Multi-scale radiomic analysis of sub-cortical regions in MRI related to autism, gender and age

Using visual attention estimation on videos for automated prediction of autism spectrum disorder and symptom severity in preschool children

Atypical visual attention in individuals with autism spectrum disorders (ASD) has been utilised as a unique diagnosis criterion in previous research. This paper presents a novel approach to the automatic and quantitative screening of ASD as well as symptom severity prediction in preschool children. We develop a novel computational pipeline that extracts learned features from a dynamic visual stimulus to classify ASD children and predict the level of ASD-related symptoms. Experimental results demonstrate promising performance that is superior to using handcrafted features and machine learning algorithms, in terms of evaluation metrics used in diagnostic tests. Using a leave-one-out cross-validation approach, we obtained an accuracy of 94.59%, a sensitivity of 100%, a specificity of 76.47% and an area under the receiver operating characteristic curve (AUC) of 96% for ASD classification. In addition, we obtained an accuracy of 94.74%, a sensitivity of 87.50%, a specificity of 100% and an AUC of 99% for ASD symptom severity prediction.

A comprehensive analysis towards exploring the promises of AI-related approaches in autism research

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that presents challenges in communication, social interaction, repetitive behaviour, and limited interests. Detecting ASD at an early stage is crucial for timely interventions and an improved quality of life. In recent times, Artificial Intelligence (AI) has been increasingly used in ASD research. The rise in ASD diagnoses is due to the growing number of ASD cases and the recognition of the importance of early detection, which leads to better symptom management. This study explores the potential of AI in identifying early indicators of autism, aligning with the United Nations Sustainable Development Goals (SDGs) of Good Health and Well-being (Goal 3) and Peace, Justice, and Strong Institutions (Goal 16). The paper aims to provide a comprehensive overview of the current state-of-the-art AI-based autism classification by reviewing recent publications from the last decade. It covers various modalities such as Eye gaze, Facial Expression, Motor skill, MRI/fMRI, and EEG, and multi-modal approaches primarily grouped into behavioural and biological markers. The paper presents a timeline spanning from the history of ASD to recent developments in the field of AI. Additionally, the paper provides a category-wise detailed analysis of the AI-based application in ASD with a diagrammatic summarization to convey a holistic summary of different modalities. It also reports on the successes and challenges of applying AI for ASD detection while providing publicly available datasets. The paper paves the way for future scope and directions, providing a complete and systematic overview for researchers in the field of ASD.

Diagnostic performance of MRI radiomics for classification of Alzheimer's disease, mild cognitive impairment, and normal subjects: a systematic review and meta-analysis

BACKGROUND

Alzheimer's disease (AD) is a debilitating neurodegenerative disease. Early diagnosis of AD and its precursor, mild cognitive impairment (MCI), is crucial for timely intervention and management. Radiomics involves extracting quantitative features from medical images and analyzing them using advanced computational algorithms. These characteristics have the potential to serve as biomarkers for disease classification, treatment response prediction, and patient stratification. Of note, Magnetic resonance imaging (MRI) radiomics showed a promising result for diagnosing and classifying AD, and MCI from normal subjects. Thus, we aimed to systematically evaluate the diagnostic performance of the MRI radiomics for this task.

METHODS AND MATERIALS

A comprehensive search of the current literature was conducted using relevant keywords in PubMed/MEDLINE, Embase, Scopus, and Web of Science databases from inception to August 5, 2023. Original studies discussing the diagnostic performance of MRI radiomics for the classification of AD, MCI, and normal subjects were included. Method quality was evaluated with the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) and the Radiomics Quality Score (RQS) tools.

RESULTS

We identified 13 studies that met the inclusion criteria, involving a total of 5448 participants. The overall quality of the included studies was moderate to high. The pooled sensitivity and specificity of MRI radiomics for differentiating AD from normal subjects were 0.92 (95% CI [0.85; 0.96]) and 0.91 (95% CI [0.85; 0.95]), respectively. The pooled sensitivity and specificity of MRI radiomics for differentiating MCI from normal subjects were 0.74 (95% CI [0.60; 0.85]) and 0.79 (95% CI [0.70; 0.86]), respectively. Also, the pooled sensitivity and specificity of MRI radiomics for differentiating AD from MCI were 0.73 (95% CI [0.64; 0.80]) and 0.79 (95% CI [0.64; 0.90]), respectively.

CONCLUSION

MRI radiomics has promising diagnostic performance in differentiating AD, MCI, and normal subjects. It can potentially serve as a non-invasive and reliable tool for early diagnosis and classification of AD and MCI.

Amygdala's T1-weighted image radiomics outperforms volume for differentiation of anxiety disorder and its subtype

INTRODUCTION

Anxiety disorder is the most common psychiatric disorder among adolescents, with generalized anxiety disorder (GAD) being a common subtype of anxiety disorder. Current studies have revealed abnormal amygdala function in patients with anxiety compared with healthy people. However, the diagnosis of anxiety disorder and its subtypes still lack specific features of amygdala from T1-weighted structural magnetic resonance (MR) imaging. The purpose of our study was to investigate the feasibility of using radiomics approach to distinguish anxiety disorder and its subtype from healthy controls on T1-weighted images of the amygdala, and provide a basis for the clinical diagnosis of anxiety disorder.

METHODS

T1-weighted MR images of 200 patients with anxiety disorder (including 103 GAD patients) as well as 138 healthy controls were obtained in the Healthy Brain Network (HBN) dataset. We extracted 107 radiomics features for the left and right amygdala, respectively, and then performed feature selection using the 10-fold LASSO regression algorithm. For the selected features, we performed group-wise comparisons, and use different machine learning algorithms, including linear kernel support vector machine (SVM), to achieve the classification between the patients and healthy controls.

