Brain Age Prediction of Children Using Routine Brain MR Images via Deep Learning

Construction of influencing factor segmentation and intelligent prediction model of college students' cell phone addiction model based on machine learning algorithm

Mobile phone addiction among college students has emerged as a prevalent phenomenon in contemporary society, posing significant challenges to the development and well-being of these individuals. The assessment of the extent of mobile phone addiction has become an urgent concern in the present context. This study employed a sample of 3000 college students from a public university in Zhejiang Province, China, to gather questionnaire data. By utilizing a machine learning algorithm, we identified the most salient factors associated with college students' addiction, with perfectionism emerging as the primary influencer. Additionally, a machine learning-based prediction model for college students' cell phone addiction was developed, yielding a prediction accuracy of 76.68%. This intelligent model can serve as a reliable tool for subsequent evaluations of college students' cell phone addiction.

Mapping neurodevelopment with sleep macro- and micro-architecture across multiple pediatric populations

Profiles of sleep duration and timing and corresponding electroencephalographic activity reflect brain changes that support cognitive and behavioral maturation and may provide practical markers for tracking typical and atypical neurodevelopment. To build and evaluate a sleep-based, quantitative metric of brain maturation, we used whole-night polysomnography data, initially from two large National Sleep Research Resource samples, spanning childhood and adolescence (total N = 4,013, aged 2.5 to 17.5 years): the Childhood Adenotonsillectomy Trial (CHAT), a research study of children with snoring without neurodevelopmental delay, and Nationwide Children's Hospital (NCH) Sleep Databank, a pediatric sleep clinic cohort. Among children without neurodevelopmental disorders (NDD), sleep metrics derived from the electroencephalogram (EEG) displayed robust age-related changes consistently across datasets. During non-rapid eye movement (NREM) sleep, spindles and slow oscillations further exhibited characteristic developmental patterns, with respect to their rate of occurrence, temporal coupling and morphology. Based on these metrics in NCH, we constructed a model to predict an individual's chronological age. The model performed with high accuracy (r = 0.93 in the held-out NCH sample and r = 0.85 in a second independent replication sample - the Pediatric Adenotonsillectomy Trial for Snoring (PATS)). EEG-based age predictions reflected clinically meaningful neurodevelopmental differences; for example, children with NDD showed greater variability in predicted age, and children with Down syndrome or intellectual disability had significantly younger brain age predictions (respectively, 2.1 and 0.8 years less than their chronological age) compared to age-matched non-NDD children. Overall, our results indicate that sleep architectureoffers a sensitive window for characterizing brain maturation, suggesting the potential for scalable, objective sleep-based biomarkers to measure neurodevelopment.

A regional brain volume-based age prediction model for neonates and the derived brain maturation index

OBJECTIVE

To develop a postmenstrual age (PMA) prediction model based on segmentation volume and to evaluate the brain maturation index using the proposed model.

METHODS

Neonatal brain MRIs without clinical illness or structural abnormalities were collected from four datasets from the Developing Human Connectome Project, the Catholic University of Korea, Hammersmith Hospital (HS), and Dankook University Hospital (DU). T1- and T2-weighted images were used to train a brain segmentation model. Another model to predict the PMA of neonates based on segmentation data was developed. Accuracy was assessed using mean absolute error (MAE), root mean square error (RMSE), and mean error (ME). The brain maturation index was calculated as the difference between the PMA predicted by the model and the true PMA, and its correlation with postnatal age was analyzed.

RESULTS

A total of 247 neonates (mean gestation age 37 ± 4 weeks; range 24-42 weeks) were included. Thirty-one features were extracted from each neonate and the three most contributing features for PMA prediction were the right lateral ventricle, left caudate, and corpus callosum. The predicted and true PMA were positively correlated (coefficient = 0.88, p < .001). MAE, RMSE, and ME of the external dataset of HS and DU were 1.57 and 1.33, 1.79 and 1.37, and 0.37 and 0.06 weeks, respectively. The brain maturation index negatively correlated with postnatal age (coefficient =  - 0.24, p < .001).

CONCLUSION

A model that calculates the regional brain volume can predict the PMA of neonates, which can then be utilized to show the brain maturation degree.

