An international study presenting a federated learning AI platform for pediatric brain tumors.

While multiple factors impact disease, artificial intelligence (AI) studies in medicine often use small, non-diverse patient cohorts due to data sharing and privacy issues. Federated learning (FL) has emerged as a solution, enabling training across hospitals without direct data sharing. Here, we present FL-PedBrain, an FL platform for pediatric posterior fossa brain tumors, and evaluate its performance on a diverse, realistic, multi-center cohort. Pediatric brain tumors were targeted due to the scarcity of such datasets, even in tertiary care hospitals. Our platform orchestrates federated training for joint tumor classification and segmentation across 19 international sites. FL-PedBrain exhibits less than a 1.5% decrease in classification and a 3% reduction in segmentation performance compared to centralized data training. FL boosts segmentation performance by 20 to 30% on three external, out-of-network sites. Finally, we explore the sources of data heterogeneity and examine FL robustness in real-world scenarios with data imbalances.

Foundation model-driven distributed learning for enhanced retinal age prediction.

OBJECTIVES: The retinal age gap (RAG) is emerging as a potential biomarker for various diseases of the human body, yet its utility depends on machine learning models capable of accurately predicting biological retinal age from fundus images. However, training generalizable models is hindered by potential shortages of diverse training data. To overcome these obstacles, this work develops a novel and computationally efficient distributed learning framework for retinal age prediction. MATERIALS AND METHODS: The proposed framework employs a memory-efficient 8-bit quantized version of RETFound, a cutting-edge foundation model for retinal image analysis, to extract features from fundus images. These features are then used to train an efficient linear regression head model for predicting retinal age. The framework explores federated learning (FL) as well as traveling model (TM) approaches for distributed training of the linear regression head. To evaluate this framework, we simulate a client network using fundus image data from the UK Biobank. Additionally, data from patients with type 1 diabetes from the UK Biobank and the Brazilian Multilabel Ophthalmological Dataset (BRSET) were utilized to explore the clinical utility of the developed methods. RESULTS: Our findings reveal that the developed distributed learning framework achieves retinal age prediction performance on par with centralized methods, with FL and TM providing similar performance (mean absolute error of 3.57 ± 0.18 years for centralized learning, 3.60 ± 0.16 years for TM, and 3.63 ± 0.19 years for FL). Notably, the TM was found to converge with fewer local updates than FL. Moreover, patients with type 1 diabetes exhibited significantly higher RAG values than healthy controls in all models, for both the UK Biobank and BRSET datasets (P < .001). DISCUSSION: The high computational and memory efficiency of the developed distributed learning framework makes it well suited for resource-constrained environments. CONCLUSION: The capacity of this framework to integrate data from underrepresented populations for training of retinal age prediction models could significantly enhance the accessibility of the RAG as an important disease biomarker.

HarmonyTM: multi-center data harmonization applied to distributed learning for Parkinson's disease classification.

Purpose: Distributed learning is widely used to comply with data-sharing regulations and access diverse datasets for training machine learning (ML) models. The traveling model (TM) is a distributed learning approach that sequentially trains with data from one center at a time, which is especially advantageous when dealing with limited local datasets. However, a critical concern emerges when centers utilize different scanners for data acquisition, which could potentially lead models to exploit these differences as shortcuts. Although data harmonization can mitigate this issue, current methods typically rely on large or paired datasets, which can be impractical to obtain in distributed setups. Approach: We introduced HarmonyTM, a data harmonization method tailored for the TM. HarmonyTM effectively mitigates bias in the model's feature representation while retaining crucial disease-related information, all without requiring extensive datasets. Specifically, we employed adversarial training to "unlearn" bias from the features used in the model for classifying Parkinson's disease (PD). We evaluated HarmonyTM using multi-center three-dimensional (3D) neuroimaging datasets from 83 centers using 23 different scanners. Results: Our results show that HarmonyTM improved PD classification accuracy from 72% to 76% and reduced (unwanted) scanner classification accuracy from 53% to 30% in the TM setup. Conclusion: HarmonyTM is a method tailored for harmonizing 3D neuroimaging data within the TM approach, aiming to minimize shortcut learning in distributed setups. This prevents the disease classifier from leveraging scanner-specific details to classify patients with or without PD-a key aspect for deploying ML models for clinical applications.