RESULTS

For the classification task of anxiety patients vs. healthy controls, 2 and 4 radiomics features were selected from left and right amygdala, respectively, and the area under receiver operating characteristic curve (AUC) of linear kernel SVM in cross-validation experiments was 0.6739±0.0708 for the left amygdala features and 0.6403±0.0519 for the right amygdala features; for classification task for GAD patients vs. healthy controls, 7 and 3 features were selected from left and right amygdala, respectively, and the cross-validation AUCs were 0.6755±0.0615 for the left amygdala features and 0.6966±0.0854 for the right amygdala features. In both classification tasks, the selected amygdala radiomics features had higher discriminatory significance and effect sizes compared with the amygdala volume.

DISCUSSION

Our study suggest that radiomics features of bilateral amygdala potentially could serve as a basis for the clinical diagnosis of anxiety disorder.

Torasemide Improves the Propionic Acid-Induced Autism in Rats: A Histopathological and Imaging Study

Objective

Autism spectrum disorder is a neurodevelopmental disease in which impaired social behaviors, impaired sociality, and restricted and repetitive behaviors are seen. Bumetanide is a loop diuretic that inhibits Na⁺-K⁺-2Cl^- cotransporter 1 and it is currently used in clinical phase studies in patients with autism spectrum disorder. In present research, it is purposed to demonstrate the beneficial effects of torasemide which is another Na⁺-K⁺-2Cl^- cotransporter 1 inhibitor on an experimental autism model induced with propionic acid by providing imaging and brain tissue investigations.

Methods

Male Wistar rats were used in the present study (n = 30). Propionic acid of 250 mg/kg/day was administrated intraperitoneally in rats to induce autism for 5 days. Three groups were created for present study as follows: group 1, normal control (n = 10); group 2, propionic acid and saline given group (n = 10); group 3, propionic acid + tora-semide-administrated group (n = 10).

Results

Torasemide group scored higher on behavioral tests compared to saline group. The brain levels of malondialdehyde, tumor necrosis factor-alpha, interleukin-2, interleukin-17, and Nuclear Factor kappa B (NF-κB), Glial fibrillary acidic protein (GFAP) were remarkably higher in propionic acid + saline group. In histopathology assessments, torasemide group had higher neuronal count of Cornu Ammonis 1, neuronal count of Cornu Ammonis 2 in hippocampus, and Purkinje cells in cerebellum. GFAP immunostaining index (Cornu Ammonis 1) and cerebellum were lower in torasemide group. Magnetic resonance spectroscopy revealed that mean lactate value was higher in propionic acid + saline group compared to torasemide group.

Conclusion

Our experimental results showed that torasemide might enhance gamma-aminobutyric acid activity. Torasemide can be considered another promising Na⁺-K⁺-2Cl^- cotransporter 1 inhibitor in the treatment of autism with a longer half-life and less side effects after further studies.

Evaluation of the corpus callosum using magnetic resonance imaging histogram analysis in autism spectrum disorder

BACKGROUND

Histogram analysis is a texture analysis method that can be used in medical images. Quantitative values of the intensity of images can be obtained with histogram analysis. It aimed to evaluate corpus callosum in magnetic resonance images (MRIs) using histogram analysis of pediatric patients with autism spectrum disorder (ASD) to compare them with healthy controls.

METHODS

This study included 29 children with ASD and 29 healthy children with normal brain MRI. High-resolution three-dimensional turbo field echo images were obtained with a 1.5 T scanner device for brain magnetic resonance imaging. On the corpus callosum in the sagittal T1-weighted images obtained, mean gray level density (mean), the standard deviation, median, minimum, maximum, entropy, variance, skewness, kurtosis, uniformity, size % L, size % M, size % U, and percentile parameters were measured.

RESULTS

In ASD patients, mean, standard deviation, maximum, median, variance, entropy, 25%, 75%, 90%, 97%, and 99% values were found to be lower than the control group, and size % U value was higher. In addition, the corpus callosum area was significantly lower in the ASD compared to the controls.

CONCLUSION

According to our study, corpus callosum of patients with ASD showed differences compared to healthy controls by histogram analysis, even though they were seen as normal in brain MRI. We think that histogram analysis can be used to evaluate possibly affected areas of brain in ASD patients.

Identification of texture MRI brain abnormalities on first-episode psychosis and clinical high-risk subjects using explainable artificial intelligence

Structural MRI studies in first-episode psychosis and the clinical high-risk state have consistently shown volumetric abnormalities. Aim of the present study was to introduce radiomics texture features in identification of psychosis. Radiomics texture features describe the interrelationship between voxel intensities across multiple spatial scales capturing the hidden information of underlying disease dynamics in addition to volumetric changes. Structural MR images were acquired from 77 first-episode psychosis (FEP) patients, 58 clinical high-risk subjects with no later transition to psychosis (CHR_NT), 15 clinical high-risk subjects with later transition (CHR_T), and 44 healthy controls (HC). Radiomics texture features were extracted from non-segmented images, and two-classification schemas were performed for the identification of FEP vs. HC and FEP vs. CHR_NT. The group of CHR_T was used as external validation in both schemas. The classification of a subject's clinical status was predicted by importing separately (a) the difference of entropy feature map and (b) the contrast feature map, resulting in classification balanced accuracy above 72% in both analyses. The proposed framework enhances the classification decision for FEP, CHR_NT, and HC subjects, verifies diagnosis-relevant features and may potentially contribute to identification of structural biomarkers for psychosis, beyond and above volumetric brain changes.

