Multimodal biological brain age prediction using magnetic resonance imaging and angiography with the identification of predictive regions

Predicting Brain Age and Gender from Brain Volume Data Using Variational Quantum Circuits

The morphology of the brain undergoes changes throughout the aging process, and accurately predicting a person's brain age and gender using brain morphology features can aid in detecting atypical brain patterns. Neuroimaging-based estimation of brain age is commonly used to assess an individual's brain health relative to a typical aging trajectory, while accurately classifying gender from neuroimaging data offers valuable insights into the inherent neurological differences between males and females. In this study, we aimed to compare the efficacy of classical machine learning models with that of a quantum machine learning method called a variational quantum circuit in estimating brain age and predicting gender based on structural magnetic resonance imaging data. We evaluated six classical machine learning models alongside a quantum machine learning model using both combined and sub-datasets, which included data from both in-house collections and public sources. The total number of participants was 1157, ranging from ages 14 to 89, with a gender distribution of 607 males and 550 females. Performance evaluation was conducted within each dataset using training and testing sets. The variational quantum circuit model generally demonstrated superior performance in estimating brain age and gender classification compared to classical machine learning algorithms when using the combined dataset. Additionally, in benchmark sub-datasets, our approach exhibited better performance compared to previous studies that utilized the same dataset for brain age prediction. Thus, our results suggest that variational quantum algorithms demonstrate comparable effectiveness to classical machine learning algorithms for both brain age and gender prediction, potentially offering reduced error and improved accuracy.

Exploiting macro- and micro-structural brain changes for improved Parkinson's disease classification from MRI data

Parkinson's disease (PD) is the second most common neurodegenerative disease. Accurate PD diagnosis is crucial for effective treatment and prognosis but can be challenging, especially at early disease stages. This study aimed to develop and evaluate an explainable deep learning model for PD classification from multimodal neuroimaging data. The model was trained using one of the largest collections of T1-weighted and diffusion-tensor magnetic resonance imaging (MRI) datasets. A total of 1264 datasets from eight different studies were collected, including 611 PD patients and 653 healthy controls (HC). These datasets were pre-processed and non-linearly registered to the MNI PD25 atlas. Six imaging maps describing the macro- and micro-structural integrity of brain tissues complemented with age and sex parameters were used to train a convolutional neural network (CNN) to classify PD/HC subjects. Explainability of the model's decision-making was achieved using SmoothGrad saliency maps, highlighting important brain regions. The CNN was trained using a 75%/10%/15% train/validation/test split stratified by diagnosis, sex, age, and study, achieving a ROC-AUC of 0.89, accuracy of 80.8%, specificity of 82.4%, and sensitivity of 79.1% on the test set. Saliency maps revealed that diffusion tensor imaging data, especially fractional anisotropy, was more important for the classification than T1-weighted data, highlighting subcortical regions such as the brainstem, thalamus, amygdala, hippocampus, and cortical areas. The proposed model, trained on a large multimodal MRI database, can classify PD patients and HC subjects with high accuracy and clinically reasonable explanations, suggesting that micro-structural brain changes play an essential role in the disease course.

Brain age prediction across the human lifespan using multimodal MRI data

Measuring differences between an individual's age and biological age with biological information from the brain have the potential to provide biomarkers of clinically relevant neurological syndromes that arise later in human life. To explore the effect of multimodal brain magnetic resonance imaging (MRI) features on the prediction of brain age, we investigated how multimodal brain imaging data improved age prediction from more imaging features of structural or functional MRI data by using partial least squares regression (PLSR) and longevity data sets (age 6-85 years). First, we found that the age-predicted values for each of these ten features ranged from high to low: cortical thickness (R = 0.866, MAE = 7.904), all seven MRI features (R = 0.8594, MAE = 8.24), four features in structural MRI (R = 0.8591, MAE = 8.24), fALFF (R = 0.853, MAE = 8.1918), gray matter volume (R = 0.8324, MAE = 8.931), three rs-fMRI feature (R = 0.7959, MAE = 9.744), mean curvature (R = 0.7784, MAE = 10.232), ReHo (R = 0.7833, MAE = 10.122), ALFF (R = 0.7517, MAE = 10.844), and surface area (R = 0.719, MAE = 11.33). In addition, the significance of the volume and size of brain MRI data in predicting age was also studied. Second, our results suggest that all multimodal imaging features, except cortical thickness, improve brain-based age prediction. Third, we found that the left hemisphere contributed more to the age prediction, that is, the left hemisphere showed a greater weight in the age prediction than the right hemisphere. Finally, we found a nonlinear relationship between the predicted age and the amount of MRI data. Combined with multimodal and lifespan brain data, our approach provides a new perspective for chronological age prediction and contributes to a better understanding of the relationship between brain disorders and aging.

