Specifically, examples corresponding to ASD and DC subjects were randomly divided into 10 folds, each of them used in turn to compute the AUC on remaining samples. The overall performance of the model was then measured as the average AUC obtained over all 10 folds [ 43 ]. Random forest classifiers provide an efficient way to measure feature importance [ 44 ]. During the induction phase, discriminative features are selected first when constructing decision trees.
Hippocampus and amygdala radiomic biomarkers for the study of autism spectrum disorder
In particular, root nodes of decision trees represent the most group-informative features. Following this principle, we used the TreeBagger Matlab function to learn a random forest containing decision trees, for the task of differentiating between ASD and DC subjects. We then measured the importance of features as the frequency at which these features occur in the root node of a decision tree 0— times.
Note that feature importance was also measured as the increase in prediction error resulting from permuting features across out-of-bag examples, this strategy giving a similar feature ranking as the one based on root nodes. Randomness testing is used to quantify the p values of individual features and feature combinations [ 45 ]. An empirical null distribution is generated from multiple trials, in which subject labels are randomly permutated, thus rendering them information-less regarding the data i.
Significance p values for individual features are then calculated by integrating the tails of the null distribution, based on classification accuracy using true non-randomized labels. Addressing the group-wise significance is also important, as a number of features may appear significant due to random chance, particularly in a calculation involving high numbers of features.
Techniques such as Bonferroni correction can be overly penalizing, a common alternative is to compute the false discovery rate [ 46 ]. In this work, we control the family-wise error rate using the Holm—Bonferroni procedure, which is known to be uniformly more powerful than Bonferroni correction. Demographic information i. Except for across-gender age differences in group B, no statistically significant differences in age were found between male and female subjects or between ASD and DC subjects.
The age bias in group B could be related to the fact that girls are less likely than boys to meet diagnostic criteria for ASD [ 47 , 48 ]. The inter-rater reliability of manual segmentation labels is reported in Fig. This confirms the quality of manual labels, in particular for hippocampal regions. ASD versus DC classification performance.
Mean receiver operating characteristic ROC curve and AUC obtained by the SVM using the texture features derived from hippocampus black curves and amygdala red curves regions in typical group A and non-typical group B age range subjects. StDev standard deviation. Dominant feature identification. First row Hippocampus-derived features; second row amygdala-derived features. Each bar represents the occurrence number of a feature in decision-tree root nodes from 0 to Group A left and group B right contains typical and non-typical age range subjects, respectively.
Radiomic features, and particulary those encoding texture, enable the quantification of voxel or pixels inter-relationships, describing characteristics of underlying tissues that may be invisible to the human visual system [ 49 ].
Causes of autism - Wikipedia
For example, texture features can help segment lesions in glioblastoma multiforme [ 50 ]. However, the link between texture in neuroanatomical regions and ASD has so far been unclear. In this study, GLCM-based texture features derived from the hippocampus 11 features and amygdala 11 features regions were used for differentiating between ASD and DC subjects.
Note that the gender differences in the untypical age group i. Various studies in the literature have reported abnormal brain development curves for ASD subjects, which may lead to volumetric differences in structures like the hippocampus [ 16 , 54 ]. It is possible that this abnormal development affects the underlying substrate, thereby leading to the observed differences in texture.
Our classification analysis based on SVM showed a higher performance accuracy and AUC of texture features from the hippocampus than those derived from the amygdala, with a mean accuracy of This suggests that hippocampus texture features could be used effectively as biomarkers for detecting ASD. In particular, our feature importance analysis based on random forests indicated hippocampus GLCM correlation to be the most discriminative feature for differentiating between ASD and DC subjects Fig.
This feature measures the linear dependency of grey levels between neighboring pixels, and is related to region heterogeneity e. Our findings on the non-difference of amygdala texture features between ASD and DC subjects group A are consistent with previous studies showing no significance difference in amygdala volume between ASD and DC subjects [ 55 ]. Although other studies have reported an enlarged amygdala in ASD subjects [ 16 , 56 , 57 ], the differences observed for non-typical age range subjects group B could be due to the age bias from using non-matched ASD and DC subjects.
Our proposed approach differs from traditional techniques, which mostly rely on morphological and volumetric characteristics [ 16 — 18 ]. Research suggests that the white matter in young children with ASD may be abnormally homogeneous, and this may reflect poor organization or differentiation of pathways in the temporal lobe [ 58 ]. Another study using multimodality neuroimaging e. Moreover, a recent study demonstrated that the differences between ASD and DC may depend on acquisition site.