Deconstructing the functional neuroanatomy of the choroid plexus: an ontogenetic perspective for studying neurodevelopmental and neuropsychiatric disorders

The choroid plexus (CP) is a delicate and highly vascularized structure in the brain comprised of a dense network of fenestrated capillary loops that help in the synthesis, secretion and circulation of cerebrospinal fluid (CSF). This unique neuroanatomical structure is comprised of arachnoid villi stemming from frond-like surface projections-that protrude into the lumen of the four cerebral ventricles-providing a key source of nutrients to the brain parenchyma in addition to serving as a 'sink' for central nervous system metabolic waste. In fact, the functions of the CP are often described as being analogous to those of the liver and kidney. Beyond forming a barrier/interface between the blood and CSF compartments, the CP has been identified as a modulator of leukocyte trafficking, inflammation, cognition, circadian rhythm and the gut brain-axis. In recent years, advances in molecular biology techniques and neuroimaging along with the use of sophisticated animal models have played an integral role in shaping our understanding of how the CP-CSF system changes in relation to the maturation of neural circuits during critical periods of brain development. In this article we provide an ontogenetic perspective of the CP and review the experimental evidence implicating this structure in the pathophysiology of neurodevelopmental and neuropsychiatric disorders.

Improving reproducibility and performance of radiomics in low-dose CT using cycle GANs

Background

As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low‐dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics’ reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect.

Purpose

In this article, we investigate the possibility of denoising low‐dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets.

Methods and materials

Two cycle GANs were trained: (1) from paired data, by simulating low‐dose CTs (i.e., introducing noise) from high‐dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice‐paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low‐dose CT images and (2) same‐day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder–decoder network (EDN) trained on simulated paired data.

Results

The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833,0.901]) to 0.93 (95%CI, [0.916,0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881,0.914]) to 0.92 (95%CI, [0.908,0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511,0.538]) to 0.59 (95%CI, [0.578,0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933,0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576,0.596]).

Conclusion

The results show that cycle GANs trained on both simulated and real data can improve radiomics’ reproducibility and performance in low‐dose CT and achieve similar results compared to CGANs and EDNs.

Ketamine administration in early postnatal life as a tool for mimicking Autism Spectrum Disorders core symptoms

Autism Spectrum Disorders (ASD) core symptoms include deficits of social interaction, stereotyped behaviours, dysfunction in language and communication. Beyond them, several additional symptoms, such as cognitive impairment, anxiety-like states and hyperactivity are often occurring, mainly overlapping with other neuropsychiatric diseases. To untangle mechanisms underlying ASD etiology, and to identify possible pharmacological approaches, different factors, such as environmental, immunological and genetic ones, need to be considered. In this context, ASD animal models, aiming to reproduce the wide range of behavioural phenotypes of this uniquely human disorder, represent a very useful tool. Ketamine administration in early postnatal life of mice has already been studied as a suitable animal model resembling psychotic-like symptoms. Here, we investigated whether ketamine administration, at postnatal days 7, 9 and 11, might induce behavioural features able to mimic ASD typical symptoms in adult mice. To this aim, we developed a 4-days behavioural tests battery, including Marble Burying, Hole Board, Olfactory and Social tests, to assess repetitive and stereotyped behaviour, social deficits and anxiety-like symptoms. Moreover, by using this mouse model, we performed neurochemical and biomolecular analyses, quantifying neurotransmitters belonging to excitatory-inhibitory pathways, such as glutamate, glutamine and gamma-aminobutyric acid (GABA), as well as immune activation biomarkers related to ASD, such as CD11b and glial fibrillary acidic protein (GFAP), in the hippocampus and amygdala. Possible alterations in levels of brain-derived neurotrophic factor (BDNF) expression in the hippocampus and amygdala were also evaluated. Our results showed an increase in stereotyped behaviours, together with social impairments and anxiety-like behaviour in adult mice, receiving ketamine administration in early postnatal life. In addition, we found decreased BDNF and enhanced GFAP hippocampal expression levels, accompanied by elevations in glutamate amount, as well as reduction in GABA content in amygdala and hippocampus. In conclusion, early ketamine administration may represent a suitable animal model of ASD, exhibiting face validity to mimic specific ASD symptoms, such as social deficits, repetitive repertoire and anxiety-like behaviour.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

Early Detection of Medical Image Analysis by Using Machine Learning Method

We develop effective medical image classification techniques, with an emphasis on histopathology and magnetic resonance imaging (MRI). The trainer utilized the curriculum as a starting point for a set of data and a restricted number of samples, and we used it as a starting point for a set of data. As calibrating a machine learning model is difficult, we used alternative methods as unsupervised feature extracts or weight-conditioning factors for identifying pathological histology pictures. As a result, the pretrained models will be trained on 3-channel RGB pictures, while the MRI sample has more slices. To alter the working model using the MRI data, the convolutional neural network (CNN) must be fine-tuned. Pretrained models are placed and then used as feature snippets. However, there is a scarcity of well-done medical photos, making training machine learning models a difficult endeavor to begin with. In any case, data augmentation aids in the generation of sufficient training samples; however, it is unclear if data augmentation aids in the prediction of unknown data samples. As a result, we fine-tuned machine learning models without using any additional data. Furthermore, rather than utilizing a standard machine learning classifier for the MRI data, we created a unique CNN that uses both 3D shear descriptors and deep features as input. This custom network identifies the MRI sample after processing our representation of the characteristics from beginning to end. On the hidden MRI dataset, our bespoke CNN outperforms traditional machine learning. Our CNN model is less prone to overfitting as a result of this. Furthermore, we have given cutting-edge outcomes employing machine learning.