A deep learning model for brain age prediction using minimally preprocessed T1w images as input

Introduction

In the last few years, several models trying to calculate the biological brain age have been proposed based on structural magnetic resonance imaging scans (T1-weighted MRIs, T1w) using multivariate methods and machine learning. We developed and validated a convolutional neural network (CNN)-based biological brain age prediction model that uses one T1w MRI preprocessing step when applying the model to external datasets to simplify implementation and increase accessibility in research settings. Our model only requires rigid image registration to the MNI space, which is an advantage compared to previous methods that require more preprocessing steps, such as feature extraction.

Methods

We used a multicohort dataset of cognitively healthy individuals (age range = 32.0-95.7 years) comprising 17,296 MRIs for training and evaluation. We compared our model using hold-out (CNN1) and cross-validation (CNN2-4) approaches. To verify generalisability, we used two external datasets with different populations and MRI scan characteristics to evaluate the model. To demonstrate its usability, we included the external dataset's images in the cross-validation training (CNN3). To ensure that our model used only the brain signal on the image, we also predicted brain age using skull-stripped images (CNN4).

Results

The trained models achieved a mean absolute error of 2.99, 2.67, 2.67, and 3.08 years for CNN1-4, respectively. The model's performance in the external dataset was in the typical range of mean absolute error (MAE) found in the literature for testing sets. Adding the external dataset to the training set (CNN3), overall, MAE is unaffected, but individual cohort MAE improves (5.63-2.25 years). Salience maps of predictions reveal that periventricular, temporal, and insular regions are the most important for age prediction.

Discussion

We provide indicators for using biological (predicted) brain age as a metric for age correction in neuroimaging studies as an alternative to the traditional chronological age. In conclusion, using different approaches, our CNN-based model showed good performance using one T1w brain MRI preprocessing step. The proposed CNN model is made publicly available for the research community to be easily implemented and used to study ageing and age-related disorders.

A deep neural network estimation of brain age is sensitive to cognitive impairment and decline

The greatest known risk factor for Alzheimer's disease (AD) is age. While both normal aging and AD pathology involve structural changes in the brain, their trajectories of atrophy are not the same. Recent developments in artificial intelligence have encouraged studies to leverage neuroimaging-derived measures and deep learning approaches to predict brain age, which has shown promise as a sensitive biomarker in diagnosing and monitoring AD. However, prior efforts primarily involved structural magnetic resonance imaging and conventional diffusion MRI (dMRI) metrics without accounting for partial volume effects. To address this issue, we post-processed our dMRI scans with an advanced free-water (FW) correction technique to compute distinct FW-corrected fractional anisotropy (FAFWcorr) and FW maps that allow for the separation of tissue from fluid in a scan. We built 3 densely connected neural networks from FW-corrected dMRI, T1-weighted MRI, and combined FW+T1 features, respectively, to predict brain age. We then investigated the relationship of actual age and predicted brain ages with cognition. We found that all models accurately predicted actual age in cognitively unimpaired (CU) controls (FW: r=0.66, p=1.62x10-32; T1: r=0.61, p=1.45x10-26, FW+T1: r=0.77, p=6.48x10-50) and distinguished between CU and mild cognitive impairment participants (FW: p=0.006; T1: p=0.048; FW+T1: p=0.003), with FW+T1-derived age showing best performance. Additionally, all predicted brain age models were significantly associated with cross-sectional cognition (memory, FW: β=-1.094, p=6.32x10-7; T1: β=-1.331, p=6.52x10-7; FW+T1: β=-1.476, p=2.53x10-10; executive function, FW: β=-1.276, p=1.46x10-9; T1: β=-1.337, p=2.52x10-7; FW+T1: β=-1.850, p=3.85x10-17) and longitudinal cognition (memory, FW: β=-0.091, p=4.62x10-11; T1: β=-0.097, p=1.40x10-8; FW+T1: β=-0.101, p=1.35x10-11; executive function, FW: β=-0.125, p=1.20x10-10; T1: β=-0.163, p=4.25x10-12; FW+T1: β=-0.158, p=1.65x10-14). Our findings provide evidence that both T1-weighted MRI and dMRI measures improve brain age prediction and support predicted brain age as a sensitive biomarker of cognition and cognitive decline.

