Role of Deep Learning in Neurodevelopmental Disorders: A Narrative Review
Published: November 1, 2025 | DOI: https://doi.org/10.7860/JCDR/2025/80493.22050
Nilah Ans Chacko, Nimmi Puthan Veedu, Abhinav Panayan, Sayali Satish Chodankar
1. Student, Nitte (Deemed to be University), K.S. Hegde Medical Academy (KSHEMA), Department of Medical Imaging Technology, Mangaluru, Karnataka, India.
2. Lecturer/Radiographer, Sapthagiri Institute of Medical Sciences and Research, Department of Medical Imaging Technology, Mangaluru, Karnataka, India.
3. Student, Nitte (Deemed to be University), K.S. Hegde Medical Academy (KSHEMA), Department of Medical Imaging Technology, Mangaluru, Karnataka, India.
4. Lecturer/Clinical Supervisor, Nitte (Deemed to be University), Nitte Institute of Allied Health Sciences (NIAHS), Department of Medical Imaging Technology, Mangaluru, Karnataka, India.
Correspondence
Dr. Sayali Satish Chodankar,
Nitte (Deemed to be University), K.S. Hegde Medical Academy, Mangaluru, Karnataka, India.
E-mail: sayali.chodankar997@gmail.com
The application of Deep Learning (DL) techniques in paediatric neuroimaging marks a significant milestone in the field. Using various DL methods, this study aims to provide a review of how these techniques can improve the diagnostic process for different neurodevelopmental conditions, including Attention Deficit Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD). The subsequent discussion addresses the prominent DL approaches applicable to paediatric neuroimaging and describes the key datasets that serve as the foundation of scientific research in this area. Additionally, the study highlights the limitations and shortcomings of these techniques, along with potential directions for future research and opportunities for further development. The adoption of these advanced methods has the potential to significantly improve patient outcomes, enhance diagnostic accuracy, and advance our understanding of early brain development.
[
FULL TEXT ] | [ PDF]