DeepMNF: Deep Multimodal Neuroimaging Framework for Diagnosing Autism Spectrum Disorder.

Researchers created a computer system called DeepMNF that uses two types of brain scans (fMRI and sMRI) to help diagnose autism. The system combines information from both scan types to get a more complete picture of brain differences in autism. When tested on a large database of brain scans, it performed better than previous computer diagnosis methods.

This study developed DeepMNF, a deep learning framework that combines functional MRI (fMRI) and structural MRI (sMRI) brain scans to diagnose autism spectrum disorder. The system integrates spatial and temporal brain information from both imaging types to address challenges with multisite data variability in the ABIDE repository. The researchers report that their approach achieved superior performance compared to previous best results on the ABIDE-1 dataset, which includes data from multiple screening sites. The framework aims to improve computer-aided diagnosis by fusing complementary neuroimaging information to better distinguish between autistic and non-autistic brain patterns.

While showing promise for improving neuroimaging-based autism diagnosis, this computational approach requires clinical validation before implementation. The multimodal neuroimaging framework could potentially support clinicians in diagnostic decision-making, but practical applicability and integration into clinical workflows remains unclear.

Study does not report sample size, specific performance metrics, or validation details. No information provided about clinical validation, real-world applicability, or comparison with clinical diagnosis. Technical approach focuses on algorithm development rather than clinical implementation.

The growing prevalence of neurological disorders, e.g., Autism Spectrum Disorder (ASD), demands robust computer-aided diagnosis (CAD) due to the diverse symptoms which require early intervention, particularly in young children. The absence of a benchmark neuroimaging diagnostics paves the way to study transitions in the brain's anatomical structure and neurological patterns associated with ASD. The existing CADs take advantage of the large-scale baseline dataset from the Autism Brain Imaging Data Exchange (ABIDE) repository to improve diagnostic performance, but the involvement of multisite data also amplifies the variabilities and heterogeneities that hinder satisfactory results. To resolve this problem, we propose a Deep Multimodal Neuroimaging Framework (DeepMNF) that employs Functional Magnetic Resonance Imaging (fMRI) and Structural Magnetic Resonance Imaging (sMRI) to integrate cross-modality spatiotemporal information by exploiting 2-dimensional time-series data along with 3-dimensional images.

The purpose is to fuse complementary information that increases group differences and homogeneities. To the best of our knowledge, our DeepMNF achieves superior validation performance than the best reported result on the ABIDE-1 repository involving datasets from all available screening sites. In this work, we also demonstrate the performance of the studied modalities in a single model as well as their possible combinations to develop the multimodal framework.