Geroscience-Centric Perspective for Geriatric Psychiatry: Integrating Aging Biology With Geriatric Mental Health Research

The geroscience hypothesis asserts that physiological aging is caused by a small number of biological pathways. Despite the explosion of geroscience research over the past couple of decades, the research on how serious mental illnesses (SMI) affects the biological aging processes is still in its infancy. In this review, we aim to provide a critical appraisal of the emerging literature focusing on how we measure biological aging systematically, and in the brain and how SMIs affect biological aging measures in older adults. We will also review recent developments in the field of cellular senescence and potential targets for interventions for SMIs in older adults, based on the geroscience hypothesis.

eXplainable Artificial Intelligence (XAI) in aging clock models

XAI is a rapidly progressing field of machine learning, aiming to unravel the predictions of complex models. XAI is especially required in sensitive applications, e.g. in health care, when diagnosis, recommendations and treatment choices might rely on the decisions made by artificial intelligence systems. AI approaches have become widely used in aging research as well, in particular, in developing biological clock models and identifying biomarkers of aging and age-related diseases. However, the potential of XAI here awaits to be fully appreciated. We discuss the application of XAI for developing the "aging clocks" and present a comprehensive analysis of the literature categorized by the focus on particular physiological systems.

Image-encoded biological and non-biological variables may be used as shortcuts in deep learning models trained on multisite neuroimaging data

OBJECTIVE

This work investigates if deep learning (DL) models can classify originating site locations directly from magnetic resonance imaging (MRI) scans with and without correction for intensity differences.

MATERIAL AND METHODS

A large database of 1880 T1-weighted MRI scans collected across 41 sites originally for Parkinson's disease (PD) classification was used to classify sites in this study. Forty-six percent of the datasets are from PD patients, while 54% are from healthy participants. After preprocessing the T1-weighted scans, 2 additional data types were generated: intensity-harmonized T1-weighted scans and log-Jacobian deformation maps resulting from nonlinear atlas registration. Corresponding DL models were trained to classify sites for each data type. Additionally, logistic regression models were used to investigate the contribution of biological (age, sex, disease status) and non-biological (scanner type) variables to the models' decision.

RESULTS

A comparison of the 3 different types of data revealed that DL models trained using T1-weighted and intensity-harmonized T1-weighted scans can classify sites with an accuracy of 85%, while the model using log-Jacobian deformation maps achieved a site classification accuracy of 54%. Disease status and scanner type were found to be significant confounders.

DISCUSSION

Our results demonstrate that MRI scans encode relevant site-specific information that models could use as shortcuts that cannot be removed using simple intensity harmonization methods.

CONCLUSION

The ability of DL models to exploit site-specific biases as shortcuts raises concerns about their reliability, generalization, and deployability in clinical settings.