Cerebroventricular deformation and vector mapping, a topographic visualizer for surgical interventions in pediatric hydrocephalus.

OBJECTIVE: Hydrocephalus is a challenging neurosurgical condition due to nonspecific symptoms and complex brain-fluid pressure dynamics. Typically, the assessment of hydrocephalus in children requires radiographic or invasive pressure monitoring. There is usually a qualitative focus on the ventricular spaces even though stress and shear forces extend across the brain. Here, the authors present an MRI-based vector approach for voxelwise brain and ventricular deformation visualization and analysis. METHODS: Twenty pediatric patients (mean age 7.7 years, range 6 months-18 years; 14 males) with acute, newly diagnosed hydrocephalus requiring surgical intervention for symptomatic relief were randomly identified after retrospective chart review. Selection criteria included acquisition of both pre- and posttherapy paired 3D T1-weighted volumetric MRI (3D T1-MRI) performed on 3T MRI systems. Both pre- and posttherapy 3D T1-MRI pairs were aligned using image registration, and subsequently, voxelwise nonlinear transformations were performed to derive two exemplary visualizations of compliance: 1) a whole-brain vector map projecting the resulting deformation field on baseline axial imaging; and 2) a 3D heat map projecting the volumetric changes along ventricular boundaries and the brain periphery. RESULTS: The patients underwent the following interventions for treatment of hydrocephalus: endoscopic third ventriculostomy (n = 6); external ventricular drain placement and/or tumor resection (n = 10); or ventriculoperitoneal shunt placement (n = 4). The mean time between pre- and postoperative imaging was 36.5 days. Following intervention, the ventricular volumes decreased significantly (mean pre- and posttherapy volumes of 151.9 cm3 and 82.0 cm3, respectively; p < 0.001, paired t-test). The largest degree of deformation vector changes occurred along the lateral ventricular spaces, relative to the genu and splenium. There was a significant correlation between change in deformation vector magnitudes within the cortical layer and age (p = 0.011, Pearson), as well as between the ventricle size and age (p = 0.014, Pearson), suggesting higher compliance among infants and younger children. CONCLUSIONS: This study highlights an approach for deformation analysis and vector mapping that may serve as a topographic visualizer for therapeutic interventions in patients with hydrocephalus. A future study that correlates the degree of cerebroventricular deformation or compliance with intracranial pressures could clarify the potential role of this technique in noninvasive pressure monitoring or in cases of noncompliant ventricles.

Towards objective and systematic evaluation of bias in artificial intelligence for medical imaging.

OBJECTIVE: Artificial intelligence (AI) models trained using medical images for clinical tasks often exhibit bias in the form of subgroup performance disparities. However, since not all sources of bias in real-world medical imaging data are easily identifiable, it is challenging to comprehensively assess their impacts. In this article, we introduce an analysis framework for systematically and objectively investigating the impact of biases in medical images on AI models. MATERIALS AND METHODS: Our framework utilizes synthetic neuroimages with known disease effects and sources of bias. We evaluated the impact of bias effects and the efficacy of 3 bias mitigation strategies in counterfactual data scenarios on a convolutional neural network (CNN) classifier. RESULTS: The analysis revealed that training a CNN model on the datasets containing bias effects resulted in expected subgroup performance disparities. Moreover, reweighing was the most successful bias mitigation strategy for this setup. Finally, we demonstrated that explainable AI methods can aid in investigating the manifestation of bias in the model using this framework. DISCUSSION: The value of this framework is showcased in our findings on the impact of bias scenarios and efficacy of bias mitigation in a deep learning model pipeline. This systematic analysis can be easily expanded to conduct further controlled in silico trials in other investigations of bias in medical imaging AI. CONCLUSION: Our novel methodology for objectively studying bias in medical imaging AI can help support the development of clinical decision-support tools that are robust and responsible.

Children with Congenital Heart Diseases Exhibit Altered Deep Gray Matter Structures.

