Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Clinical Effectiveness of Automated Coronary CT-derived Fractional Flow Reserve: A Chinese Randomized Controlled Trial.

Radiology·2024
Same author

Role of Ultrasound and Ultrasound-Based Prediction Model in Differentiating Follicular Thyroid Carcinoma From Follicular Thyroid Adenoma.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2024
Same author

Letter to the Editor: Effectiveness of a Preoperative Bowel Preparation Protocol for Patients with Adolescent Idiopathic Scoliosis to Decrease Postoperative Gastrointestinal Morbidities and the Hospital Length of Stay.

Global spine journal·2024
Same author

Machine Learning Model for Predicting Axillary Lymph Node Metastasis in Clinically Node Positive Breast Cancer Based on Peritumoral Ultrasound Radiomics and SHAP Feature Analysis.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2024
Same author

Testicular tumors: discriminative value of conventional MRI and diffusion weighted imaging.

Medicine·2022
Same author

Computed tomographic angiography may be used for assessing the dilatation of the anterior choroidal and posterior communicating arteries in patients with moyamoya syndrome.

European radiology·2021

Related Experiment Video

Updated: Oct 21, 2025

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging
12:21

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Published on: September 12, 2011

25.4K

Diagnosing autism spectrum disorder in children using conventional MRI and apparent diffusion coefficient based deep

Xiang Guo1, Jiehuan Wang1, Xiaoqiang Wang1

  • 1Department of Radiology, the Affiliated Hospital of Jining Medical University, Jining, China.

European Radiology
|September 5, 2021
PubMed
Summary

Deep learning models show promise in diagnosing autism spectrum disorder (ASD) using conventional MRI (cMRI) and apparent diffusion coefficient (ADC) images. An attention-based dominant sequence model (DSM) achieved the highest diagnostic performance, demonstrating the potential of AI in ASD identification.

Keywords:
Autism spectrum disorderComputational neural networksDeep learningMagnetic resonance imaging

More Related Videos

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.5K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.1K

Related Experiment Videos

Last Updated: Oct 21, 2025

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging
12:21

Probing the Brain in Autism Using fMRI and Diffusion Tensor Imaging

Published on: September 12, 2011

25.4K
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.5K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.1K

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Autism spectrum disorder (ASD) diagnosis relies on behavioral assessments, with limited objective biomarkers.
  • Conventional MRI (cMRI) and apparent diffusion coefficient (ADC) imaging offer potential structural and microstructural insights into the brain.
  • Developing automated diagnostic tools can aid in early and accurate ASD identification.

Purpose of the Study:

  • To develop and validate deep learning (DL) models for diagnosing ASD using cMRI and ADC data.
  • To compare the diagnostic performance of different DL model architectures, including single-sequence, dominant-sequence, and all-sequence models.
  • To evaluate the impact of an attention mechanism on DL model performance for ASD diagnosis.

Main Methods:

  • 151 children with ASD and 151 typically developing (TD) controls were included for training and validation.
  • An independent test set comprised 20 ASD children and 25 TD controls.
  • Multiple DL models, including single-sequence models (SSMs), a dominant-sequence model (DSM), and an all-sequence model (ASM), were developed using cMRI and ADC data.
  • An attention mechanism was integrated to enhance feature detection.

Main Results:

  • Single-sequence models (SSMs) based on FLAIR or ADC achieved an AUC of 0.824–0.850.
  • A dominant-sequence model (DSM) combining FLAIR and ADC demonstrated improved AUC in validation (0.873) and test sets (0.876).
  • The DSM with an attention mechanism achieved the highest diagnostic performance, with an AUC of 0.898, accuracy of 84.4%, sensitivity of 85.0%, and specificity of 84.0%.

Conclusions:

  • Deep learning models utilizing cMRI and ADC images show significant potential for distinguishing ASD from TD individuals.
  • The DSM incorporating an attention mechanism demonstrated superior diagnostic accuracy, highlighting the effectiveness of advanced AI techniques.
  • These findings support the use of DL-based neuroimaging analysis as a valuable tool in ASD diagnosis.