The causal link between cardiometabolic risk factors and gray matter atrophy: An exploratory study

Although gray matter atrophy is commonly observed with aging, it is highly variable, even among healthy people of the same age. This raises the question of what other factors may contribute to gray matter atrophy. Previous studies have reported that risk factors for cardiometabolic diseases are associated with accelerated brain aging. However, these studies were primarily based on standard correlation analyses, which do not unveil a causal relationship. While randomized controlled trials are typically required to investigate true causality, in this work, we investigated an alternative method by exploring data-driven causal discovery and inference techniques on observational data. Accordingly, this feasibility study used clinical and quantified gray matter volume data from 22,793 subjects from the UK biobank cohort without any known neurological disease. Our method identified that age, sex, body mass index (BMI), body fat percentage (BFP), and smoking exhibit a causal relationship with gray matter volume. Interventions on the causal network revealed that higher BMI and BFP values significantly increased the chance of gray matter atrophy in males, whereas this was not the case in females.

Assessing Machine Learning Models for Predicting Age with Intracranial Vessel Tortuosity and Thickness Information

This study aimed to develop and validate machine learning (ML) models that predict age using intracranial vessels' tortuosity and diameter features derived from magnetic resonance angiography (MRA) data. A total of 171 subjects' three-dimensional (3D) time-of-flight MRA image data were considered for analysis. After annotations of two endpoints in each arterial segment, tortuosity features such as the sum of the angle metrics, triangular index, relative length, and product of the angle distance, as well as the vessels' diameter features, were extracted and used to train and validate the ML models for age prediction. Features extracted from the right and left internal carotid arteries (ICA) and basilar arteries were considered as the inputs to train and validate six ML regression models with a four-fold cross validation. The random forest regression model resulted in the lowest root mean square error of 14.9 years and the highest average coefficient of determination of 0.186. The linear regression model showed the lowest average mean absolute percentage error (MAPE) and the highest average Pearson correlation coefficient (0.532). The mean diameter of the right ICA vessel segment was the most important feature contributing to prediction of age in two out of the four regression models considered. An ML of tortuosity descriptors and diameter features extracted from MRA data showed a modest correlation between real age and ML-predicted age. Further studies are warranted for the assessment of the model's age predictions in patients with intracranial vessel diseases.

A deep neural network estimation of brain age is sensitive to cognitive impairment and decline

The greatest known risk factor for Alzheimer's disease (AD) is age. While both normal aging and AD pathology involve structural changes in the brain, their trajectories of atrophy are not the same. Recent developments in artificial intelligence have encouraged studies to leverage neuroimaging-derived measures and deep learning approaches to predict brain age, which has shown promise as a sensitive biomarker in diagnosing and monitoring AD. However, prior efforts primarily involved structural magnetic resonance imaging and conventional diffusion MRI (dMRI) metrics without accounting for partial volume effects. To address this issue, we post-processed our dMRI scans with an advanced free-water (FW) correction technique to compute distinct FW-corrected fractional anisotropy (FAFWcorr) and FW maps that allow for the separation of tissue from fluid in a scan. We built 3 densely connected neural networks from FW-corrected dMRI, T1-weighted MRI, and combined FW+T1 features, respectively, to predict brain age. We then investigated the relationship of actual age and predicted brain ages with cognition. We found that all models accurately predicted actual age in cognitively unimpaired (CU) controls (FW: r=0.66, p=1.62×10-32; T1: r=0.61, p=1.45×10-26, FW+T1: r=0.77, p=6.48×10-50) and distinguished between CU and mild cognitive impairment participants (FW: p=0.006; T1: p=0.048; FW+T1: p=0.003), with FW+T1-derived age showing best performance. Additionally, all predicted brain age models were significantly associated with cross-sectional cognition (memory, FW: β=-1.094, p=6.32×10-7; T1: β=-1.331, p=6.52×10-7; FW+T1: β=-1.476, p=2.53×10-10; executive function, FW: β=-1.276, p=1.46×10-9; T1: β=-1.337, p=2.52×10-7; FW+T1: β=-1.850, p=3.85×10-17) and longitudinal cognition (memory, FW: β=-0.091, p=4.62×10-11; T1: β=-0.097, p=1.40×10-8; FW+T1: β=-0.101, p=1.35×10-11; executive function, FW: β=-0.125, p=1.20×10-10; T1: β=-0.163, p=4.25×10-12; FW+T1: β=-0.158, p=1.65×10-14). Our findings provide evidence that both T1-weighted MRI and dMRI measures improve brain age prediction and support predicted brain age as a sensitive biomarker of cognition and cognitive decline.