CLINICAL RELEVANCE STATEMENT

A brain maturity index based on regional volume of neonate's brain can be used to measure brain maturation degree, which can help identify the status of early brain development.

KEY POINTS

• Neonatal brain MRI segmentation model could be used to assess neonatal brain maturation status. • A postmenstrual age (PMA) prediction model was developed based on a neonatal brain MRI segmentation model. • The brain maturation index, derived from the PMA prediction model, enabled the estimation of the neonatal brain maturation status.

Development and Evaluation of Deep Learning Models for Automated Estimation of Myelin Maturation Using Pediatric Brain MRI Scans

Purpose

To predict the corresponding age of myelin maturation from brain MRI scans in infants and young children by using a deep learning algorithm and to build upon previously published models.

Materials and Methods

Brain MRI scans acquired between January 1, 2011, and March 17, 2021, in our institution in patients aged 0-3 years were retrospectively retrieved from the archive. An ensemble of two-dimensional (2D) and three-dimensional (3D) convolutional neural network models was trained and internally validated in 710 patients to predict myelin maturation age on the basis of radiologist-generated labels. The model ensemble was tested on an internal dataset of 123 patients and two external datasets of 226 (0-25 months of age) and 383 (0-2 months of age) healthy children and infants, respectively. Mean absolute error (MAE) and Pearson correlation coefficients were used to assess model performance.

Results

The 2D, 3D, and 2D-plus-3D ensemble models showed MAE values of 1.43, 2.55, and 1.77 months, respectively, on the internal test set, values of 2.26, 2.27, and 1.22 months on the first external test set, and values of 0.44, 0.27, and 0.31 months on the second external test set. The ensemble model outperformed the previous state-of-the-art model on the same external test set (MAE = 1.22 vs 2.09 months).

Conclusion

The proposed deep learning model accurately predicted myelin maturation age using pediatric brain MRI scans and may help reduce the time needed to complete this task, as well as interobserver variability in radiologist predictions.Keywords: Pediatrics, MR Imaging, CNS, Brain/Brain Stem, Convolutional Neural Network (CNN), Artificial Intelligence, Pediatric Imaging, Myelin Maturation, Brain MRI, Neuroradiology Supplemental material is available for this article. © RSNA, 2023.

Replication and Refinement of Brain Age Model for adolescent development

The discrepancy between chronological age and estimated brain age, known as the brain age gap, may serve as a biomarker to reveal brain development and neuropsychiatric problems. This has motivated many studies focusing on the accurate estimation of brain age using different features and models, of which the generalizability is yet to be tested. Our recent study has demonstrated that conventional machine learning models can achieve high accuracy on brain age prediction during development using only a small set of selected features from multimodal brain imaging data. In the current study, we tested the replicability of various brain age models on the Adolescent Brain Cognitive Development (ABCD) cohort. We proposed a new refined model to improve the robustness of brain age prediction. The direct replication test for existing brain age models derived from the age range of 8-22 years onto the ABCD participants at baseline (9 to 10 years old) and year-two follow-up (11 to 12 years old) indicate that pre-trained models could capture the overall mean age failed precisely estimating brain age variation within a narrow range. The refined model, which combined broad prediction of the pre-trained model and granular information with the narrow age range, achieved the best performance with a mean absolute error of 0.49 and 0.48 years on the baseline and year-two data, respectively. The brain age gap yielded by the refined model showed significant associations with the participants' information processing speed and verbal comprehension ability on baseline data.

Brain Functional Network Generation Using Distribution-Regularized Adversarial Graph Autoencoder with Transformer for Dementia Diagnosis

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia disorders. The brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia disorders. However, it is challenging to access considerable amounts of brain functional network data, which hinders the widespread application of data-driven models in dementia diagnosis. In this study, a novel distribution-regularized adversarial graph auto-Encoder (DAGAE) with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset, improving the dementia diagnosis accuracy of data-driven models. Specifically, the label distribution is estimated to regularize the latent space learned by the graph encoder, which can make the learning process stable and the learned representation robust. Also, the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain regions. The typical topological properties and discriminative features can be preserved entirely. Furthermore, the generated brain functional networks improve the prediction performance using different classifiers, which can be applied to analyze other cognitive diseases. Attempts on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed model can generate good brain functional networks. The classification results show adding generated data can achieve the best accuracy value of 85.33%, sensitivity value of 84.00%, specificity value of 86.67%. The proposed model also achieves superior performance compared with other related augmented models. Overall, the proposed model effectively improves cognitive disease diagnosis by generating diverse brain functional networks.