Differences in the choroid plexus volume and microstructure are associated with body adiposity

The choroid plexus (CP) is a cerebral structure located in the ventricles that functions in producing most of the brain's cerebrospinal fluid (CSF) and transporting proteins and immune cells. Alterations in CP structure and function has been implicated in several pathologies including aging, multiple sclerosis, Alzheimer's disease, and stroke. However, identification of changes in the CP remains poorly characterized in obesity, one of the main risk factors of neurodegeneration, including in the absence of frank central nervous system alterations. Our goal here was to characterize the association between obesity, measured by the body mass index (BMI) or waist circumference (WC) metrics, and CP microstructure and volume, assessed using advanced magnetic resonance imaging (MRI) methodology. This cross-sectional study was performed in the clinical unit of the National Institute on Aging and included a participant population of 123 cognitively unimpaired individuals spanning the age range of 22 - 94 years. Automated segmentation methods from FreeSurfer were used to identify the CP structure. Our analysis included volumetric measurements, quantitative relaxometry measures (T ₁ and T ₂), and the diffusion tensor imaging (DTI) measure of mean diffusivity (MD). Strong positive associations were observed between WC and all MRI metrics, as well as CP volume. When comparing groups based on the established cutoff point by the National Institutes of Health for WC, a modest difference in MD and a significant difference in T ₁ values were observed between obese and lean individuals. We also found differences in T1 and MD between obese and overweight individuals as defined using the BMI cutoff. We conjecture that these observations in CP volume and microstructure are due to obesity-induced inflammation, diet, or, very likely, dysregulations in leptin binding and transport. These findings demonstrate that obesity is strongly associated with a decline in CP microstructural integrity. We expect that this work will lay the foundation for further investigations on obesity-induced alterations in CP structure and function.

A Systematic Review of Brainstem Contributions to Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that affects one in 66 children in Canada. The contributions of changes in the cortex and cerebellum to autism have been studied for decades. However, our understanding of brainstem contributions has only started to emerge more recently. Disruptions of sensory processing, startle response, sensory filtering, sensorimotor gating, multisensory integration and sleep are all features of ASD and are processes in which the brainstem is involved. In addition, preliminary research into brainstem contribution emphasizes the importance of the developmental timeline rather than just the mature brainstem. Therefore, the purpose of this systematic review is to compile histological, behavioral, neuroimaging, and electrophysiological evidence from human and animal studies about brainstem contributions and their functional implications in autism. Moreover, due to the developmental nature of autism, the review pays attention to the atypical brainstem development and compares findings based on age. Overall, there is evidence of an important role of brainstem disruptions in ASD, but there is still the need to examine the brainstem across the life span, from infancy to adulthood which could lead the way for early diagnosis and possibly treatment of ASD.

Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks such as autism spectrum disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to the variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and healthy control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.

Deep Multimodal Learning From MRI and Clinical Data for Early Prediction of Neurodevelopmental Deficits in Very Preterm Infants

The prevalence of disabled survivors of prematurity has increased dramatically in the past 3 decades. These survivors, especially, very preterm infants (VPIs), born ≤ 32 weeks gestational age, are at high risk for neurodevelopmental impairments. Early and clinically effective personalized prediction of outcomes, which forms the basis for early treatment decisions, is urgently needed during the peak neuroplasticity window—the first couple of years after birth—for at-risk infants, when intervention is likely to be most effective. Advances in MRI enable the noninvasive visualization of infants' brains through acquired multimodal images, which are more informative than unimodal MRI data by providing complementary/supplementary depicting of brain tissue characteristics and pathology. Thus, analyzing quantitative multimodal MRI features affords unique opportunities to study early postnatal brain development and neurodevelopmental outcome prediction in VPIs. In this study, we investigated the predictive power of multimodal MRI data, including T2-weighted anatomical MRI, diffusion tensor imaging, resting-state functional MRI, and clinical data for the prediction of neurodevelopmental deficits. We hypothesize that integrating multimodal MRI and clinical data improves the prediction over using each individual data modality. Employing the aforementioned multimodal data, we proposed novel end-to-end deep multimodal models to predict neurodevelopmental (i.e., cognitive, language, and motor) deficits independently at 2 years corrected age. We found that the proposed models can predict cognitive, language, and motor deficits at 2 years corrected age with an accuracy of 88.4, 87.2, and 86.7%, respectively, significantly better than using individual data modalities. This current study can be considered as proof-of-concept. A larger study with external validation is important to validate our approach to further assess its clinical utility and overall generalizability.

