Background/Objectives: Artificial intelligence (AI) is transforming neuroimaging by enhancing diagnostic precision and treatment planning. However, its applications in pediatric cancer neuroimaging remain limited. This review assesses the current state, potential applications, and challenges of AI in pediatric neuroimaging for cancer, emphasizing the unique needs of the pediatric population. Methods: A comprehensive literature review was conducted, focusing on AI’s impact on pediatric neuroimaging through accelerated image acquisition, reduced radiation, and improved tumor detection. Key methods include convolutional neural networks for tumor segmentation, radiomics for tumor characterization, and several tools for functional imaging. Challenges such as limited pediatric datasets, developmental variability, ethical concerns, and the need for explainable models were analyzed. Results: AI has shown significant potential to improve imaging quality, reduce scan times, and enhance diagnostic accuracy in pediatric neuroimaging, resulting in improved accuracy in tumor segmentation and outcome prediction for treatment. However, progress is hindered by the scarcity of pediatric datasets, issues with data sharing, and the ethical implications of applying AI in vulnerable populations. Conclusions: To overcome current limitations, future research should focus on building robust pediatric datasets, fostering multi-institutional collaborations for data sharing, and developing interpretable AI models that align with clinical practice and ethical standards. These efforts are essential in harnessing the full potential of AI in pediatric neuroimaging and improving outcomes for children with cancer.

Experimental evidence in animals demonstrates cortical neurons innervate subcortex bilaterally to tune brainstem auditory coding. Yet, the role of the descending (corticofugal) auditory system in modulating earlier sound processing in humans during speech perception remains unclear. Here, we measured EEG activity as listeners performed speech identification tasks in different noise backgrounds designed to tax perceptual and attentional processing. We hypothesized brainstem speech coding might be tied to attention and arousal states (indexed by cortical α power) that actively modulate the interplay of brainstem-cortical signal processing. When speech-evoked brainstem frequency-following responses (FFRs) were categorized according to cortical α states, we found low α FFRs in noise were weaker, correlated positively with behavioral response times, and were more “decodable” via neural classifiers. Our data provide new evidence for online corticofugal interplay in humans and establish that brainstem sensory representations are continuously yoked to (i.e., modulated by) the ebb and flow of cortical states to dynamically update perceptual processing.

Sickle cell disease (SCD) decreases the oxygen-carrying capacity of red blood cells. Children with SCD have reduced/restricted cerebral blood flow, resulting in neurocognitive deficits. Hydroxyurea is the standard treatment for SCD; however, whether hydroxyurea influences such effects is unclear. A key area of SCD-associated neurocognitive impairment is working memory, which is implicated in other cognitive and academic skills. The neural correlates of working memory can be tested using n-back tasks. We analyzed functional magnetic resonance imaging (fMRI) data of patients with SCD (20 hydroxyurea-treated patients and 11 controls, aged 7–18 years) while they performed n-back tasks. Blood-oxygenation level–dependent (BOLD) signals were assessed during working memory processing at 2 time points: before hydroxyurea treatment and ~1 year after treatment was initiated. Neurocognitive measures were also assessed at both time points. Our results suggested that working memory was stable in the treated group. We observed a treatment-by-time interaction in the right cuneus and angular gyrus for the 2- >0-back contrast. Searchlight-pattern classification of the 2 time points of the 2-back tasks identified greater changes in the pattern and magnitude of BOLD signals, especially in the posterior regions of the brain, in the control group than in the treated group. In the control group at 1-year follow-up, 2-back BOLD signals increased across time points in several clusters (e.g., right inferior temporal lobe, right angular gyrus). We hypothesize that these changes resulted from increased cognitive effort during working memory processing in the absence of hydroxyurea. In the treated group, 0- to 2-back BOLD signals in the right angular gyrus and left cuneus increased continuously with increasing working memory load, potentially related to a broader dynamic range in response to task difficulty and cognitive effort. These findings suggest that hydroxyurea treatment helps maintain working memory function in SCD.

Objective assays of human cochlear synaptopathy (CS) have been challenging to develop. It is suspected that relative summating potential (SP) changes are different in listeners with CS. In this proof-of-concept study, young, normal-hearing adults were recruited and assigned to a low/high-risk group for having CS based on their extended audiograms (9–16 kHz). SPs to paired-clicks with varying inter-click intervals isolated non-refractory receptor components of cochlear activity. Abrupt increases in SPs to paired- vs single-clicks were observed in high-risk listeners. Critically, exaggerated SPs predicted speech-in-noise and subjective hearing abilities, suggesting relative SP changes to rapid clicks might help identify putative synaptopathic listeners.

Predictive accuracy of surgical case duration plays a critical role in reducing cost of operation room (OR) utilization. The most common approaches used by hospitals rely on historic averages based on a specific surgeon or a specific procedure type obtained from the electronic medical record (EMR) scheduling systems. However, low predictive accuracy of EMR leads to negative impacts on patients and hospitals, such as rescheduling of surgeries and cancellation. In this study, we aim to improve prediction of operation case duration with advanced machine learning (ML) algorithms. We obtained a large data set containing 170,748 operation cases (from Jan 2017 to Dec 2019) from a hospital. The data covered a broad variety of details on patients, operations, specialties and surgical teams. Meanwhile, a more recent data with 8,672 cases (from Mar to Apr 2020) was also available to be used for external evaluation. We computed historic averages from EMR for surgeon- or procedure-specific and they were used as baseline models for comparison. Subsequently, we developed our models using linear regression, random forest and extreme gradient boosting (XGB) algorithms. All models were evaluated with R-squre ( R ² ), mean absolute error ( MAE ), and percentage overage (case duration > prediction + 10 % & 15 mins), underage (case duration < prediction - 10 % & 15 mins) and within (otherwise). The XGB model was superior to the other models by having higher R ² (85 %) and percentage within (48 %) as well as lower MAE (30.2 mins). The total prediction errors computed for all the models showed that the XGB model had the lowest inaccurate percent (23.7 %). As a whole, this study applied ML techniques in the field of OR scheduling to reduce medical and financial burden for healthcare management. It revealed the importance of operation and surgeon factors in operation case duration prediction. This study also demonstrated the importance of performing an external evaluation to better validate performance of ML models.

Experimental evidence in animals demonstrates cortical neurons innervate subcortex bilaterally to tune brainstem auditory coding. Yet, the role of the descending (corticofugal) auditory system in modulating earlier sound processing in humans during speech perception remains unclear. Here, we measured EEG activity as listeners performed speech identification tasks in different noise backgrounds designed to tax perceptual and attentional processing. Brainstem speech coding might be tied to attention and arousal states (indexed by cortical α power) that actively modulate the interplay of brainstem-cortical signal processing. When speech-evoked brainstem frequency-following responses (FFRs) were categorized according to cortical α states, low α FFRs in noise were found to be weaker, correlated positively with behavioral response times, more “decodable” via classifiers, and associated indirectly with other signal-in-noise perceptual performance. Our data provide evidence for online corticofugal interplay in humans and establish that brainstem sensory representations are continuously yoked to the ebb and flow of cortical states to dynamically update perceptual processing.