Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer

Mayes, Linda C.; Pollatou, Angeliki; Dufford, Alexander J.; Jiang, Rongtao; Farruggia, Michael C.; Rosenblatt, Matthew; Peterson, Hannah; Rodriguez, Raimundo X.; Dadashkarimi, Javid; Liang, Qinghao; Dai, Wei; Foster, Maya L.; Camp, Christopher C.; Tejavibulya, Link; Adkinson, Brendan; Sun, Huili; Ye, Jean; Cheng, Qi; Spann, Marisa; Rolison, Max; Noble, Stephanie; Westwater, Margaret L.

doi:10.1016/j.biopsych.2022.10.014

Cited by 10 publications

(6 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A single model will not be appropriate in all cases. For example, models designed for adults likely should not work on infants and young children (Scheinost et al, 2023).…”

Section: Discussionmentioning

confidence: 99%

“…A single model will not be appropriate in all cases. For example, models designed for adults likely should not work on infants and young children (Scheinost et al, 2023). Many brain-behavior associations may exhibit sex differences, where sex-specific models could be needed (Dhamala et al, 2023; Greene et al, 2018; Jiang et al, 2020; Yip et al, 2023).…”

Section: Discussionmentioning

confidence: 99%

“…However, the observed effect sizes are still smaller than necessary for real-world utility. Further, even if our models were actionable, ethical concerns related to their implementation in developmental populations exist (Scheinost et al, 2023). For example, false positives lead to unnecessary interventions, while false negatives divert resources from those who need them.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Brain-phenotype predictions can survive across diverse real-world data

Adkinson,

Rosenblatt,

Dadashkarimi

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Recent work suggests that machine learning models predicting psychiatric treatment outcomes based on clinical data may fail when applied to unharmonized samples. Neuroimaging predictive models offer the opportunity to incorporate neurobiological information, which may be more robust to dataset shifts. Yet, among the minority of neuroimaging studies that undertake any form of external validation, there is a notable lack of attention to generalization across dataset-specific idiosyncrasies. Research settings, by design, remove the between-site variations that real-world and, eventually, clinical applications demand. Here, we rigorously test the ability of a range of predictive models to generalize across three diverse, unharmonized samples: the Philadelphia Neurodevelopmental Cohort (n=1291), the Healthy Brain Network (n=1110), and the Human Connectome Project in Development (n=428). These datasets have high inter-dataset heterogeneity, encompassing substantial variations in age distribution, sex, racial and ethnic minority representation, recruitment geography, clinical symptom burdens, fMRI tasks, sequences, and behavioral measures. We demonstrate that reproducible and generalizable brain-behavior associations can be realized across diverse dataset features with sample sizes in the hundreds. Results indicate the potential of functional connectivity-based predictive models to be robust despite substantial inter-dataset variability. Notably, for the HCPD and HBN datasets, the best predictions were not from training and testing in the same dataset (i.e., cross-validation) but across datasets. This result suggests that training on diverse data may improve prediction in specific cases. Overall, this work provides a critical foundation for future work evaluating the generalizability of neuroimaging predictive models in real-world scenarios and clinical settings.

show abstract

“…A single model will not be appropriate in all cases. For example, models designed for adults likely should not work on infants and young children (Scheinost et al, 2023).…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Brain-phenotype predictions can survive across diverse real-world data

Adkinson,

Rosenblatt,

Dadashkarimi

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A hope for infant neuroimaging studies is to predict the risk for poor developmental outcomes in toddlerhood or later 50 . We found that BAGs are associated with several toddler outcomes.…”

Section: Discussionmentioning

confidence: 99%

Brain age prediction and deviations from normative trajectories in the neonatal connectome

Sun,

Mehta,

Khaitova

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Structural and functional connectomes undergo rapid changes during the third trimester and the first month of postnatal life. Despite progress, our understanding of the developmental trajectories of the connectome in the perinatal period remains incomplete. Brain age prediction uses machine learning to estimate the brain's maturity relative to normative data. The difference between the individual's predicted and chronological age, or brain age gap (BAG),represents the deviation from these normative trajectories. Here, we assess brain age prediction and BAGs using structural and functional connectomes for infants in the first month of life. We used resting-state fMRI and DTI data from 611 infants (174 preterm; 437 term) from the Developing Human Connectome Project (dHCP) and connectome-based predictive modeling to predict postmenstrual age (PMA). Structural and functional connectomes accurately predicted PMA for term and preterm infants. Predicted ages from each modality were correlated. At the network level, nearly all canonical brain networks, even putatively later developing ones, generated accurate PMA prediction. Additionally, BAGs were associated with perinatal exposures and toddler behavioral outcomes. Overall, our results underscore the importance of normative modeling and deviations from these models during the perinatal period.

show abstract

“…For neonates, brain MRI is particularly important for assessment of patients with neonatal encephalopathy, where both the presence and pattern of brain injury can assist prognostication and treatment planning 2 – 7 . Advances in artificial intelligence (AI) and machine learning (ML) have allowed accurate prediction of functional outcomes in infants using MRI data 8 – 11 taking advantage of the imaging information beyond what is reasonably utilized by human visual inspection alone. Image preprocessing is an essential step in standardizing data inputs for AI/ML algorithms, and ensures faster, more robust data processing while minimizing potential confounding features 12 – 18 .…”

Section: Introductionmentioning

confidence: 99%

Automated neonatal nnU-Net brain MRI extractor trained on a large multi-institutional dataset

Chen,

Li,

Tang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Brain extraction, or skull-stripping, is an essential data preprocessing step for machine learning approaches to brain MRI analysis. Currently, there are limited extraction algorithms for the neonatal brain. We aim to adapt an established deep learning algorithm for the automatic segmentation of neonatal brains from MRI, trained on a large multi-institutional dataset for improved generalizability across image acquisition parameters. Our model, ANUBEX (automated neonatal nnU-Net brain MRI extractor), was designed using nnU-Net and was trained on a subset of participants (N = 433) enrolled in the High-dose Erythropoietin for Asphyxia and Encephalopathy (HEAL) study. We compared the performance of our model to five publicly available models (BET, BSE, CABINET, iBEATv2, ROBEX) across conventional and machine learning methods, tested on two public datasets (NIH and dHCP). We found that our model had a significantly higher Dice score on the aggregate of both data sets and comparable or significantly higher Dice scores on the NIH (low-resolution) and dHCP (high-resolution) datasets independently. ANUBEX performs similarly when trained on sequence-agnostic or motion-degraded MRI, but slightly worse on preterm brains. In conclusion, we created an automatic deep learning-based neonatal brain extraction algorithm that demonstrates accurate performance with both high- and low-resolution MRIs with fast computation time.

show abstract

Machine Learning and Prediction in Fetal, Infant, and Toddler Neuroimaging: A Review and Primer

Cited by 10 publications

References 102 publications

Brain-phenotype predictions can survive across diverse real-world data

Brain-phenotype predictions can survive across diverse real-world data

Brain age prediction and deviations from normative trajectories in the neonatal connectome

Automated neonatal nnU-Net brain MRI extractor trained on a large multi-institutional dataset

Contact Info

Product

Resources

About