Related Experiment Video
Updated: Jan 9, 2026
10:25
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
Published on: September 25, 2019
49.2K
Neural Mechanisms of Post-Stroke Anomic Aphasia: Insights from fMRI-Based Machine Learning Categorical Features
Summary
Anomic aphasia, a language disorder affecting naming, can be misdiagnosed. This study used neuroimaging and machine learning to accurately identify anomic aphasia, improving early diagnosis and intervention for patients.
Area of Science:
- Neuroimaging
- Machine Learning
- Neurology
Background:
- Anomic aphasia is a subtype of aphasia characterized by impaired naming, often leading to misdiagnosis due to mild symptoms.
- Early diagnosis and intervention are crucial for managing anomic aphasia and improving patient outcomes.
- Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive method to investigate brain activity patterns.
Purpose of the Study:
- To classify anomic aphasia using rs-fMRI data and machine learning.
- To differentiate anomic aphasia patients from post-stroke non-aphasic individuals.
- To explore the neural mechanisms associated with anomic aphasia.
Main Methods:
- rs-fMRI data from 95 subjects were analyzed using fractional amplitude of low-frequency fluctuations (fALFF), regional homogeneity (ReHo), and Laterality Index (LI).
- Machine learning classifiers, including Multilayer Perceptron (MLP), were trained and validated using imaging-derived features.
- Statistical analyses identified significant differences in brain activity between groups.
Main Results:
- Significant differences in brain activity were observed between anomic aphasia subjects and post-stroke non-aphasic subjects.
- The Multilayer Perceptron (MLP) classifier achieved a high accuracy of 94.74% in distinguishing between the two groups.
- Anomic aphasia was associated with increased rightward activation in the superior and inferior frontal gyri, and reduced activation in the inferior parietal lobule and superior temporal gyrus.
Conclusions:
- Automated methods combining neuroimaging and machine learning show promise for enhancing diagnostic efficiency in anomic aphasia.
- These techniques can aid clinicians in the early detection of anomic aphasia, facilitating timely intervention.
- Understanding the neural underpinnings of anomic aphasia is essential for developing targeted therapeutic strategies.