Brain Age Prediction in Developing Childhood with Multimodal Magnetic Resonance Images

It is well known that brain development is very fast and complex in the early childhood with age-based neurological and physiological changes of brain structure and function. The brain maturity is an important indicator for evaluating the normal development of children. In this paper, we propose a multimodal regression framework to combine the features from structural magnetic resonance imaging (sMRI) and diffusion tensor imaging (DTI) data for age prediction of children. First, three types of features are extracted from sMRI and DTI data. Second, we propose to combine the sparse coding and Q-Learning for feature selection from each modality. Finally, the ensemble regression is performed by random forest based on proximity measures to fuse multimodal features for age prediction. The proposed method is evaluated on 212 participants, including 76 young children less than 2 years old and 136 children aged from 2-15 years old recruited from Shanghai Children's Hospital. The results show that integrating multimodal features has achieved the highest accuracies with the root mean squared error (RMSE) of 0.208 years and mean absolute error (MAE) of 0.150 years for age prediction of young children (0-2), and RMSE of 1.666 years and MAE of 1.087 years for older children (2-15). We have shown that the selected features by Q-Learning can consistently improve the prediction accuracy. The comparison of prediction results demonstrates that the proposed method performs better than other competing methods.

Constructing brain functional network by Adversarial Temporal-Spatial Aligned Transformer for early AD analysis

Introduction

The brain functional network can describe the spontaneous activity of nerve cells and reveal the subtle abnormal changes associated with brain disease. It has been widely used for analyzing early Alzheimer's disease (AD) and exploring pathological mechanisms. However, the current methods of constructing functional connectivity networks from functional magnetic resonance imaging (fMRI) heavily depend on the software toolboxes, which may lead to errors in connection strength estimation and bad performance in disease analysis because of many subjective settings.

Methods

To solve this problem, in this paper, a novel Adversarial Temporal-Spatial Aligned Transformer (ATAT) model is proposed to automatically map 4D fMRI into functional connectivity network for early AD analysis. By incorporating the volume and location of anatomical brain regions, the region-guided feature learning network can roughly focus on local features for each brain region. Also, the spatial-temporal aligned transformer network is developed to adaptively adjust boundary features of adjacent regions and capture global functional connectivity patterns of distant regions. Furthermore, a multi-channel temporal discriminator is devised to distinguish the joint distributions of the multi-region time series from the generator and the real sample.

Results

Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) proved the effectiveness and superior performance of the proposed model in early AD prediction and progression analysis.

Discussion

To verify the reliability of the proposed model, the detected important ROIs are compared with clinical studies and show partial consistency. Furthermore, the most significant altered connectivity reflects the main characteristics associated with AD.

Conclusion

Generally, the proposed ATAT provides a new perspective in constructing functional connectivity networks and is able to evaluate the disease-related changing characteristics at different stages for neuroscience exploration and clinical disease analysis.

Predicting the brain age of children with cerebral palsy using a two-dimensional convolutional neural networks prediction model without gray and white matter segmentation

Background

Abnormal brain development is common in children with cerebral palsy (CP), but there are no recent reports on the actual brain age of children with CP.

Objective

Our objective is to use the brain age prediction model to explore the law of brain development in children with CP.

Methods

A two-dimensional convolutional neural networks brain age prediction model was designed without segmenting the white and gray matter. Training and testing brain age prediction model using magnetic resonance images of healthy people in a public database. The brain age of children with CP aged 5-27 years old was predicted.

