Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classification

IntroductionAristotle illusion is a well-known tactile illusion which causes the perception of one object as two. EEG analysis was employed to investigate the neural correlates of Aristotle illusion, yet was limited due to low spatial resolution of EEG. This study aimed to identify brain regions inv...

Full description

Saved in:
Bibliographic Details
Main Authors: Eunji Lee, Ji-Hyun Kim, Jaeseok Park, Sung-Phil Kim, Taehoon Shin
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnins.2025.1606801/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850210060494438400
author Eunji Lee
Eunji Lee
Ji-Hyun Kim
Jaeseok Park
Jaeseok Park
Sung-Phil Kim
Taehoon Shin
Taehoon Shin
Taehoon Shin
author_facet Eunji Lee
Eunji Lee
Ji-Hyun Kim
Jaeseok Park
Jaeseok Park
Sung-Phil Kim
Taehoon Shin
Taehoon Shin
Taehoon Shin
author_sort Eunji Lee
collection DOAJ
description IntroductionAristotle illusion is a well-known tactile illusion which causes the perception of one object as two. EEG analysis was employed to investigate the neural correlates of Aristotle illusion, yet was limited due to low spatial resolution of EEG. This study aimed to identify brain regions involved in the Aristotle illusion using functional magnetic resonance imaging (fMRI) and deep learning-based analysis of fMRI data.MethodsWhile three types of tactile stimuli (Aristotle, Reverse, Asynchronous) were applied to thirty participants’ fingers, we collected fMRI data, and recorded the number of stimuli each participant perceived. Four convolutional neural network (CNN) models were trained for perception-based classification tasks (the occurrence of Aristotle illusion vs. Reverse illusion, the occurrence vs. absence of Reverse illusion), and stimulus-based classification tasks (Aristotle vs. Reverse, Reverse vs. Asynchronous, and Aristotle vs. Asynchronous).ResultsSimple fully convolution network (SFCN) achieved the highest classification accuracy of 68.4% for the occurrence of Aristotle illusion vs. Reverse illusion, and 80.1% for the occurrence vs. absence of Reverse illusion. For stimulus-based classification tasks, all CNN models yielded accuracies around 50% failing to distinguish among the three types of applied stimuli. Gradient-weighted class activation mapping (Grad-CAM) analysis revealed salient brain regions-of-interest (ROIs) for the perception-based classification tasks, including the somatosensory cortex and parietal regions.DiscussionOur findings demonstrate that perception-driven neural responses are classifiable using fMRI-based CNN models. Saliency analysis of the trained CNNs reveals the involvement of the somatosensory cortex and parietal regions in making classification decisions, consistent with previous research. Other salient ROIs include orbitofrontal cortex, middle temporal pole, supplementary motor area, and middle cingulate cortex.
format Article
id doaj-art-b2cc5ee365014048b4de82f83f93ca38
institution OA Journals
issn 1662-453X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neuroscience
spelling doaj-art-b2cc5ee365014048b4de82f83f93ca382025-08-20T02:09:51ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2025-06-011910.3389/fnins.2025.16068011606801Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classificationEunji Lee0Eunji Lee1Ji-Hyun Kim2Jaeseok Park3Jaeseok Park4Sung-Phil Kim5Taehoon Shin6Taehoon Shin7Taehoon Shin8Department of Mechanical and Biomedical Engineering, Ewha W. University, Seoul, Republic of KoreaGraduate Program in Smart Factory, Ewha W. University, Seoul, Republic of KoreaDepartment of Cognitive and Psychological Sciences, Brown University, Providence, RI, United StatesDepartment of Biomedical Engineering, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Intelligent Precision Healthcare Convergence, Sungkyunkwan University, Suwon, Republic of KoreaDepartment of Biomedical Engineering, Ulsan National Institute of Science and Technology, Ulsan, Republic of KoreaDepartment of Mechanical and Biomedical Engineering, Ewha W. University, Seoul, Republic of KoreaGraduate Program in Smart Factory, Ewha W. University, Seoul, Republic of KoreaDepartment of Artificial Intelligence and Software, Ewha W. University, Seoul, Republic of KoreaIntroductionAristotle illusion is a well-known tactile illusion which causes the perception of one object as two. EEG analysis was employed to investigate the neural correlates of Aristotle illusion, yet was limited due to low spatial resolution of EEG. This study aimed to identify brain regions involved in the Aristotle illusion using functional magnetic resonance imaging (fMRI) and deep learning-based analysis of fMRI data.MethodsWhile three types of tactile stimuli (Aristotle, Reverse, Asynchronous) were applied to thirty participants’ fingers, we collected fMRI data, and recorded the number of stimuli each participant perceived. Four convolutional neural network (CNN) models were trained for perception-based classification tasks (the occurrence of Aristotle illusion vs. Reverse illusion, the occurrence vs. absence of Reverse illusion), and stimulus-based classification tasks (Aristotle vs. Reverse, Reverse vs. Asynchronous, and Aristotle vs. Asynchronous).ResultsSimple fully convolution network (SFCN) achieved the highest classification accuracy of 68.4% for the occurrence of Aristotle illusion vs. Reverse illusion, and 80.1% for the occurrence vs. absence of Reverse illusion. For stimulus-based classification tasks, all CNN models yielded accuracies around 50% failing to distinguish among the three types of applied stimuli. Gradient-weighted class activation mapping (Grad-CAM) analysis revealed salient brain regions-of-interest (ROIs) for the perception-based classification tasks, including the somatosensory cortex and parietal regions.DiscussionOur findings demonstrate that perception-driven neural responses are classifiable using fMRI-based CNN models. Saliency analysis of the trained CNNs reveals the involvement of the somatosensory cortex and parietal regions in making classification decisions, consistent with previous research. Other salient ROIs include orbitofrontal cortex, middle temporal pole, supplementary motor area, and middle cingulate cortex.https://www.frontiersin.org/articles/10.3389/fnins.2025.1606801/fullsomatosensorytactile illusionfMRIdeep learningbrain mapping
spellingShingle Eunji Lee
Eunji Lee
Ji-Hyun Kim
Jaeseok Park
Jaeseok Park
Sung-Phil Kim
Taehoon Shin
Taehoon Shin
Taehoon Shin
Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classification
Frontiers in Neuroscience
somatosensory
tactile illusion
fMRI
deep learning
brain mapping
title Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classification
title_full Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classification
title_fullStr Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classification
title_full_unstemmed Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classification
title_short Neural decoding of Aristotle tactile illusion using deep learning-based fMRI classification
title_sort neural decoding of aristotle tactile illusion using deep learning based fmri classification
topic somatosensory
tactile illusion
fMRI
deep learning
brain mapping
url https://www.frontiersin.org/articles/10.3389/fnins.2025.1606801/full
work_keys_str_mv AT eunjilee neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT eunjilee neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT jihyunkim neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT jaeseokpark neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT jaeseokpark neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT sungphilkim neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT taehoonshin neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT taehoonshin neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification
AT taehoonshin neuraldecodingofaristotletactileillusionusingdeeplearningbasedfmriclassification