Вештачка интелигенција

New AI System Utilizing Brain Tumor Cells Detects Autism with 98.5% Accuracy

Summary

Beograd, November 21, 2023 – A newly developed artificial intelligence (AI) system that analyzes specialized brain magnetic resonance imaging (MRI) accurately diagnoses children between 24 and 48 months with autism with an accuracy of 98.5%, according to research that will […]

New AI System Utilizing Brain Tumor Cells Detects Autism with 98.5% Accuracy

Beograd, November 21, 2023 – A newly developed artificial intelligence (AI) system that analyzes specialized brain magnetic resonance imaging (MRI) accurately diagnoses children between 24 and 48 months with autism with an accuracy of 98.5%, according to research that will be presented next week at the annual meeting of the Radiological Society of North America (RSNA).

The multidisciplinary team of experts who developed the three-layered system for analyzing and classifying diffusion tensor magnetic resonance imaging (DT-MRI) includes Mohammed Khudri, B.Sc., a visiting research associate at the University of Louisville in Kentucky. DT-MRI is a specialized technique that detects how water travels along white fibers in the brain.

Our algorithm is trained to identify regions of deviation to diagnose whether someone is autistic or typically neurologically developing, said Khudri.

The AI system involves extracting brain images from DT-MRI scans and extracting imaging indicators that indicate the level of connectivity between different parts of the brain. The machine learning algorithm compares patterns of markers in the brains of children with autism to those of normally developing brains.

Autism is primarily a disorder of improper connections within the brain, said co-author Gregory N. Barnes, M.D., Ph.D., professor of neurology and director of the Norton Children’s Autism Center in Louisville. DT-MRI records these abnormal connections that lead to symptoms often seen in children with autism, such as social communication disorders and repetitive behaviors.

Researchers applied their method to DT-MRI brain scans of 226 children aged 24 to 48 months from the Autism Brain Imaging Data Exchange II. The dataset included scans from 126 children with autism and 100 typically developing children. The technology demonstrated 97% sensitivity, 98% specificity, and an overall accuracy of 98.5% in identifying children with autism.

Our approach is an achievement that enables early detection of autism in infants up to two years old, said Khudri. We believe that therapeutic intervention before the age of three can lead to better outcomes, including increased independence and higher intelligence quotient in individuals with autism.

According to the CDC Autism Community Report 2023, less than half of children with autism spectrum disorder had received developmental evaluation by the age of three, and 30% of children who met the criteria for autism spectrum disorder were not formally diagnosed by the age of eight.

The idea behind early intervention is to harness brain plasticity, or the brain’s ability to normalize function through therapy, said Dr. Barnes.

Researchers stated that children with autism receive delayed diagnoses for several reasons, including lack of capacity at testing centers. Khudri stated that their AI system can facilitate precise management of autism, reducing the time and costs associated with assessment and treatment.

“Brain imaging offers the opportunity for rapid detection of autism in an objective manner,” said Dr. Barnes. “We envision an autism assessment that starts with DT-MRI, followed by a shortened session with a psychologist to confirm the results and guide parents to the next steps. This approach could reduce the workload of psychologists by 30%.”

The AI system generates a report that details which neural pathways are affected, the expected impact on brain functionality, and the severity level that can be used to guide early therapeutic intervention.

Researchers are working on commercializing their AI-based software and obtaining FDA approval.

For more information about brain MRI, visit RadiologyInfo.org.

Source: Radiological Society of North America (RSNA)

Frequently Asked Questions:

Q: What is DT-MRI?
A: DT-MRI is a magnetic resonance technique that detects how water travels along white fibers in the brain. It is used to analyze connections between different parts of the brain.

Q: How does the AI system diagnose autism?
A: The AI system analyzes DT-MRI brain scans and compares patterns of markers in the brains of children with autism and typically developing children. Based on this comparison, the system can accurately diagnose autism in children.

Q: What is the benefit of early intervention in autism?
A: Early intervention in autism can harness brain plasticity, which is the brain’s ability to normalize through therapy. This can lead to better outcomes, such as increased independence and higher intelligence quotient in individuals with autism.

Q: What is the accuracy of the AI system in diagnosing autism?
A: The AI system has an accuracy of 98.5% in diagnosing autism in children between 24 and 48 months of age.

Q: What are the advantages of using an AI system in diagnosing autism?
A: Using an AI system allows for faster detection of autism in an objective manner, reduces the time and costs associated with assessment and treatment, and reduces the workload of psychologists by 30%.