Results

The training dataset mean absolute error (MAE) = 1.85, r = 0.99; test dataset MAE = 3.98, r = 0.95. The brain age gap estimation (BrainAGE) of the 5- to 27-year-old patients with CP was generally higher than that of healthy peers (p < 0.0001). The BrainAGE of male patients with CP was higher than that of female patients (p < 0.05). The BrainAGE of patients with bilateral spastic CP was higher than those with unilateral spastic CP (p < 0.05).

Conclusion

A two-dimensional convolutional neural networks brain age prediction model allows for brain age prediction using routine hospital T1-weighted head MRI without segmenting the white and gray matter of the brain. At the same time, these findings suggest that brain aging occurs in patients with CP after brain damage. Female patients with CP are more likely to return to their original brain development trajectory than male patients after brain injury. In patients with spastic CP, brain aging is more serious in those with bilateral cerebral hemisphere injury than in those with unilateral cerebral hemisphere injury.

Cervical Cell Image Classification-Based Knowledge Distillation

Current deep-learning-based cervical cell classification methods suffer from parameter redundancy and poor model generalization performance, which creates challenges for the intelligent classification of cervical cytology smear images. In this paper, we establish a method for such classification that combines transfer learning and knowledge distillation. This new method not only transfers common features between different source domain data, but also realizes model-to-model knowledge transfer using the unnormalized probability output between models as knowledge. A multi-exit classification network is then introduced as the student network, where a global context module is embedded in each exit branch. A self-distillation method is then proposed to fuse contextual information; deep classifiers in the student network guide shallow classifiers to learn, and multiple classifier outputs are fused using an average integration strategy to form a classifier with strong generalization performance. The experimental results show that the developed method achieves good results using the SIPaKMeD dataset. The accuracy, sensitivity, specificity, and F-measure of the five classifications are 98.52%, 98.53%, 98.68%, 98.59%, respectively. The effectiveness of the method is further verified on a natural image dataset.

A novel scaled-gamma-tanh (SGT) activation function in 3D CNN applied for MRI classification

Activation functions in the neural network are responsible for 'firing' the nodes in it. In a deep neural network they 'activate' the features to reduce feature redundancy and learn the complex pattern by adding non-linearity in the network to learn task-specific goals. In this paper, we propose a simple and interesting activation function based on the combination of scaled gamma correction and hyperbolic tangent function, which we call Scaled Gamma Tanh (SGT) activation. The proposed activation function is applied in two steps, first is the calculation of gamma version as y = f(x) = axα for x < 0 and y = f(x) = bxβ for x ≥ 0, second is obtaining the squashed value as z = tanh(y). The variables a and b are user-defined constant values whereas [Formula: see text] and [Formula: see text] are channel-based learnable parameters. We analyzed the behavior of the proposed SGT activation function against other popular activation functions like ReLU, Leaky-ReLU, and tanh along with their role to confront vanishing/exploding gradient problems. For this, we implemented the SGT activation functions in a 3D Convolutional neural network (CNN) for the classification of magnetic resonance imaging (MRIs). More importantly to support our proposed idea we have presented a thorough analysis via histogram of inputs and outputs in activation layers along with weights/bias plot and t-SNE (t-Distributed Stochastic Neighbor Embedding) projection of fully connected layer for the trained CNN models. Our results in MRI classification show SGT outperforms standard ReLU and tanh activation in all cases i.e., final validation accuracy, final validation loss, test accuracy, Cohen's kappa score, and Precision.

Linking Brain Age Gap to Mental and Physical Health in the Berlin Aging Study II

From a biological perspective, humans differ in the speed they age, and this may manifest in both mental and physical health disparities. The discrepancy between an individual's biological and chronological age of the brain ("brain age gap") can be assessed by applying machine learning techniques to Magnetic Resonance Imaging (MRI) data. Here, we examined the links between brain age gap and a broad range of cognitive, affective, socioeconomic, lifestyle, and physical health variables in up to 335 adults of the Berlin Aging Study II. Brain age gap was assessed using a validated prediction model that we previously trained on MRI scans of 32,634 UK Biobank individuals. Our statistical analyses revealed overall stronger evidence for a link between higher brain age gap and less favorable health characteristics than expected under the null hypothesis of no effect, with 80% of the tested associations showing hypothesis-consistent effect directions and 23% reaching nominal significance. The most compelling support was observed for a cluster covering both cognitive performance variables (episodic memory, working memory, fluid intelligence, digit symbol substitution test) and socioeconomic variables (years of education and household income). Furthermore, we observed higher brain age gap to be associated with heavy episodic drinking, higher blood pressure, and higher blood glucose. In sum, our results point toward multifaceted links between brain age gap and human health. Understanding differences in biological brain aging may therefore have broad implications for future informed interventions to preserve mental and physical health in old age.

