Study: MRI can detect autism in the adult brain
Spatial patterns detected using a support vector machine (SVM) may help further exploration of the specific genetic and neuropathological underpinnings of autism spectrum disorder (ASD) in adults, and can potentially provide new insights into the multifactorial etiology of the condition, according to a study published online Aug. 11 in the Journal of Neuroscience.
“ASD is a neurodevelopmental condition with multiple causes, comorbid conditions and a wide range in the type and severity of symptoms expressed by different individuals. This makes the neuroanatomy of autism inherently difficult to describe,” wrote Christine Ecker, MSc, PhD, from the brain maturation subspecialty in the department of psychological medicine at the Institute of Psychiatry at King’s College London in England, and colleagues.
The researchers sought to demonstrate how using biological markers, rather than personality traits, can be used to show ASD in adults. They also hypothesized that MRI can be used to characterize complex and subtle structural patterns of gray matter anatomy that can reveal ASD and spatially distributed patterns of discriminating regions for a variety of parameters describing brain anatomy.
Ecker and colleagues selected a set of five morphological parameters-including volumetric and geometric features-at each spatial location on the cortical surface in order to discriminate between people with ASD and controls using an SVM analytic approach. The authors recruited males between the ages of 20 and 68 years for the study, consisting of 20 healthy adults, 20 adults with ASD and 19 adults with attention deficit hyperactivity disorder (ADHD).
Each of the participants underwent testing for ASD and ADHD by way of traditional methods, including an IQ test, a psychiatric interview, a physical exam and a blood test. The researchers then utilized the MRI brain scanning technique to compare adults with ASD and ADHD to the control group.
The authors found that the scanning method was able to identify individuals with ASD at a sensitivity of up to 90 percent and a specificity of up to 80 percent. However, the ability of individual cortical features to discriminate between groups was highly variable, and the discriminating patterns of regions varied across parameters, they wrote, citing that the classification was specific to ASD rather than other neurodevelopmental conditions, such as ADHD.
“SVM achieved good separation between groups, and revealed spatially distributed and largely non-overlapping patterns of regions with highest classification weights for each of five morphological features," offered the researchers. “Our results confirm the hypothesis that the neuroanatomy of autism is truly multidimensional, and affects multiple and most likely independent cortical features.”
Ecker noted that the next step for the research is to determine whether the scanning method can be used to diagnose children. "The value of this rapid and accurate tool to diagnose ASD is immense. It could help to alleviate the need for the emotional, time consuming and expensive diagnosis process which ASD patients and families currently have to endure,” she concluded.
“ASD is a neurodevelopmental condition with multiple causes, comorbid conditions and a wide range in the type and severity of symptoms expressed by different individuals. This makes the neuroanatomy of autism inherently difficult to describe,” wrote Christine Ecker, MSc, PhD, from the brain maturation subspecialty in the department of psychological medicine at the Institute of Psychiatry at King’s College London in England, and colleagues.
The researchers sought to demonstrate how using biological markers, rather than personality traits, can be used to show ASD in adults. They also hypothesized that MRI can be used to characterize complex and subtle structural patterns of gray matter anatomy that can reveal ASD and spatially distributed patterns of discriminating regions for a variety of parameters describing brain anatomy.
Ecker and colleagues selected a set of five morphological parameters-including volumetric and geometric features-at each spatial location on the cortical surface in order to discriminate between people with ASD and controls using an SVM analytic approach. The authors recruited males between the ages of 20 and 68 years for the study, consisting of 20 healthy adults, 20 adults with ASD and 19 adults with attention deficit hyperactivity disorder (ADHD).
Each of the participants underwent testing for ASD and ADHD by way of traditional methods, including an IQ test, a psychiatric interview, a physical exam and a blood test. The researchers then utilized the MRI brain scanning technique to compare adults with ASD and ADHD to the control group.
The authors found that the scanning method was able to identify individuals with ASD at a sensitivity of up to 90 percent and a specificity of up to 80 percent. However, the ability of individual cortical features to discriminate between groups was highly variable, and the discriminating patterns of regions varied across parameters, they wrote, citing that the classification was specific to ASD rather than other neurodevelopmental conditions, such as ADHD.
“SVM achieved good separation between groups, and revealed spatially distributed and largely non-overlapping patterns of regions with highest classification weights for each of five morphological features," offered the researchers. “Our results confirm the hypothesis that the neuroanatomy of autism is truly multidimensional, and affects multiple and most likely independent cortical features.”
Ecker noted that the next step for the research is to determine whether the scanning method can be used to diagnose children. "The value of this rapid and accurate tool to diagnose ASD is immense. It could help to alleviate the need for the emotional, time consuming and expensive diagnosis process which ASD patients and families currently have to endure,” she concluded.