Characterization of Age-Related Differences in the Human Choroid Plexus Volume, Microstructural Integrity, and Blood Perfusion Using Multiparameter Magnetic Resonance Imaging

The choroid plexus (CP) is an important cerebral structure involved in cerebrospinal fluid production and transport of solutes into the brain. Recent studies have uncovered the involvement of the CP in neurological disorders such as Alzheimer's disease and multiple sclerosis. However, our understanding of human age-related microstructural and functional changes in the CP with aging and neuropathology is limited. In this cross-sectional study, we investigated age and sex differences in the CP structure and function using advanced quantitative magnetic resonance imaging methodology in a large cohort (n = 155) of cognitively unimpaired individuals over a wide age range between 21 and 94 years. Our analysis included volumetric measurements, relaxometry measures (T 1 and T 2), diffusion tensor imaging (DTI) measures of fractional anisotropy (FA) and mean diffusivity (MD), as well as measures of cerebral blood flow (CBF). Our results revealed that CP volume was increasing with advancing age. We conjecture that this novel observation is likely attributed to alterations in the CP microstructure or function as well as to ventriculomegaly. Indeed, we also found that CBF was lower with advanced age, while, consistent with previous studies, T 1, T 2 and MD were higher, and FA was lower with advanced age. We attribute these functional and microstructural differences to a deteriorated CP structural integrity with aging. Furthermore, our relaxometry and DTI measures were found to be associated with differences in blood perfusion revealing lower microstructural integrity with lower CBF. Finally, in agreement with literature, sex-related differences in MD and CBF were statistically significant. This work lays the foundation for ongoing investigation of the involvement of CP in neurodegeneration.

Automatic classification of autism spectrum disorder in children using cortical thickness and support vector machine

OBJECTIVE

Autism spectrum disorder (ASD) is a neurodevelopmental condition with a heterogeneous phenotype. The role of biomarkers in ASD diagnosis has been highlighted; cortical thickness has proved to be involved in the etiopathogenesis of ASD core symptoms. We apply support vector machine, a supervised machine learning method, in order to identify specific cortical thickness alterations in ASD subjects.

METHODS

A sample of 76 subjects (9.5 ± 3.4 years old) has been selected, 40 diagnosed with ASD and 36 typically developed subjects. All children underwent a magnetic resonance imaging (MRI) examination; T1-MPRAGE sequences were analyzed to extract features for the characterization and parcellation of regions of interests (ROI); average cortical thickness (CT) has been measured for each ROI. For the classification process, the extracted features were used as input for a classifier to identify ASD subjects through a "learning by example" procedure; the features with best performance was then selected by "greedy forward-feature selection." Finally, this model underwent a leave-one-out cross-validation approach.

RESULTS

From the training set of 68 ROIs, five ROIs reached accuracies of over 70%. After this phase, we used a recursive feature selection process in order to identify the eight features with the best accuracy (84.2%). CT resulted higher in ASD compared to controls in all the ROIs identified at the end of the process.

CONCLUSION

We found increased CT in various brain regions in ASD subjects, confirming their role in the pathogenesis of this condition. Considering the brain development curve during ages, these changes in CT may normalize during development. Further validation on a larger sample is required.

MRI Radiomics Classification and Prediction in Alzheimer's Disease and Mild Cognitive Impairment: A Review

BACKGROUND

Alzheimer's Disease (AD) is a progressive neurodegenerative disease that threatens the health of the elderly. Mild Cognitive Impairment (MCI) is considered to be the prodromal stage of AD. To date, AD or MCI diagnosis is established after irreversible brain structure alterations. Therefore, the development of new biomarkers is crucial to the early detection and treatment of this disease. At present, there exist some research studies showing that radiomics analysis can be a good diagnosis and classification method in AD and MCI.

OBJECTIVE

An extensive review of the literature was carried out to explore the application of radiomics analysis in the diagnosis and classification among AD patients, MCI patients, and Normal Controls (NCs).

RESULTS

Thirty completed MRI radiomics studies were finally selected for inclusion. The process of radiomics analysis usually includes the acquisition of image data, Region of Interest (ROI) segmentation, feature extracting, feature selection, and classification or prediction. From those radiomics methods, texture analysis occupied a large part. In addition, the extracted features include histogram, shapebased features, texture-based features, wavelet features, Gray Level Co-Occurrence Matrix (GLCM), and Run-Length Matrix (RLM).

CONCLUSION

Although radiomics analysis is already applied to AD and MCI diagnosis and classification, there still is a long way to go from these computer-aided diagnostic methods to the clinical application.

Correlation of [18F]florbetaben textural features and age of onset of Alzheimer's disease: a principal components analysis approach

BACKGROUND

When Alzheimer's disease (AD) is occurring at an early onset before 65 years old, its clinical course is generally more aggressive than in the case of a late onset. We aim at identifying [[Formula: see text]F]florbetaben PET biomarkers sensitive to differences between early-onset Alzheimer's disease (EOAD) and late-onset Alzheimer's disease (LOAD). We conducted [[Formula: see text]F]florbetaben PET/CT scans of 43 newly diagnosed AD subjects. We calculated 93 textural parameters for each of the 83 Hammers areas. We identified 41 independent principal components for each brain region, and we studied their Spearman correlation with the age of AD onset, by taking into account multiple comparison corrections. Finally, we calculated the probability that EOAD and LOAD patients have different amyloid-[Formula: see text] ([Formula: see text]) deposition by comparing the mean and the variance of the significant principal components obtained in the two groups with a 2-tailed Student's t-test.

RESULTS

We found that four principal components exhibit a significant correlation at a 95% confidence level with the age of onset in the left lateral part of the anterior temporal lobe, the right anterior orbital gyrus of the frontal lobe, the right lateral orbital gyrus of the frontal lobe and the left anterior part of the superior temporal gyrus. The data are consistent with the hypothesis that EOAD patients have a significantly different [[Formula: see text]F]florbetaben uptake than LOAD patients in those four brain regions.

CONCLUSIONS

Early-onset AD implies a very irregular pattern of [Formula: see text] deposition. The authors suggest that the identified textural features can be used as quantitative biomarkers for the diagnosis and characterization of EOAD patients.