This study suggested applying a significance-weighted principal component analysis PCA technique to reduce the undesired intensity variance, thereby increasing the statistical power in detecting the differences between ASD and DC groups [ 60 ]. However, the classifier accuracy between ASD and DC was not sufficient to classify diagnostic groups. Nevertheless, this study motivated our decision of using data from a single site, instead of all available sites, to avoid introducing cross-site intensity variance in our analysis of texture.
Other studies have argued that MRI techniques are too spatiotemporally limited to appreciate the synaptic or neuronal-level abnormalities that may be at the of disorders like ASD [ 61 ]. Our work suggests that MRI texture, which stem from tissue heterogeneity, could capture these abnormalities at a higher scale and, thus, be used for understanding ASD.
A broader investigation involving more subjects would however be required to clarify the nature of texture differences and their impact on ASD. Our study has several limitations worth of mention. The number of subjects i. However, the primary goal of this study was to assess the feasibility of using texture features derived from neuroanatomical region for discriminating between the ASD and DC subjects.
Moreover, employing more advanced methods for segmenting brain regions and classification, for instance based on deep learning, could potentially increase the performance of our approach. This paper presented a radiomic approach using GLCM texture features derived from hippocampal and amygdala regions to characterize differences between ASD and development control subjects.
Our preliminary results show the potential of these features as a biomarker to aid clinicians in the diagnostic of ASD. Texture features derived from the hippocampus, and particularly GLCM correlation, were found to have significant discriminative power for differentiating between ASD and control subjects. Future work can include a validation of the proposed approach on a larger subject cohort, and using additional imaging modalities.
AC and CD contributed to the design of the study, collected and analyzed data, wrote and edited the manuscript; LH contributed to the design of the study and helped to draft the manuscript; CT conceived of the study and helped to draft the manuscript. All authors read and approved the manuscript. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Research article Open Access. Hippocampus and amygdala radiomic biomarkers for the study of autism spectrum disorder. Abstract Background Emerging evidence suggests the presence of neuroanatomical abnormalities in subjects with autism spectrum disorder ASD.
Conclusions Results demonstrate the potential of hippocampal texture features as a biomarker for the diagnosis and characterization of ASD. Autism spectrum disorder Hippocampus Radiomics. The flowchart of the proposed method, shown in Fig. The data used in our study and these steps are discussed in following sub-sections. We considered the following two subject groups: A typical age range children, further divided into A1 14 children with ASD 6 males, 8 females; median age Within this group, the 6 males and 8 females with ASD were individually matched based on age with the 6 males and 8 females labeled as DC.
Subjects in this unbalanced group 20 ASD vs 16 DC were not age-matched, allowing us to evaluate the effect of this confound in our analysis.
A Short Review on the Current Understanding of Autism Spectrum Disorders
We see that these histograms are similar to one another and, therefore, that raw intensity values in the hippocampus are not reliable for differentiating between ASD and DC subjects. More informative features, such as those encoding texture, are thus necessary to the capture the subtle differences arising from ASD. Toward this goal, we used the segmentation masks of hippocampus and amygdala regions to extract texture features based on GLCM. Neighboring pixels are known to exhibit correlation in natural images.
GLCMs are second-order statistics which estimate the properties of two or more pixel values occurring at specific locations relative to each other. To obtain GLCM features, we considered the segmented regions corresponding to the hippocampus and amygdala. Intensities within these regions were then equalized to 32 grey levels before computing the GLCM matrices.
Following this, a set of 11 textures features or descriptors was obtained for each GLCM by applying to these matrices the following quantifier functions: energy, entropy, correlation, contrast, homogeneity, variance, sum-mean, cluster shade, cluster tendency, maximum probability, and inverse variance. Institutional Login Shibboleth or OpenAthens For the academic login, please select your organization on the next page. Forgot Password?
Sign up for MyKarger Institutional Login. Related Articles for " ". Phenotypes, Mechanisms and Treatments. Key Issues Ment Health. Basel, Karger, , vol , pp To view the fulltext, please log in. To view the pdf, please log in. CHF Complete book Immediate access to all parts of this book Cover-to-cover formats may be available Unlimited re-access via MyKarger Unrestricted printing, no saving restriction for personal use read more.