Recent Advances in Explainable Artificial Intelligence for Magnetic Resonance Imaging

Advances in artificial intelligence (AI), especially deep learning (DL), have facilitated magnetic resonance imaging (MRI) data analysis, enabling AI-assisted medical image diagnoses and prognoses. However, most of the DL models are considered as "black boxes". There is an unmet need to demystify DL models so domain experts can trust these high-performance DL models. This has resulted in a sub-domain of AI research called explainable artificial intelligence (XAI). In the last decade, many experts have dedicated their efforts to developing novel XAI methods that are competent at visualizing and explaining the logic behind data-driven DL models. However, XAI techniques are still in their infancy for medical MRI image analysis. This study aims to outline the XAI applications that are able to interpret DL models for MRI data analysis. We first introduce several common MRI data modalities. Then, a brief history of DL models is discussed. Next, we highlight XAI frameworks and elaborate on the principles of multiple popular XAI methods. Moreover, studies on XAI applications in MRI image analysis are reviewed across the tissues/organs of the human body. A quantitative analysis is conducted to reveal the insights of MRI researchers on these XAI techniques. Finally, evaluations of XAI methods are discussed. This survey presents recent advances in the XAI domain for explaining the DL models that have been utilized in MRI applications.

Explainable classification of Parkinson's disease using deep learning trained on a large multi-center database of T1-weighted MRI datasets

INTRODUCTION

Parkinson's disease (PD) is a severe neurodegenerative disease that affects millions of people. Early diagnosis is important to facilitate prompt interventions to slow down disease progression. However, accurate PD diagnosis can be challenging, especially in the early disease stages. The aim of this work was to develop and evaluate a robust explainable deep learning model for PD classification trained from one of the largest collections of T1-weighted magnetic resonance imaging datasets.

MATERIALS AND METHODS

A total of 2,041 T1-weighted MRI datasets from 13 different studies were collected, including 1,024 datasets from PD patients and 1,017 datasets from age- and sex-matched healthy controls (HC). The datasets were skull stripped, resampled to isotropic resolution, bias field corrected, and non-linearly registered to the MNI PD25 atlas. The Jacobian maps derived from the deformation fields together with basic clinical parameters were used to train a state-of-the-art convolutional neural network (CNN) to classify PD and HC subjects. Saliency maps were generated to display the brain regions contributing the most to the classification task as a means of explainable artificial intelligence.

RESULTS

The CNN model was trained using an 85%/5%/10% train/validation/test split stratified by diagnosis, sex, and study. The model achieved an accuracy of 79.3%, precision of 80.2%, specificity of 81.3%, sensitivity of 77.7%, and AUC-ROC of 0.87 on the test set while performing similarly on an independent test set. Saliency maps computed for the test set data highlighted frontotemporal regions, the orbital-frontal cortex, and multiple deep gray matter structures as most important.

CONCLUSION

The developed CNN model, trained on a large heterogenous database, was able to differentiate PD patients from HC subjects with high accuracy with clinically feasible classification explanations. Future research should aim to investigate the combination of multiple imaging modalities with deep learning and on validating these results in a prospective trial as a clinical decision support system.

A systematic review of multimodal brain age studies: Uncovering a divergence between model accuracy and utility

Brain aging is a complex, multifaceted process that can be challenging to model in ways that are accurate and clinically useful. One of the most common approaches has been to apply machine learning to neuroimaging data with the goal of predicting age in a data-driven manner. Building on initial brain age studies that were derived solely from T1-weighted scans (i.e., unimodal), recent studies have incorporated features across multiple imaging modalities (i.e., "multimodal"). In this systematic review, we show that unimodal and multimodal models have distinct advantages. Multimodal models are the most accurate and sensitive to differences in chronic brain disorders. In contrast, unimodal models from functional magnetic resonance imaging were most sensitive to differences across a broad array of phenotypes. Altogether, multimodal imaging has provided us valuable insight for improving the accuracy of brain age models, but there is still much untapped potential with regard to achieving widespread clinical utility.

