Unified framework for early stage status prediction of autism based on infant structural magnetic resonance imaging.
A one-year-old brain scan can now forecast autism at age two better than older MRI tools.
01Research in Context
What this study did
Kun et al. (2021) built a computer tool that reads baby MRI scans. The tool looks at the shape and size of brain areas.
Doctors can run the scan when a child is one year old. The program then guesses if the child will meet autism criteria at age two.
What they found
The new tool beat older MRI methods. It caught more true cases and made fewer false alarms.
That means fewer babies missed and fewer families scared by wrong labels.
How this fits with other research
McGlade et al. (2023) looked at 12 trials where babies got early therapy. They found no clear gain in autism signs or IQ by age three. That sounds opposite, but it is not. Kun gives a heads-up; McGlade asks what to do with it.
Howe et al. (2016) also built an early warning model. They used motor scores and birth facts, not brain scans. Both papers show the same goal: spot delay sooner so help can start faster.
de Jonge et al. (2025) used EEG instead of MRI. They saw small network gaps in older kids with autism. Kun moves the lens younger and swaps wires for pictures.
Why it matters
You can not treat what you can not see. A 12-month MRI flag gives families a year jump on planning. Pair the scan with your own early red-flag checklists. If risk looks high, start low-stress teaching at home while the family waits for full diagnosis. The scan is not ready for every clinic yet, but the idea is clear: earlier warning buys calmer, cheaper, and kinder next steps.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Add a quick parent question about MRI referral to your 12-15 month intake form.
02At a glance
03Original abstract
Autism, or autism spectrum disorder (ASD), is a developmental disability that is diagnosed at about 2 years of age based on abnormal behaviors. Existing neuroimaging-based methods for the prediction of ASD typically focus on functional magnetic resonance imaging (fMRI); however, most of these fMRI-based studies include subjects older than 5 years of age. Due to challenges in the application of fMRI for infants, structural magnetic resonance imaging (sMRI) has increasingly received attention in the field for early status prediction of ASD. In this study, we propose an automated prediction framework based on infant sMRI at about 24 months of age. Specifically, by leveraging an infant-dedicated pipeline, iBEAT V2.0 Cloud, we derived segmentation and parcellation maps from infant sMRI. We employed a convolutional neural network to extract features from pairwise maps and a Siamese network to distinguish whether paired subjects were from the same or different classes. As compared to T1w imaging without segmentation and parcellation maps, our proposed approach with segmentation and parcellation maps yielded greater sensitivity, specificity, and accuracy of ASD prediction, which was validated using two datasets with different imaging protocols/scanners and was confirmed by receiver operating characteristic analysis. Furthermore, comparison with state-of-the-art methods demonstrated the superior effectiveness and robustness of the proposed method. Finally, attention maps were generated to identify subject-specific autism effects, supporting the reasonability of the predictive results. Collectively, these findings demonstrate the utility of our unified framework for the early-stage status prediction of ASD by sMRI. LAY SUMMARY: The status prediction of autism spectrum disorder (ASD) at an early age is highly desirable, as early intervention may significantly reduce autism symptoms. However, current methods for diagnosing young children are limited to behavioral assays. In this study, we propose an automated method for ASD status prediction at the age of 24 months that uses infant structural magnetic resonance imaging to identify neural features.
Autism research : official journal of the International Society for Autism Research, 2021 · doi:10.1109/TMI.2016.2582386