BACKGROUND AND OBJECTIVES: Children with congenital heart diseases (CHDs) have an increased risk of developing neurologic deficits, even in the absence of apparent brain pathology. The aim of this work was to compare quantitative macro- and microstructural properties of subcortical gray matter structures of pediatric CHD patients with normal appearing brain magnetic resonance imaging to healthy controls. METHODS: We retrospectively reviewed children with coarctation of the aorta (COA) and hypoplastic left heart syndrome (HLHS) admitted to our hospital. We identified 24 pediatric CHD patients (17 COA, 7 HLHS) with normal-appearing brain MRI. Using an atlas-based approach, the volume and apparent diffusion coefficient (ADC) were determined for the thalamus, caudate, putamen, pallidum, hippocampus, amygdala, nucleus accumbens, cerebral white matter, cerebral cortex, and brainstem. Multivariate statistics were used to compare the extracted values to reference values from 100 typically developing children without any known cardiac or neurological diseases. RESULTS: Multivariate analysis of covariance using the regional ADC and volume values as dependent variables and age and sex as co-variates revealed a significant difference between pediatric CHD patients and healthy controls (p < 0.001). Post-hoc comparisons demonstrated significantly reduced brain volumes in most subcortical brain regions investigated and elevated ADC values in the thalamus for children with CHD. No significant differences were found comparing children with COA and HLHS. CONCLUSIONS: Despite normal appearing brain MRI, children with CHD exhibit wide-spread macro-structural and regional micro-structural differences of subcortical brain structures compared to healthy controls, which could negatively impact neurodevelopment, leading to neurological deficits in childhood and beyond.

Visual Functions Are Associated with Biomarker Changes in Alzheimer's Disease.

Background: While various biomarkers of Alzheimer's disease (AD) have been associated with general cognitive function, their association to visual-perceptive function across the AD spectrum warrant more attention due to its significant impact on quality of life. Thus, this study explores how AD biomarkers are associated with decline in this cognitive domain. Objective: To explore associations between various fluid and imaging biomarkers and visual-based cognitive assessments in participants across the AD spectrum. Methods: Data from participants (N = 1,460) in the Alzheimer's Disease Neuroimaging Initiative were analyzed, including fluid and imaging biomarkers. Along with the Mini-Mental State Examination (MMSE), three specific visual-based cognitive tests were investigated: Trail Making Test (TMT) A and TMT B, and the Boston Naming Test (BNT). Locally estimated scatterplot smoothing curves and Pearson correlation coefficients were used to examine associations. Results: MMSE showed the strongest correlations with most biomarkers, followed by TMT-B. The p-tau181/Aß1-42 ratio, along with the volume of the hippocampus and entorhinal cortex, had the strongest associations among the biomarkers. Conclusions: Several biomarkers are associated with visual processing across the disease spectrum, emphasizing their potential in assessing disease severity and contributing to progression models of visual function and cognition.

Sex and age effects on gray matter volume trajectories in young children with prenatal alcohol exposure.

Prenatal alcohol exposure (PAE) occurs in ~11% of North American pregnancies and is the most common known cause of neurodevelopmental disabilities such as fetal alcohol spectrum disorder (FASD; ~2-5% prevalence). PAE has been consistently associated with smaller gray matter volumes in children, adolescents, and adults. A small number of longitudinal studies show altered gray matter development trajectories in late childhood/early adolescence, but patterns in early childhood and potential sex differences have not been characterized in young children. Using longitudinal T1-weighted MRI, the present study characterized gray matter volume development in young children with PAE (N = 42, 84 scans, ages 3-8 years) compared to unexposed children (N = 127, 450 scans, ages 2-8.5 years). Overall, we observed altered global and regional gray matter development trajectories in the PAE group, wherein they had attenuated age-related increases and more volume decreases relative to unexposed children. Moreover, we found more pronounced sex differences in children with PAE; females with PAE having the smallest gray matter volumes and the least age-related changes of all groups. This pattern of altered development may indicate reduced brain plasticity and/or accelerated maturation and may underlie the cognitive/behavioral difficulties often experienced by children with PAE. In conjunction with previous research on older children, adolescents, and adults with PAE, our results suggest that gray matter volume differences associated with PAE vary by age and may become more apparent in older children.