Garcia A, Buetow K, Thomas GS, Finch CE, Stieglitz J, Trumble BC, Gurven MD, Irimia A. Brain volume, energy balance, and cardiovascular health in two nonindustrial South American populations

Little is known about brain aging or dementia in nonindustrialized environments that are similar to how humans lived throughout evolutionary history. This paper examines brain volume (BV) in middle and old age among two indigenous South American populations, the Tsimane and Moseten, whose lifestyles and environments diverge from those in high-income nations. With a sample of 1,165 individuals aged 40 to 94, we analyze population differences in cross-sectional rates of decline in BV with age. We also assess the relationships of BV with energy biomarkers and arterial disease and compare them against findings in industrialized contexts. The analyses test three hypotheses derived from an evolutionary model of brain health, which we call the embarrassment of riches (EOR). The model hypothesizes that food energy was positively associated with late life BV in the physically active, food-limited past, but excess body mass and adiposity are now associated with reduced BV in industrialized societies in middle and older ages. We find that the relationship of BV with both non-HDL cholesterol and body mass index is curvilinear, positive from the lowest values to 1.4 to 1.6 SDs above the mean, and negative from that value to the highest values. The more acculturated Moseten exhibit a steeper decrease in BV with age than Tsimane, but still shallower than US and European populations. Lastly, aortic arteriosclerosis is associated with lower BV. Complemented by findings from the United States and Europe, our results are consistent with the EOR model, with implications for interventions to improve brain health.

Graph Transformer Geometric Learning of Brain Networks Using Multimodal MR Images for Brain Age Estimation

Brain age is considered as an important biomarker for detecting aging-related diseases such as Alzheimer's Disease (AD). Magnetic resonance imaging (MRI) have been widely investigated with deep neural networks for brain age estimation. However, most existing methods cannot make full use of multimodal MRIs due to the difference in data structure. In this paper, we propose a graph transformer geometric learning framework to model the multimodal brain network constructed by structural MRI (sMRI) and diffusion tensor imaging (DTI) for brain age estimation. First, we build a two-stream convolutional autoencoder to learn the latent representations for each imaging modality. The brain template with prior knowledge is utilized to calculate the features from the regions of interest (ROIs). Then, a multi-level construction of the brain network is proposed to establish the hybrid ROI connections in space, feature and modality. Next, a graph transformer network is proposed to model the cross-modal interaction and fusion by geometric learning for brain age estimation. Finally, the difference between the estimated age and the chronological age is used as an important biomarker for AD diagnosis. Our method is evaluated with the sMRI and DTI data from UK Biobank and Alzheimer's Disease Neuroimaging Initiative database. Experimental results demonstrate that our method has achieved promising performances for brain age estimation and AD diagnosis.

Multimodal brain age prediction fusing morphometric and imaging data and association with cardiovascular risk factors

Introduction

The difference between the chronological and biological brain age, called the brain age gap (BAG), has been identified as a promising biomarker to detect deviation from normal brain aging and to indicate the presence of neurodegenerative diseases. Moreover, the BAG has been shown to encode biological information about general health, which can be measured through cardiovascular risk factors. Current approaches for biological brain age estimation, and therefore BAG estimation, either depend on hand-crafted, morphological measurements extracted from brain magnetic resonance imaging (MRI) or on direct analysis of brain MRI images. The former can be processed with traditional machine learning models while the latter is commonly processed with convolutional neural networks (CNNs). Using a multimodal setting, this study aims to compare both approaches in terms of biological brain age prediction accuracy and biological information captured in the BAG.

