., Selimis V., et al. 2017. “RADAR: A Novel Fast‐Screening Method for Reading Difficulties With Special Focus on Dyslexia.” PLoS One 12, no. 8: e0182597. 10.1371/journal.pone.0182597. PubMed DOI PMC
Snowling, M. 1998. “Dyslexia as a Phonological Deficit: Evidence and Implications.” Child Psychology and Psychiatry Review 3: 4–11. 10.1111/1475-3588.00201. DOI
Stein, J. 2001. “The Magnocellular Theory of Developmental Dyslexia.” Dyslexia 7, no. 1: 12–36. 10.1002/dys.186. PubMed DOI
Trauzettel‐Klosinski, S. , Koitzsch A. M., Dürrwächter U., Sokolov A. N., Reinhard J., and Klosinski G.. 2010. “Eye Movements in German‐Speaking Children With and Without Dyslexia When Reading Aloud.” Acta Ophthalmologica 88: 681–691. 10.1111/j.1755-3768.2009.01523.x. PubMed DOI
Vajs, I. , Kovic V., Papic T., Savic A. M., and Jankovic M. M.. 2022. “Spatiotemporal Eye‐Tracking Feature Set for Improved Recognition of Dyslexic Reading Patterns in Children.” Sensors 22: 4900. 10.3390/s22134900. PubMed DOI PMC
Vellutino, F. R. , Fletcher J. M., Snowling M. J., and Scanlon D. M.. 2004. “Specific Reading Disability (Dyslexia): What Have We Learned in the Past Four Decades?” Journal of Child Psychology and Psychiatry 45: 2–40. 10.1046/j.0021-9630.2003.00305.x. PubMed DOI
Yang, L. , Li C., Li X., et al. 2022. “Prevalence of Developmental Dyslexia in Primary School Children: A Systematic Review and Meta‐Analysis.” Brain Sciences 12: 240. 10.3390/brainsci12020240. PubMed DOI PMC