Multimodal Brain Age Prediction with Feature Selection and Comparison

Brain age, an estimated biological age from anatomical and/or functional brain imaging data, and its deviation from the chronological age (brain age gap) have shown the potential to serve as biomarkers for characterizing typical brain development, the abnormal aging process, and early indicators of clinical neuropsychiatric problems. In this study, we leverage multimodal brain imaging data for brain age prediction. We studied and compared the performance of individual data modalities (gray matter density in components and regions of interest, cortical and subcortical anatomical features, resting-state functional connectivity) and different combinations of multiple data modalities using data collected from 1417 participants with age between 8 and 22 years. The result indicates that feature selection and multimodal imaging data can improve brain age prediction with linear support vector and partial least squares regression models. We have achieved a mean absolute error of 1.22 years on the test data with 188 features selected equally from all data sources, better than any individual source. After bias correction, the brain age gap was significantly associated with attention accuracy/speed and motor speed in addition to age. Our results conclude that traditional machine learning with proper feature selection can achieve similar if not better performance compared to complex deep learning neural network methods for the used sample size.

Automation of a Rule-based Workflow to Estimate Age from Brain MR Imaging of Infants and Children Up to 2 Years Old Using Stacked Deep Learning

PURPOSE

Myelination-related MR signal changes in white matter are helpful for assessing normal development in infants and children. A rule-based myelination evaluation workflow regarding signal changes on T1-weighted images (T1WIs) and T2-weighted images (T2WIs) has been widely used in radiology. This study aimed to simulate a rule-based workflow using a stacked deep learning model and evaluate age estimation accuracy.

METHODS

The age estimation system involved two stacked neural networks: a target network-to extract five myelination-related images from the whole brain, and an age estimation network from extracted T1- and T2WIs separately. A dataset was constructed from 119 children aged below 2 years with two MRI systems. A four-fold cross-validation method was adopted. The correlation coefficient (CC), mean absolute error (MAE), and root mean squared error (RMSE) of the corrected chronological age of full-term birth, as well as the mean difference and the upper and lower limits of 95% agreement, were measured. Generalization performance was assessed using datasets acquired from different MR images. Age estimation was performed in Sturge-Weber syndrome (SWS) cases.

RESULTS

There was a strong correlation between estimated age and corrected chronological age (MAE: 0.98 months; RMSE: 1.27 months; and CC: 0.99). The mean difference and standard deviation (SD) were -0.15 and 1.26, respectively, and the upper and lower limits of 95% agreement were 2.33 and -2.63 months. Regarding generalization performance, the performance values on the external dataset were MAE of 1.85 months, RMSE of 2.59 months, and CC of 0.93. Among 13 SWS cases, 7 exceeded the limits of 95% agreement, and a proportional bias of age estimation based on myelination acceleration was exhibited below 12 months of age (P = 0.03).

CONCLUSION

Stacked deep learning models automated the rule-based workflow in radiology and achieved highly accurate age estimation in infants and children up to 2 years of age.

A review of medical image data augmentation techniques for deep learning applications

Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning-based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren't typically available, which is often the case when working with medical images. Data augmentation aims to generate additional data which is used to train the model and has been shown to improve performance when validated on a separate unseen dataset. This approach has become commonplace so to help understand the types of data augmentation techniques used in state-of-the-art deep learning models, we conducted a systematic review of the literature where data augmentation was utilised on medical images (limited to CT and MRI) to train a deep learning model. Articles were categorised into basic, deformable, deep learning or other data augmentation techniques. As artificial intelligence models trained using augmented data make their way into the clinic, this review aims to give an insight to these techniques and confidence in the validity of the models produced.