Methods

T1-weighted MRI, containing brain tissue information, and magnetic resonance angiography (MRA), providing information about brain arteries, from 1,658 predominantly healthy adults were used. The volumes, surface areas, and cortical thickness of brain structures were extracted from the T1-weighted MRI data, while artery density and thickness within the major blood flow territories and thickness of the major arteries were extracted from MRA data. Independent multilayer perceptron and CNN models were trained to estimate the brain age from the hand-crafted features and image data, respectively. Next, both approaches were fused to assess the benefits of combining image data and hand-crafted features for brain age prediction.

Results

The combined model achieved a mean absolute error of 4 years between the chronological and predicted biological brain age. Among the independent models, the lowest mean absolute error was observed for the CNN using T1-weighted MRI data (4.2 years). When evaluating the BAGs obtained using the different approaches and imaging modalities, diverging associations between cardiovascular risk factors were found. For example, BAGs obtained from the CNN models showed an association with systolic blood pressure, while BAGs obtained from hand-crafted measurements showed greater associations with obesity markers.

Discussion

In conclusion, the use of more diverse sources of data can improve brain age estimation modeling and capture more diverse biological deviations from normal aging.

An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction

OBJECTIVE

Distributed learning avoids problems associated with central data collection by training models locally at each site. This can be achieved by federated learning (FL) aggregating multiple models that were trained in parallel or training a single model visiting sites sequentially, the traveling model (TM). While both approaches have been applied to medical imaging tasks, their performance in limited local data scenarios remains unknown. In this study, we specifically analyze FL and TM performances when very small sample sizes are available per site.

MATERIALS AND METHODS

2025 T1-weighted magnetic resonance imaging scans were used to investigate the effect of sample sizes on FL and TM for brain age prediction. We evaluated models across 18 scenarios varying the number of samples per site (1, 2, 5, 10, and 20) and the number of training rounds (20, 40, and 200).

RESULTS

Our results demonstrate that the TM outperforms FL, for every sample size examined. In the extreme case when each site provided only one sample, FL achieved a mean absolute error (MAE) of 18.9 ± 0.13 years, while the TM achieved a MAE of 6.21 ± 0.50 years, comparable to central learning (MAE = 5.99 years).

DISCUSSION

Although FL is more commonly used, our study demonstrates that TM is the best implementation for small sample sizes.

CONCLUSION

The TM offers new opportunities to apply machine learning models in rare diseases and pediatric research but also allows even small hospitals to contribute small datasets.

Fairness-related performance and explainability effects in deep learning models for brain image analysis

Purpose: Explainability and fairness are two key factors for the effective and ethical clinical implementation of deep learning-based machine learning models in healthcare settings. However, there has been limited work on investigating how unfair performance manifests in explainable artificial intelligence (XAI) methods, and how XAI can be used to investigate potential reasons for unfairness. Thus, the aim of this work was to analyze the effects of previously established sociodemographic-related confounders on classifier performance and explainability methods. Approach: A convolutional neural network (CNN) was trained to predict biological sex from T1-weighted brain MRI datasets of 4547 9- to 10-year-old adolescents from the Adolescent Brain Cognitive Development study. Performance disparities of the trained CNN between White and Black subjects were analyzed and saliency maps were generated for each subgroup at the intersection of sex and race. Results: The classification model demonstrated a significant difference in the percentage of correctly classified White male ( 90.3 % ± 1.7 % ) and Black male ( 81.1 % ± 4.5 % ) children. Conversely, slightly higher performance was found for Black female ( 89.3 % ± 4.8 % ) compared with White female ( 86.5 % ± 2.0 % ) children. Saliency maps showed subgroup-specific differences, corresponding to brain regions previously associated with pubertal development. In line with this finding, average pubertal development scores of subjects used in this study were significantly different between Black and White females ( p < 0.001 ) and males ( p < 0.001 ). Conclusions: We demonstrate that a CNN with significantly different sex classification performance between Black and White adolescents can identify different important brain regions when comparing subgroup saliency maps. Importance scores vary substantially between subgroups within brain structures associated with pubertal development, a race-associated confounder for predicting sex. We illustrate that unfair models can produce different XAI results between subgroups and that these results may explain potential reasons for biased performance.