Casanova MF. White matter volume increase and minicolumns in autism. Ann Neurol. Network-based analysis reveals stronger local diffusion-based connectivity and different correlations with oral language skills in brains of children with high functioning autism spectrum disorders. Hum Brain Mapp. Clinical and macroscopic correlates of minicolumnar pathology in autism. J Child Neurol. Abnormalities of cortical minicolumnar organization in the prefrontal lobes of autistic patients. Clin Neurosci Res. The minicolumn hypothesis in neuroscience.
Mountcastle VB. The columnar organization of the neocortex. DeFelipe J. Reflections on the structure of the cortical minicolumn. In: Casanova MF, editor. Neocortical modularity and the cell minicolumn.
Autism Spectrum Disorders
New York: Nova Biomedical; Chandelier cells and epilepsy. A microcolumnar structure of monkey cerebral cortex revealed by immunocytochemical studies of double bouquet cell axons. Minicolumnar organization within somatosensory cortical segregates: II. Emergent functional properties. Cereb Cortex. Basal ganglia and autism: a translational perspective. Autism Res. Evidence for topographic organization in the cerebellum of motor control versus cognitive and affective processing. Frye RE. Central tetrahydrobiopterin concentration in neurodevelopmental disorders.
Front Neurosci. Metabolic effects of sapropterin treatment in autism spectrum disorder: a preliminary study. Transl Psychiatry. Tetrahydrobiopterin as a novel therapeutic intervention for autism. Front Pediatr. Oberman LM.
- Saggi sulla società abruzzese: Negli anni della ricostruzione e della crescita economica: 2 (Contemporanea) (Italian Edition).
- Social Functioning in Autism - Abstract - Autism Spectrum Disorders - Karger Publishers.
- The Scarlet Button (Mr Crook Murder Mystery);
- John Stuart Mill und die induktive Mathematik (German Edition).
- Proteus VSM: Análisis con gráficos (Colección Proteus VSM nº 5) (Spanish Edition).
Expert Opin Investig Drugs. Cellot G, Cherubini E. GABAergic signaling as therapeutic target for autism spectrum disorders. Disruption in the inhibitory architecture of the cell minicolumn: implications for autism. Genes Brain Behav. Grothe B, Klump GM. Temporal processing in sensory systems. Webb S. Drugmakers dance with autism.
Nat Biotechnol. Clinical potential, safety, and tolerability of arbaclofen in the treatment of autism spectrum disorder. Drug Healthc Patient Saf. Ben-Ari Y. NKCC1 chloride importer antagonists attenuate many neurological and psychiatric dsorders. Trends Neurosci. Identifying essential cell types and circuits in autism spectrum disorders.
Int Rev Neurobiol. Evidence of oxidative damage and inflammation associated with low glutathione redox status in the autism brain. Evidence linking oxidative stress, mitochondrial dysfunction, and inflammation in the brain of individuals with autism.
chapter and author info
Front Physiol. Clinical trials of N -acetylcysteine in psychiatry and neurology: a systematic review. Neurosci Biobehav Rev. Metabolic pathology of autism in relation to redox metabolism. Biomark Med. Metabolic and mitochondrial disorders associated with epilepsy in children with autism spectrum disorder. Epilepsy Behav. Mitochondrial dysfunction in autism spectrum disorders: a systematic review and meta-analysis. Mol Psychiatry. Neuropathological mechanisms of seizures in autism spectrum disorder. Treatments for biomedical abnormalities associated with autism spectrum disorder.
Cerebral folate receptor autoantibodies in autism spectrum disorder. Lefevre A, Sirigu A. The two fold role of oxytocin in social developmental disorders: a cause and a remedy? Neurophysiological effects of acute oxytocin administration: systematic review and meta-analysis of placebo-controlled imaging studies. J Psychiatry Neurosci.
The role of hyperhomocysteinemia and B-vitamin deficiency in neurological and psychiatric diseases. Clin Chem Lab Med. Folate metabolism abnormalities in autism: potential biomarkers. Oxidative stress-related biomarkers in autism: systematic review and meta-analyses. Free Radic Biol Med. J Am Physicians Surg. Aberrations in folate metabolic pathway and altered susceptibility to autism. Psychiatr Genet. Methylenetetrahydrofolate reductase polymorphisms CT and risk of autism in the Chinese Han population. Genet Test Mol Biomarkers.
