Search

Search

Home
...
Research Domains Information and Computing Sciences Artificial Intelligence Natural language processing
Evaluating Biases and Quality Issues in Intermodality Image Translation Studies for Neuroradiology: A Systematic Review

Evaluating Biases and Quality Issues in Intermodality Image Translation Studies for Neuroradiology: A Systematic Review

Shannon L Walston ¹, Hiroyuki Tatekawa ¹, Hirotaka Takita ¹, Yukio Miki ¹, Daiju Ueda ^2,3

Shannon L Walston ¹, Hiroyuki Tatekawa ¹, Hirotaka Takita ¹

¹From the Department of Diagnostic and Interventional Radiology (S.L.W., H.Tatekawa, H.Takita, Y.M., D.U.), Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan.
²From the Department of Diagnostic and Interventional Radiology (S.L.W., H.Tatekawa, H.Takita, Y.M., D.U.), Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan ai.labo.ocu@gmail.com.
³Smart Life Science Lab (D.U.), Center for Health Science Innovation, Osaka Metropolitan University, Osaka, Japan.

⁰From the Department of Diagnostic and Interventional Radiology (S.L.W., H.Tatekawa, H.Takita, Y.M., D.U.), Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan.

Ajnr. American Journal of Neuroradiology +

|

April 25, 2024

Related Experiment Videos

These videos have been matched automatically. Contact us if they are not relevant.

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities

Published on: October 27, 2023

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Transferring Cognitive Tasks Between Brain Imaging Modalities: Implications for Task Design and Results Interpretation in fMRI Studies

Transferring Cognitive Tasks Between Brain Imaging Modalities: Implications for Task Design and Results Interpretation in fMRI Studies

Published on: September 22, 2014

See all related videos

View abstract on PubMed

Summary

This summary is machine-generated.

Artificial intelligence (AI) for brain image translation faces critical issues hindering clinical use. Collaboration between medical and engineering fields is essential to improve AI model reporting and validation for better clinical application.

Area Of Science

Medical Imaging
Artificial Intelligence
Radiology

Background

Intermodality image-to-image translation is an AI technique for generating one image modality from another.
AI models are increasingly used in medical imaging for tasks like brain image translation.

Purpose Of The Study

To systematically identify and quantify biases and quality issues in AI models for intermodality brain image translation.
To assess factors preventing the clinical application of these AI models.

Main Methods

Searched PubMed, Scopus, and IEEE Xplore for AI-based image translation models of radiologic brain images (April 2017-August 2023).
Evaluated 102 studies for quality using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and bias using PROBAST.
Compared adherence to CLAIM and PROBAST criteria between medically-focused and engineering-focused articles.

Main Results

Median adherence to CLAIM was 69%, and to PROBAST was 38%.
Medically-focused articles showed higher overall CLAIM adherence (73%) than engineering-focused ones (65%).
Engineering-focused studies had better model description adherence but lower overall adherence than medical studies.

Conclusions

Most studies have critical issues preventing clinical application of AI brain image translation.
Engineering-focused AI studies, while strong in technical description, lag in overall adherence compared to medical studies.
Improved reporting and collaboration between medical and engineering fields are crucial for advancing clinical AI applications.

Related Experiment Videos

These videos have been matched automatically. Contact us if they are not relevant.

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities

Multimodal Cross-Device and Marker-Free Co-Registration of Preclinical Imaging Modalities

Published on: October 27, 2023

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Transferring Cognitive Tasks Between Brain Imaging Modalities: Implications for Task Design and Results Interpretation in fMRI Studies

Transferring Cognitive Tasks Between Brain Imaging Modalities: Implications for Task Design and Results Interpretation in fMRI Studies

Published on: September 22, 2014

See all related videos

Related Concept Videos

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

Share

X
Facebook
LinkedIn
YouTube

ABOUT JoVE

Overview
Leadership
Blog
JoVE Help Center

AUTHORS

Publishing Process
Editorial Board
Scope & Policies
Peer Review
FAQ
Submit

LIBRARIANS

Testimonials
Subscriptions
Access
Resources
Library Advisory Board
FAQ

RESEARCH

JoVE Journal
Methods Collections
JoVE Encyclopedia of Experiments
Archive

EDUCATION

JoVE Core
JoVE Business
JoVE Science Education
JoVE Lab Manual
Faculty Resource Center
Faculty Site

Terms & Conditions of Use
Privacy Policy
Policies