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

## TL;DR

This study uses fMRI and deep learning to identify brain regions involved in the Aristotle tactile illusion, showing that perception-based classifications can be made with reasonable accuracy.

## Contribution

The novel use of deep learning-based fMRI classification to decode the neural correlates of tactile illusions, specifically the Aristotle illusion.

## Key findings

- A CNN model achieved 68.4% accuracy in classifying the occurrence of Aristotle illusion versus Reverse illusion.
- Grad-CAM analysis identified somatosensory cortex and parietal regions as salient for perception-based classification.
- Stimulus-based classification tasks showed CNN models with accuracies around 50%, indicating difficulty in distinguishing tactile stimuli types.

## Abstract

Aristotle 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.

While 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).

Simple 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.

Our 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.