Am J Clin Nutr. Population- and family-based studies associate the MTHFR gene with idiopathic autism in simplex families. J Cell Mol Med. Metabolic endophenotype and related genotypes are associated with oxidative stress in children with autism. Association between MTHFR gene polymorphisms and the risk of autism spectrum disorders: a meta-analysis.
Preliminary evidence for involvement of the folate gene polymorphism 19bp deletion-DHFR in occurrence of autism. Neurosci Lett. Folinic acid improves verbal communication in children with autism and language impairment: a randomized double-blind placebo-controlled trial. Blocking and binding folate receptor alpha autoantibodies identify novel autism spectrum disorder subgroups. Decreased brain levels of vitamin B 12 in aging, autism and schizophrenia. PLoS One. Relative carnitine deficiency in autism.
A common X-linked inborn error of carnitine biosynthesis may be a risk factor for nondysmorphic autism. Frye RE, Rossignol D. Metabolic disorders and abnormalities associated with autism spectrum disorder. J Pediatr Biochem. The immune response in autism: a new frontier for autism research. J Leukoc Biol. Autism-specific maternal autoantibodies recognize critical proteins in developing brain. Neuroglial activation and neuroinflammation in the brain of patients with autism.
Normal gut microbiota modulates brain development and behavior. Increased abundance of Sutterella spp. Gastrointestinal microbiota and metabolite biomarkers in children with autism spectrum disorders. Impaired carbohydrate digestion and transport and mucosal dysbiosis in the intestines of children with autism and gastrointestinal disturbances. Reduced incidence of Prevotella and other fermenters in intestinal microflora of autistic children. Gut bacteria in children with autism spectrum disorders: challenges and promise of studying how a complex community influences a complex disease.
Microb Ecol Health Dis. A model for the induction of autism in the ecosystem of the human body: the anatomy of a modern pandemic? Fecal microbiota and metabolome of children with autism and pervasive developmental disorder not otherwise specified. Buie T.
Potential etiologic factors of microbiome disruption in autism. Clin Ther. Finegold SM. Desulfovibrio species are potentially important in regressive autism. Med Hypotheses. Short-term benefit from oral vancomycin treatment of regressive-onset autism. Microbiota modulate behavioral and physiological abnormalities associated with neurodevelopmental disorders. Neural circuits for social cognition: implications for autism. Development of social skills in children: neural and behavioral evidence for the elaboration of cognitive models.
Characteristics of brains in autism spectrum disorder: structure, function and connectivity across the lifespan. Exp Neurobiol. Resting-state functional connectivity in autism spectrum disorders: a review. Front Psychiatry. Safety and efficacy of memantine in children with autism: randomized, placebo-controlled study and open-label extension. J Child Adolesc Psychopharmacol.
A systematic review of group social skills interventions, and meta-analysis of outcomes, for children with high functioning ASD. Using a patient-centered outcome measure to test methylphenidate versus placebo in children with autism spectrum disorder. Choque Olsson N, Bolte S.
- 1. Introduction.
- Frizzled Like Fried Eggs.
- Next Level Parenting: Raising Authentic, Independent, Spiritually Healthy Children With Gods Help.
- Que la blessure se ferme (Blanche) (French Edition).
- The amygdala and the relevance detection theory of autism: an evolutionary perspective!
- The amygdala and autism: implications from non‐human primate studies!
Sulforaphane treatment of autism spectrum disorder ASD. Nasal oxytocin for social deficits in childhood autism: a randomized controlled trial. The ADOS calibrated severity score: relationship to phenotypic variables and stability over time. Brief report: the ADOS calibrated severity score best measures autism diagnostic symptom severity in pre-school children. A preliminary examination of a general social outcome measure. Assess Eff Interv. Daytime physical activity and sleep in pre-schoolers with developmental disorders. J Paediatr Child Health.
Automated tracking and quantification of autistic behavioral symptoms using Microsoft Kinect. Stud Health Technol Inform. PubMed Google Scholar. A systematic review and meta-analysis of eye-tracking studies in children with autism spectrum disorders. Soc Neurosci. A review of evidence-based early intervention for behavioural problems in children with autism spectrum disorder: the core components of effective programs, child-focused interventions and comprehensive treatment models.