Prediction of tissue outcome in acute ischemic stroke based on single-phase CT angiography at admission.

Introduction: In acute ischemic stroke, prediction of the tissue outcome after reperfusion can be used to identify patients that might benefit from mechanical thrombectomy (MT). The aim of this work was to develop a deep learning model that can predict the follow-up infarct location and extent exclusively based on acute single-phase computed tomography angiography (CTA) datasets. In comparison to CT perfusion (CTP), CTA imaging is more widely available, less prone to artifacts, and the established standard of care in acute stroke imaging protocols. Furthermore, recent RCTs have shown that also patients with large established infarctions benefit from MT, which might not have been selected for MT based on CTP core/penumbra mismatch analysis. Methods: All patients with acute large vessel occlusion of the anterior circulation treated at our institution between 12/2015 and 12/2020 were screened (N = 404) and 238 patients undergoing MT with successful reperfusion were included for final analysis. Ground truth infarct lesions were segmented on 24 h follow-up CT scans. Pre-processed CTA images were used as input for a U-Net-based convolutional neural network trained for lesion prediction, enhanced with a spatial and channel-wise squeeze-and-excitation block. Post-processing was applied to remove small predicted lesion components. The model was evaluated using a 5-fold cross-validation and a separate test set with Dice similarity coefficient (DSC) as the primary metric and average volume error as the secondary metric. Results: The mean ± standard deviation test set DSC over all folds after post-processing was 0.35 ± 0.2 and the mean test set average volume error was 11.5 mL. The performance was relatively uniform across models with the best model according to the DSC achieved a score of 0.37 ± 0.2 after post-processing and the best model in terms of average volume error yielded 3.9 mL. Conclusion: 24 h follow-up infarct prediction using acute CTA imaging exclusively is feasible with DSC measures comparable to results of CTP-based algorithms reported in other studies. The proposed method might pave the way to a wider acceptance, feasibility, and applicability of follow-up infarct prediction based on artificial intelligence.

Annotation-free prediction of treatment-specific tissue outcome from 4D CT perfusion imaging in acute ischemic stroke.

Acute ischemic stroke is a critical health condition that requires timely intervention. Following admission, clinicians typically use perfusion imaging to facilitate treatment decision-making. While deep learning models leveraging perfusion data have demonstrated the ability to predict post-treatment tissue infarction for individual patients, predictions are often represented as binary or probabilistic masks that are not straightforward to interpret or easy to obtain. Moreover, these models typically rely on large amounts of subjectively segmented data and non-standard perfusion analysis techniques. To address these challenges, we propose a novel deep learning approach that directly predicts follow-up computed tomography images from full spatio-temporal 4D perfusion scans through a temporal compression. The results show that this method leads to realistic follow-up image predictions containing the infarcted tissue outcomes. The proposed compression method achieves comparable prediction results to using perfusion maps as inputs but without the need for perfusion analysis or arterial input function selection. Additionally, separate models trained on 45 patients treated with thrombolysis and 102 treated with thrombectomy showed that each model correctly captured the different patient-specific treatment effects as shown by image difference maps. The findings of this work clearly highlight the potential of our method to provide interpretable stroke treatment decision support without requiring manual annotations.

A multi-center distributed learning approach for Parkinson's disease classification using the traveling model paradigm.

Distributed learning is a promising alternative to central learning for machine learning (ML) model training, overcoming data-sharing problems in healthcare. Previous studies exploring federated learning (FL) or the traveling model (TM) setup for medical image-based disease classification often relied on large databases with a limited number of centers or simulated artificial centers, raising doubts about real-world applicability. This study develops and evaluates a convolution neural network (CNN) for Parkinson's disease classification using data acquired by 83 diverse real centers around the world, mostly contributing small training samples. Our approach specifically makes use of the TM setup, which has proven effective in scenarios with limited data availability but has never been used for image-based disease classification. Our findings reveal that TM is effective for training CNN models, even in complex real-world scenarios with variable data distributions. After sufficient training cycles, the TM-trained CNN matches or slightly surpasses the performance of the centrally trained counterpart (AUROC of 83% vs. 80%). Our study highlights, for the first time, the effectiveness of TM in 3D medical image classification, especially in scenarios with limited training samples and heterogeneous distributed data. These insights are relevant for situations where ML models are supposed to be trained using data from small or remote medical centers, and rare diseases with sparse cases. The simplicity of this approach enables a broad application to many deep learning tasks, enhancing its clinical utility across various contexts and medical facilities.