Computer vision in autism spectrum disorder research: a systematic review of published studies from 2009 to 2019

The current state of computer vision methods applied to autism spectrum disorder (ASD) research has not been well established. Increasing evidence suggests that computer vision techniques have a strong impact on autism research. The primary objective of this systematic review is to examine how computer vision analysis has been useful in ASD diagnosis, therapy and autism research in general. A systematic review of publications indexed on PubMed, IEEE Xplore and ACM Digital Library was conducted from 2009 to 2019. Search terms included ['autis*' AND ('computer vision' OR 'behavio* imaging' OR 'behavio* analysis' OR 'affective computing')]. Results are reported according to PRISMA statement. A total of 94 studies are included in the analysis. Eligible papers are categorised based on the potential biological/behavioural markers quantified in each study. Then, different computer vision approaches that were employed in the included papers are described. Different publicly available datasets are also reviewed in order to rapidly familiarise researchers with datasets applicable to their field and to accelerate both new behavioural and technological work on autism research. Finally, future research directions are outlined. The findings in this review suggest that computer vision analysis is useful for the quantification of behavioural/biological markers which can further lead to a more objective analysis in autism research.

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Prenatal S-Adenosine Methionine (SAMe) Induces Changes in Gene Expression in the Brain of Newborn Mice That Are Prevented by Co-Administration of Valproic Acid (VPA)

In previous studies, we produced changes in gene expression in the brain of mice by early postnatal administration of valproic acid (VPA), with distinct differences between genders. The addition of S-adenosine methionine (SAMe) normalized the expression of most genes in both genders, while SAMe alone induced no changes. We treated pregnant dams with a single injection of VPA on day 12.5 of gestation, or with SAMe during gestational days 12–14, or by a combination of VPA and SAMe. In the frontal half of the brain, we studied the expression of 770 genes of the pathways involved in neurophysiology and neuropathology using the NanoString nCounter method. SAMe, but not VPA, induced statistically significant changes in the expression of many genes, with differences between genders. The expression of 112 genes was changed in both sexes, and another 170 genes were changed only in females and 31 only in males. About 30% of the genes were changed by more than 50%. One of the most important pathways changed by SAMe in both sexes was the VEGF (vascular endothelial growth factor) pathway. Pretreatment with VPA prevented almost all the changes in gene expression induced by SAMe. We conclude that large doses of SAMe, if administered prenatally, may induce significant epigenetic changes in the offspring. Hence, SAMe and possibly other methyl donors may be epigenetic teratogens.

Increased hippocampal shape asymmetry and volumetric ventricular asymmetry in autism spectrum disorder

•

Found increased subcortical asymmetry associated with autism.

•

Utilized a new measure of shape asymmetry for analysis of structural differences.

•

Observed significantly increased shape asymmetry of the hippocampus.

•

Observed significantly increased volumetric asymmetry in the lateral ventricles.

•

Focalized abnormalities may result in detectable shape (but not volume) differences.

Autism spectrum disorder (ASD) is a prevalent and fast-growing pervasive neurodevelopmental disorder worldwide. Despite the increasing prevalence of ASD and the breadth of research conducted on the disorder, a conclusive etiology has yet to be established and controversy still exists surrounding the anatomical abnormalities in ASD. In particular, structural asymmetries have seldom been investigated in ASD, especially in subcortical regions. Additionally, the majority of studies for identifying structural biomarkers associated with ASD have focused on small sample sizes. Therefore, the present study utilizes a large-scale, multi-site database to investigate asymmetries in the amygdala, hippocampus, and lateral ventricles, given the potential involvement of these regions in ASD. Contrary to prior work, we are not only computing volumetric asymmetries, but also shape asymmetries, using a new measure of asymmetry based on spectral shape descriptors. This measure represents the magnitude of the asymmetry and therefore captures both directional and undirectional asymmetry. The asymmetry analysis is conducted on 437 individuals with ASD and 511 healthy controls using T1-weighted MRI scans from the Autism Brain Imaging Data Exchange (ABIDE) database. Results reveal significant asymmetries in the hippocampus and the ventricles, but not in the amygdala, in individuals with ASD. We observe a significant increase in shape asymmetry in the hippocampus, as well as increased volumetric asymmetry in the lateral ventricles in individuals with ASD. Asymmetries in these regions have not previously been reported, likely due to the different characterization of neuroanatomical asymmetry and smaller sample sizes used in previous studies. Given that these results were demonstrated in a large cohort, such asymmetries may be worthy of consideration in the development of neurodiagnostic classification tools for ASD.

Integration of Radiomic and Multi-omic Analyses Predicts Survival of Newly Diagnosed IDH1 Wild-Type Glioblastoma

Predictors of patient outcome derived from gene methylation, mutation, or expression are severely limited in IDH1 wild-type glioblastoma (GBM). Radiomics offers an alternative insight into tumor characteristics which can provide complementary information for predictive models. The study aimed to evaluate whether predictive models which integrate radiomic, gene, and clinical (multi-omic) features together offer an increased capacity to predict patient outcome. A dataset comprising 200 IDH1 wild-type GBM patients, derived from The Cancer Imaging Archive (TCIA) (n = 71) and the McGill University Health Centre (n = 129), was used in this study. Radiomic features (n = 45) were extracted from tumor volumes then correlated to biological variables and clinical outcomes. By performing 10-fold cross-validation (n = 200) and utilizing independent training/testing datasets (n = 100/100), an integrative model was derived from multi-omic features and evaluated for predictive strength. Integrative models using a limited panel of radiomic (sum of squares variance, large zone/low gray emphasis, autocorrelation), clinical (therapy type, age), genetic (CIC, PIK3R1, FUBP1) and protein expression (p53, vimentin) yielded a maximal AUC of 78.24% (p = 2.9 × 10⁻⁵). We posit that multi-omic models using the limited set of ‘omic’ features outlined above can improve capacity to predict the outcome for IDH1 wild-type GBM patients.