Curr Opin Psychiatry. Cochrane Database Syst Rev. Parent and family impact of autism spectrum disorders: a review and proposed model for intervention evaluation. Clin Child Fam Psychol Rev. Racial and ethnic differences in subspecialty service use by children with autism. Cognitive, language, social and behavioural outcomes in adults with autism spectrum disorders: a systematic review of longitudinal follow-up studies in adulthood. Clin Psychol Rev. Risperidone in children with autism and serious behavioral problems. Medication and parent training in children with pervasive developmental disorders and serious behavior problems: results from a randomized clinical trial.
Risperidone in children with autism: randomized, placebo-controlled, double-blind study. Tolerability, safety, and benefits of risperidone in children and adolescents with autism: month follow-up after 8-week placebo-controlled trial. Lack of effect of risperidone on core autistic symptoms: data from a longitudinal study. Cardiometabolic risk of second-generation antipsychotic medications during first-time use in children and adolescents.
Body mass index change in autism spectrum disorders: comparison of treatment with risperidone and aripiprazole. J Autism Develop Disord. Antipsychotics and the risk of type 2 diabetes mellitus in children and youth.
- Reduced Neural Habituation in the Amygdala and Social Impairments in Autism Spectrum Disorders.
- The Life and Crimes of Harry Lavender?
- Social Functioning in Autism.
JAMA Psychiatry. One-year incidence rates of tardive dyskinesia in children and adolescents treated with second-generation antipsychotics: a systematic review. STX arbaclofen for autism spectrum disorders: an 8-week open-label study. A randomised controlled trial of bumetanide in the treatment of autism in children. Effects of bumetanide on neurobehavioral function in children and adolescents with autism spectrum disorders. Improving emotional face perception in autism with diuretic bumetanide: a proof-of-concept behavioral and functional brain imaging pilot study.
Bumetanide for autism: more eye contact, less amygdala activation. Sci Rep. Memantine experience in children and adolescents with autistic spectrum disorders. A retrospective study of memantine in children and adolescents with pervasive developmental disorders. Psychopharmacology Berl. Memantine as adjunctive therapy in children diagnosed with autistic spectrum disorders: an observation of initial clinical response and maintenance tolerability.
A prospective open-label trial of memantine hydrochloride for the treatment of social deficits in intellectually capable adults with autism spectrum disorder. J Clin Psychopharmacol. Memantine as adjunctive treatment to risperidone in children with autistic disorder: a randomized, double-blind, placebo-controlled trial. Int J Neuropsychopharmacol. Open trial effects of beta-blockers on speech and social behaviors in 8 autistic adults.
Deepmala D, Agrawal M. Use of propranolol for hypersexual behavior in an adolescent with autism. Ann Pharmacother. Effects of propranolol on conversational reciprocity in autism spectrum disorder: a pilot, double-blind, single-dose psychopharmacological challenge study. Effect of propranolol on facial scanning in autism spectrum disorder: a preliminary investigation. J Clin Exp Neuropsychol. Effects of acute beta-adrenergic antagonism on verbal problem solving in autism spectrum disorder and exploration of treatment response markers. Effect of propranolol on word fluency in autism.
Cogn Behav Neurol. Noradrenergic moderation of working memory impairments in adults with autism spectrum disorder. J Int Neuropsychol Soc. Effect of propranolol on functional connectivity in autism spectrum disorder: a pilot study. Brain Imaging Behav. Beta-adrenergic antagonism modulates functional connectivity in the default mode network of individuals with and without autism spectrum disorder. Oxytocin increases retention of social cognition in autism.
Intranasal oxytocin improves emotion recognition for youth with autism spectrum disorders. Oxytocin increases eye contact during a real-time, naturalistic social interaction in males with and without autism. Restoring effects of oxytocin on the attentional preference for faces in autism.
Intranasal oxytocin versus placebo in the treatment of adults with autism spectrum disorders: a randomized controlled trial. Mol Autism. Long-term administration of intranasal oxytocin is a safe and promising therapy for early adolescent boys with autism spectrum disorders. Clinical and neural effects of six-week administration of oxytocin on core symptoms of autism.
The effect of oxytocin nasal spray on social interaction deficits observed in young children with autism: a randomized clinical crossover trial. The effects of a course of intranasal oxytocin on social behaviors in youth diagnosed with autism spectrum disorders: a randomized controlled trial. J Child Psychol Psychiatry.