Related Experiment Video
Updated: May 21, 2025
State of the Art Cranial Ultrasound Imaging in Neonates
Published on: February 2, 2015
Graph-based prototype inverse-projection for identifying cortical sulcal pattern abnormalities in congenital heart
Hyeokjin Kwon1, Seungyeon Son2, Sarah U Morton3
1Department of Electronic Engineering, Hanyang University, Seoul, South Korea; Fetal Neonatal Neuroimaging and Developmental Science Center, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA; Division of Newborn Medicine, Boston Children's Hospital, Boston, MA, USA; Department of Pediatrics, Harvard Medical School, Boston, MA, USA.
A novel deep learning method analyzes brain sulcal patterns for neurodevelopmental insights. This approach improves classification accuracy for psychiatric and neurological disorders, offering a more sensitive and interpretable tool.
Area of Science:
- Neuroscience
- Artificial Intelligence
- Medical Imaging
Background:
- Altered brain sulcal patterns are linked to neurodevelopmental differences in psychiatric and neurological disorders.
- Previous sulcal pattern analysis methods, like spectral graph matching, face challenges including lack of standardization and computational cost.
Purpose of the Study:
- To develop a deep learning-based sulcal pattern analysis method to overcome limitations of existing techniques.
- To improve the interpretability and efficiency of sulcal pattern analysis for identifying neurodevelopmental differences.
Main Methods:
- Adapted prototype-based graph neural networks for sulcal pattern graphs.
- Introduced a prototype inverse-projection technique for enhanced visualization and selective region focus.
- Evaluated the method on a classification task distinguishing healthy controls from patients with congenital heart disease using multiple datasets.
Main Results:
- The deep learning approach demonstrated superior classification performance compared to state-of-the-art models.
- Ablative studies confirmed the effectiveness of the proposed method.
- Learned prototypes were visualized and examined, enhancing the understanding of sulcal pattern variations.
Conclusions:
- The developed deep learning method offers a sensitive and understandable tool for sulcal pattern analysis.
- This approach has the potential to advance the study of neurodevelopmental differences in various disorders.
