Related Experiment Video
Updated: Jun 13, 2025
The Use of Trace Eyeblink Classical Conditioning to Assess Hippocampal Dysfunction in a Rat Model of Fetal Alcohol Spectrum Disorders
Published on: August 5, 2017
Deep learning for detecting prenatal alcohol exposure in pediatric brain MRI: a transfer learning approach with
Anik Das1, Kaue Duarte2, Catherine Lebel2,3
1Department of Biomedical Engineering, University of Calgary, Calgary, AB, Canada.
Insights
Deep learning effectively detects prenatal alcohol exposure (PAE) in young children using brain MRI scans. This approach shows promise for identifying PAE
Area of Science:
- Neuroscience
- Medical Imaging
- Artificial Intelligence
Background:
- Prenatal alcohol exposure (PAE) can cause lifelong learning and behavioral issues.
- Understanding PAE's impact on the developing brain is complex.
- Machine learning (ML) and deep learning (DL) offer novel approaches to study PAE.
Purpose of the Study:
- To apply DL for detecting PAE in pediatric brain MRI scans.
- To utilize transfer learning with a pre-trained Simple Fully Convolutional Network (SFCN).
- To distinguish between exposed and unexposed pediatric participants aged 2-8 years.
Main Methods:
- Employed transfer learning using a pre-trained SFCN for feature extraction.
- Trained a classifier to differentiate PAE from controls using T1-weighted structural MRI.
- Investigated dataset balancing and augmentation strategies.
- Performed explainability analysis using Grad-CAM.
Main Results:
- Achieved 88.47% sensitivity and 85.04% average accuracy with a balanced, augmented dataset.
- Identified key brain regions (corpus callosum, cerebellum, pons, white matter) influencing predictions.
- Demonstrated the potential of transfer learning with limited pediatric data.
Conclusions:
- DL, particularly transfer learning, shows significant potential for PAE detection in children.
- Balanced datasets and explainability are crucial for reliable and interpretable AI models in pediatric neuroscience.
- This study highlights a viable method for identifying PAE's neurobiological impact in early development.
Abstract:
Prenatal alcohol exposure (PAE) refers to the exposure of the developing fetus due to alcohol consumption during pregnancy and can have life-long consequences for learning, behavior, and health. Understanding the impact of PAE on the developing brain manifests challenges due to its complex structural and functional attributes, which can be addressed by leveraging machine learning (ML) and deep learning (DL) approaches. While most ML and DL models have been tailored for adult-centric problems, this work focuses on applying DL to detect PAE in the pediatric population. This study integrates the pre-trained simple fully convolutional network (SFCN) as a transfer learning approach for extracting features and a newly trained classifier to distinguish between unexposed and PAE participants based on T1-weighted structural brain magnetic resonance (MR) scans of individuals aged 2-8 years. Among several varying dataset sizes and augmentation strategy during training, the classifier secured the highest sensitivity of 88.47% with 85.04% average accuracy on testing data when considering a balanced dataset with augmentation for both classes. Moreover, we also preliminarily performed explainability analysis using the Grad-CAM method, highlighting various brain regions such as corpus callosum, cerebellum, pons, and white matter as the most important features in the model's decision-making process. Despite the challenges of constructing DL models for pediatric populations due to the brain's rapid development, motion artifacts, and insufficient data, this work highlights the potential of transfer learning in situations where data is limited. Furthermore, this study underscores the importance of preserving a balanced dataset for fair classification and clarifying the rationale behind the model's prediction using explainability analysis.
