Adaptive AI Approach to Pediatric fMRI Network Mapping
Poster No:
1900
Submission Type:
Abstract Submission
Authors:
Akshay Kumaar1, Sachin Patalasingh1, Malvika Ganesh1, Radha Kumari1, Rimjhim Agrawal1
Institutions:
1BrainsightAI, Bengaluru, Karnataka
First Author:
Co-Author(s):
Introduction:
Resting-state functional MRI (rs-fMRI) provides valuable insights into intrinsic brain functional organization. However, in paediatric cases, developmental changes present challenges such as differences in head size, grey-white matter distribution, and myelination, rendering adult templates unsuitable for analyses. This complicates clinical problem-solving, hampering the understanding and treatment of neurodevelopmental disorders and conditions like epileptic lesions or brain tumours. This study introduces a novel adaptive pipeline for mapping brain networks in paediatric rs-fMRI for effective clinical management and understanding paediatric brain function.
Methods:
The raw resting-state functional MRI (N=50) underwent canonical reorientation, motion artefact correction, despiking, skull stripping, anatomical coregistration, and denoising. Normalisation was then applied using a paediatric MRI template. Resting state networks were extracted via Independent Component Analysis (ICA), with the best-fit ICA selected using a self-supervised neural network pretrained on adult networks and fine-tuned for paediatric data (N=10).
·Pre-Training and Fine-Tuning of Neural Network
Results:
Leveraging the proposed framework, the Visual, Sensorimotor, Language, and Default Mode networks were mapped successfully using paediatric rs-fMRI. The fine-tuned neural network achieved an accuracy of ~96% in identifying the networks from the independent components of paediatric data post ICA.
·Functional Networks of a Paediatric Subject
Conclusions:
In conclusion, this study introduces an innovative adaptable pipeline and proves the efficacy in mapping functional brain networks in paediatric rs-fMRI, marking a significant advancement in paediatric neuroimaging. Further refinement and validation of this pipeline may extend its utility to extract additional resting state networks. This study holds great potential for improving our comprehension of neurodevelopmental disorders and guiding treatment approaches for paediatric neurological conditions.
Disorders of the Nervous System:
Neurodevelopmental/ Early Life (eg. ADHD, autism) 2
Novel Imaging Acquisition Methods:
BOLD fMRI 1
Keywords:
Cognition
Data analysis
Development
FUNCTIONAL MRI
Informatics
Language
Machine Learning
PEDIATRIC
Statistical Methods
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
Provide references using APA citation style.
Bernal, B. (2021). Resting-state fMRI: Canonical networks in normal children. International Journal of Radiology Sciences, 3(1), 22–29
ozais, V., Boutinaud, P., Verrecchia, V., Gueye, M. F., Hervé, P. Y., Tzourio, C., Mazoyer, B., & Joliot, M. (2021). Deep learning-based classification of resting-state fMRI independent-component analysis. Neuroinformatics, 19, 619–637.