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.

Identifying Biases in a Multicenter MRI Database for Parkinson's Disease Classification: Is the Disease Classifier a Secret Site Classifier?

Sharing multicenter imaging datasets can be advantageous to increase data diversity and size but may lead to spurious correlations between site-related biological and non-biological image features and target labels, which machine learning (ML) models may exploit as shortcuts. To date, studies analyzing how and if deep learning models may use such effects as a shortcut are scarce. Thus, the aim of this work was to investigate if site-related effects are encoded in the feature space of an established deep learning model designed for Parkinson's disease (PD) classification based on T1-weighted MRI datasets. Therefore, all layers of the PD classifier were frozen, except for the last layer of the network, which was replaced by a linear layer that was exclusively re-trained to predict three potential bias types (biological sex, scanner type, and originating site). Our findings based on a large database consisting of 1880 MRI scans collected across 41 centers show that the feature space of the established PD model (74% accuracy) can be used to classify sex (75% accuracy), scanner type (79% accuracy), and site location (71% accuracy) with high accuracies despite this information never being explicitly provided to the PD model during original training. Overall, the results of this study suggest that trained image-based classifiers may use unwanted shortcuts that are not meaningful for the actual clinical task at hand. This finding may explain why many image-based deep learning models do not perform well when applied to data from centers not contributing to the training set.

Challenges and Potential of Artificial Intelligence in Neuroradiology.

PURPOSE: Artificial intelligence (AI) has emerged as a transformative force in medical research and is garnering increased attention in the public consciousness. This represents a critical time period in which medical researchers, healthcare providers, insurers, regulatory agencies, and patients are all developing and shaping their beliefs and policies regarding the use of AI in the healthcare sector. The successful deployment of AI will require support from all these groups. This commentary proposes that widespread support for medical AI must be driven by clear and transparent scientific reporting, beginning at the earliest stages of scientific research. METHODS: A review of relevant guidelines and literature describing how scientific reporting plays a central role at key stages in the life cycle of an AI software product was conducted. To contextualize this principle within a specific medical domain, we discuss the current state of predictive tissue outcome modeling in acute ischemic stroke and the unique challenges presented therein. RESULTS AND CONCLUSION: Translating AI methods from the research to the clinical domain is complicated by challenges related to model design and validation studies, medical product regulations, and healthcare providers' reservations regarding AI's efficacy and affordability. However, each of these limitations is also an opportunity for high-impact research that will help to accelerate the clinical adoption of state-of-the-art medical AI. In all cases, establishing and adhering to appropriate reporting standards is an important responsibility that is shared by all of the parties involved in the life cycle of a prospective AI software product.

Multimodal imaging measures in the prediction of clinical response to deep brain stimulation for refractory depression: A machine learning approach.

OBJECTIVES: This study compared machine learning models using unimodal imaging measures and combined multi-modal imaging measures for deep brain stimulation (DBS) outcome prediction in treatment resistant depression (TRD). METHODS: Regional brain glucose metabolism (CMRGlu), cerebral blood flow (CBF), and grey matter volume (GMV) were measured at baseline using 18F-fluorodeoxy glucose (18F-FDG) positron emission tomography (PET), arterial spin labelling (ASL) magnetic resonance imaging (MRI), and T1-weighted MRI, respectively, in 19 patients with TRD receiving subcallosal cingulate (SCC)-DBS. Responders (n = 9) were defined by a 50% reduction in HAMD-17 at 6 months from the baseline. Using an atlas-based approach, values of each measure were determined for pre-selected brain regions. OneR feature selection algorithm and the naïve Bayes model was used for classification. Leave-out-one cross validation was used for classifier evaluation. RESULTS: The performance accuracy of the CMRGlu classification model (84%) was greater than CBF (74%) or GMV (74%) models. The classification model using the three image modalities together led to a similar accuracy (84%0 compared to the CMRGlu classification model. CONCLUSIONS: CMRGlu imaging measures may be useful for the development of multivariate prediction models for SCC-DBS studies for TRD. The future of multivariate methods for multimodal imaging may rest on the selection of complementing features and the developing better models.Clinical Trial Registration: ClinicalTrials.gov (#NCT01983904).