Correlation Between Hippocampus MRI Radiomic Features and Resting-State Intrahippocampal Functional Connectivity in Alzheimer's Disease

Alzheimer’s disease (AD) is a neurodegenerative disease with main symptoms of chronic primary memory loss and cognitive impairment. The study aim was to investigate the correlation between intrahippocampal functional connectivity (FC) and MRI radiomic features in AD. A total of 67 AD patients and 44 normal controls (NCs) were enrolled in this study. Using the seed-based method of resting-state functional MRI (rs-fMRI), the whole-brain FC with bilateral hippocampus as seed was performed, and the FC values were extracted from the bilateral hippocampus. We observed that AD patients demonstrated disruptive FC in some brain regions in the left hippocampal functional network, including right gyrus rectus, right anterior cingulate and paracingulate gyri, bilateral precuneus, bilateral angular gyrus, and bilateral middle occipital gyrus. In addition, decreased FC was detected in some brain regions in the right hippocampal functional network, including bilateral anterior cingulate and paracingulate gyri, right dorsolateral superior frontal gyrus, and right precentral gyrus. Bilateral hippocampal radiomics features were calculated and selected using the A.K. software. Finally, Pearson’s correlation analyses were conducted between these selected features and the bilateral hippocampal FC values. The results suggested that two gray level run-length matrix (RLM) radiomic features and one gray level co-occurrence matrix (GLCM) radiomic feature weakly associated with FC values in the left hippocampus. However, there were no significant correlations between radiomic features and FC values in the right hippocampus. These findings present that the AD group showed abnormalities in the bilateral hippocampal functional network. This is a prospective study that revealed the weak correlation between the MRI radiomic features and the intrahippocampal FC in AD patients.

Lifespan Changes of the Human Brain In Alzheimer's Disease

Brain imaging studies have shown that slow and progressive cerebral atrophy characterized the development of Alzheimer's Disease (AD). Despite a large number of studies dedicated to AD, key questions about the lifespan evolution of AD biomarkers remain open. When does the AD model diverge from the normal aging model? What is the lifespan trajectory of imaging biomarkers for AD? How do the trajectories of biomarkers in AD differ from normal aging? To answer these questions, we proposed an innovative way by inferring brain structure model across the entire lifespan using a massive number of MRI (N = 4329). We compared the normal model based on 2944 control subjects with the pathological model based on 3262 patients (AD + Mild cognitive Impaired subjects) older than 55 years and controls younger than 55 years. Our study provides evidences of early divergence of the AD models from the normal aging trajectory before 40 years for the hippocampus, followed by the lateral ventricles and the amygdala around 40 years. Moreover, our lifespan model reveals the evolution of these biomarkers and suggests close abnormality evolution for the hippocampus and the amygdala, whereas trajectory of ventricular enlargement appears to follow an inverted U-shape. Finally, our models indicate that medial temporal lobe atrophy and ventricular enlargement are two mid-life physiopathological events characterizing AD brain.

Clinical Imaging of Choroid Plexus in Health and in Brain Disorders: A Mini-Review

The choroid plexuses (ChPs) perform indispensable functions for the development, maintenance and functioning of the brain. Although they have gained considerable interest in the last years, their involvement in brain disorders is still largely unknown, notably because their deep location inside the brain hampers non-invasive investigations. Imaging tools have become instrumental to the diagnosis and pathophysiological study of neurological and neuropsychiatric diseases. This review summarizes the knowledge that has been gathered from the clinical imaging of ChPs in health and brain disorders not related to ChP pathologies. Results are discussed in the light of pre-clinical imaging studies. As seen in this review, to date, most clinical imaging studies of ChPs have used disease-free human subjects to demonstrate the value of different imaging biomarkers (ChP size, perfusion/permeability, glucose metabolism, inflammation), sometimes combined with the study of normal aging. Although very few studies have actually tested the value of ChP imaging biomarkers in patients with brain disorders, these pioneer studies identified ChP changes that are promising data for a better understanding and follow-up of diseases such as schizophrenia, epilepsy and Alzheimer’s disease. Imaging of immune cell trafficking at the ChPs has remained limited to pre-clinical studies so far but has the potential to be translated in patients for example using MRI coupled with the injection of iron oxide nanoparticles. Future investigations should aim at confirming and extending these findings and at developing translational molecular imaging tools for bridging the gap between basic molecular and cellular neuroscience and clinical research.

Topological Properties of Resting-State fMRI Functional Networks Improve Machine Learning-Based Autism Classification

Automatic algorithms for disease diagnosis are being thoroughly researched for use in clinical settings. They usually rely on pre-identified biomarkers to highlight the existence of certain problems. However, finding such biomarkers for neurodevelopmental disorders such as Autism Spectrum Disorder (ASD) has challenged researchers for many years. With enough data and computational power, machine learning (ML) algorithms can be used to interpret the data and extract the best biomarkers from thousands of candidates. In this study, we used the fMRI data of 816 individuals enrolled in the Autism Brain Imaging Data Exchange (ABIDE) to introduce a new biomarker extraction pipeline for ASD that relies on the use of graph theoretical metrics of fMRI-based functional connectivity to inform a support vector machine (SVM). Furthermore, we split the dataset into 5 age groups to account for the effect of aging on functional connectivity. Our methodology achieved better results than most state-of-the-art investigations on this dataset with the best model for the >30 years age group achieving an accuracy, sensitivity, and specificity of 95, 97, and 95%, respectively. Our results suggest that measures of centrality provide the highest contribution to the classification power of the models.