An interactive atlas of three-dimensional syndromic facial morphology.

Craniofacial phenotyping is critical for both syndrome delineation and diagnosis because craniofacial abnormalities occur in 30% of characterized genetic syndromes. Clinical reports, textbooks, and available software tools typically provide two-dimensional, static images and illustrations of the characteristic phenotypes of genetic syndromes. In this work, we provide an interactive web application that provides three-dimensional, dynamic visualizations for the characteristic craniofacial effects of 95 syndromes. Users can visualize syndrome facial appearance estimates quantified from data and easily compare craniofacial phenotypes of different syndromes. Our application also provides a map of morphological similarity between a target syndrome and other syndromes. Finally, users can upload 3D facial scans of individuals and compare them to our syndrome atlas estimates. In summary, we provide an interactive reference for the craniofacial phenotypes of syndromes that allows for precise, individual-specific comparisons of dysmorphology.

Providing clinical context to the spatio-temporal analysis of 4D CT perfusion to predict acute ischemic stroke lesion outcomes.

Acute ischemic stroke is a leading cause of mortality and morbidity worldwide. Timely identification of the extent of a stroke is crucial for effective treatment, whereas spatio-temporal (4D) Computed Tomography Perfusion (CTP) imaging is playing a critical role in this process. Recently, the first deep learning-based methods that leverage the full spatio-temporal nature of perfusion imaging for predicting stroke lesion outcomes have been proposed. However, clinical information is typically not integrated into the learning process, which may be helpful to improve the tissue outcome prediction given the known influence of various factors (i.e., physiological, demographic, and treatment factors) on lesion growth. Cross-attention, a multimodal fusion strategy, has been successfully used to combine information from multiple sources, but it has yet to be applied to stroke lesion outcome prediction. Therefore, this work aimed to develop and evaluate a novel multimodal and spatio-temporal deep learning model that utilizes cross-attention to combine information from 4D CTP and clinical metadata simultaneously to predict stroke lesion outcomes. The proposed model was evaluated using a dataset of 70 acute ischemic stroke patients, demonstrating significantly improved volume estimates (mean error = 19 ml) compared to a baseline unimodal approach (mean error = 35 ml, p< 0.05). The proposed model allows generating attention maps and counterfactual outcome scenarios to investigate the relevance of clinical variables in predicting stroke lesion outcomes at a patient level, helping to provide a better understanding of the model's decision-making process.

Simulation of neuroplasticity in a CNN-based in-silico model of neurodegeneration of the visual system.

The aim of this work was to enhance the biological feasibility of a deep convolutional neural network-based in-silico model of neurodegeneration of the visual system by equipping it with a mechanism to simulate neuroplasticity. Therefore, deep convolutional networks of multiple sizes were trained for object recognition tasks and progressively lesioned to simulate neurodegeneration of the visual cortex. More specifically, the injured parts of the network remained injured while we investigated how the added retraining steps were able to recover some of the model's object recognition baseline performance. The results showed with retraining, model object recognition abilities are subject to a smoother and more gradual decline with increasing injury levels than without retraining and, therefore, more similar to the longitudinal cognition impairments of patients diagnosed with Alzheimer's disease (AD). Moreover, with retraining, the injured model exhibits internal activation patterns similar to those of the healthy baseline model when compared to the injured model without retraining. Furthermore, we conducted this analysis on a network that had been extensively pruned, resulting in an optimized number of parameters or synapses. Our findings show that this network exhibited remarkably similar capability to recover task performance with decreasingly viable pathways through the network. In conclusion, adding a retraining step to the in-silico setup that simulates neuroplasticity improves the model's biological feasibility considerably and could prove valuable to test different rehabilitation approaches in-silico.

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.

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.