Hippocampal deficits in neurodevelopmental disorders

Neurodevelopmental disorders result from impaired development or maturation of the central nervous system. Both genetic and environmental factors can contribute to the pathogenesis of these disorders; however, the exact causes are frequently complex and unclear. Individuals with neurodevelopmental disorders may have deficits with diverse manifestations, including challenges with sensory function, motor function, learning, memory, executive function, emotion, anxiety, and social ability. Although these functions are mediated by multiple brain regions, many of them are dependent on the hippocampus. Extensive research supports important roles of the mammalian hippocampus in learning and cognition. In addition, with its high levels of activity-dependent synaptic plasticity and lifelong neurogenesis, the hippocampus is sensitive to experience and exposure and susceptible to disease and injury. In this review, we first summarize hippocampal deficits seen in several human neurodevelopmental disorders, and then discuss hippocampal impairment including hippocampus-dependent behavioral deficits found in animal models of these neurodevelopmental disorders.

Regional volumetric abnormalities in pediatric autism revealed by structural magnetic resonance imaging

Autism is a group of complex neurodevelopmental disorders characterized by impaired social interaction, restricted and repetitive behavior. We performed a large-scale retrospective analysis of 1,996 structural magnetic resonance imaging (MRI) examinations of the brain from 1,769 autistic and neurologically typically developing patients (aged 0-32 years), and extracted regional volumetric measurements distributed across 463 brain regions of each patient. The youngest autistic patients (<2.5 years) were diagnosed after imaging and identified retrospectively. Our study demonstrates corpus callosum volumetric abnormalities among autistic patients that are associated with brain overgrowth in early childhood (0-5 years old), followed by a shift towards known decreased volumes in later ages. Results confirm known increases in ventricular volumes among autistic populations and extends those findings to increased volumes of the choroid plexus. Our study also demonstrates distributed volumetric abnormalities among autistic patients that affect a variety of key regional white and grey matter areas of the brain potentially associated with known symptoms of autism.

Corpus Callosum Radiomics-Based Classification Model in Alzheimer's Disease: A Case-Control Study

Background: Alzheimer's disease (AD) is a progressive neurodegenerative disease that causes the decline of some cognitive impairments. The present study aimed to identify the corpus callosum (CC) radiomic features related to the diagnosis of AD and build and evaluate a classification model. Methods: Radiomics analysis was applied to the three-dimensional T1-weighted magnetization-prepared rapid gradient echo (MPRAGE) images of 78 patients with AD and 44 healthy controls (HC). The CC, in each subject, was segmented manually and 385 features were obtained after calculation. Then, the feature selection were carried out. The logistic regression model was constructed and evaluated according to identified features. Thus, the model can be used for distinguishing the AD from HC subjects. Results: Eleven features were selected from the three-dimensional T1-weighted MPRAGE images using the LASSO model, following which, the logistic regression model was constructed. The area under the receiver operating characteristic curve values (AUC), sensitivity, specificity, accuracy, precision, and positive and negative predictive values were 0.720, 0.792, 0.500, 0.684, 0.731, 0.731, and 0.583, respectively. Conclusion: The results demonstrated the potential of CC texture features as a biomarker for the diagnosis of AD. This is the first study showing that the radiomics model based on machine learning was a valuable method for the diagnosis of AD.

Hippocampus and amygdala radiomic biomarkers for the study of autism spectrum disorder

BACKGROUND

Emerging evidence suggests the presence of neuroanatomical abnormalities in subjects with autism spectrum disorder (ASD). Identifying anatomical correlates could thus prove useful for the automated diagnosis of ASD. Radiomic analyses based on MRI texture features have shown a great potential for characterizing differences occurring from tissue heterogeneity, and for identifying abnormalities related to these differences. However, only a limited number of studies have investigated the link between image texture and ASD. This paper proposes the study of texture features based on grey level co-occurrence matrix (GLCM) as a means for characterizing differences between ASD and development control (DC) subjects. Our study uses 64 T1-weighted MRI scans acquired from two groups of subjects: 28 typical age range subjects 4-15 years old (14 ASD and 14 DC, age-matched), and 36 non-typical age range subjects 10-24 years old (20 ASD and 16 DC). GLCM matrices are computed from manually labeled hippocampus and amygdala regions, and then encoded as texture features by applying 11 standard Haralick quantifier functions. Significance tests are performed to identify texture differences between ASD and DC subjects. An analysis using SVM and random forest classifiers is then carried out to find the most discriminative features, and use these features for classifying ASD from DC subjects.

RESULTS

Preliminary results show that all 11 features derived from the hippocampus (typical and non-typical age) and 4 features extracted from the amygdala (non-typical age) have significantly different distributions in ASD subjects compared to DC subjects, with a significance of p < 0.05 following Holm-Bonferroni correction. Features derived from hippocampal regions also demonstrate high discriminative power for differentiating between ASD and DC subjects, with classifier accuracy of 67.85%, sensitivity of 62.50%, specificity of 71.42%, and the area under the ROC curve (AUC) of 76.80% for age-matched subjects with typical age range.

CONCLUSIONS

Results demonstrate the potential of hippocampal texture features as a biomarker for the diagnosis and characterization of ASD.