好色先生

好色先生

Explore the latest content from across our publications

Log In

Forgot Password?
Create New Account

Loading... please wait

Abstract Details

Artificial Intelligence-based Thalamic Volumetry Is Fast, Reliable, and Generalizable to Large, Heterogeneous Datasets Using Only Clinical Quality T2-FLAIR MRI
Multiple Sclerosis
S45 - Multiple Sclerosis: Imaging (5:18 PM-5:30 PM)
010
To evaluate the generalizability of artificial intelligence (AI)-based thalamic quantification to a large, heterogeneous, multi-center dataset, and to evaluate scan-rescan and inter-scanner reliability.
The thalamus is a key gray matter structure, and a sensitive marker of neurodegeneration in multiple sclerosis (MS). Previous reports have indicated that thalamic volumetry on clinical-quality T2-FLAIR images alone is feasible using AI, but large heterogeneous datasets were not assessed.
4,288 MRI exams from 54 centers were used to train and test a convolutional neural network. This dataset was split into training (n=3429) and independent validation/testing sets (n=859). For all exams, FIRST was used to generate thalamic masks from high-resolution T1 images. Masks were then co-registered into the space of clinical-quality T2-FLAIR images, and used as training/testing targets. Additionally, a separate dataset of 177 subjects scanned at both 1.5T and 3T within one week was evaluated to determine inter-scanner reliability. Another dataset of subjects scanned, repositioned, and then re-scanned (n=5) was used to evaluate scan-rescan reliability. Finally, a longitudinal dataset including cognitive processing speed at baseline and follow-up was used to evaluate the predictive value of AI-measured baseline thalamic volume for cognitive decline (n=49) via age- and sex-adjusted linear regression.
The trained model was able to automatically quantify thalamic volume in approximately 42 seconds per case. On the independent validation dataset, accuracy relative to FIRST on high-resolution 3D T1 was 96.3% (r=0.93,p<0.001). Inter-scanner error between 1.5T and 3T was 3.67%. Scan-rescan error with repositioning was 1.94%. Finally, AI-derived baseline thalamic volume was a significant predictor of  longitudinal SDMT decline (R2=0.081, p=0.024; comparatively, FIRST was R2=0.080, p=0.025).
Fully automated AI-based thalamic volume measurement is fast, reliable, and feasible on multicenter clinical-quality T2-FLAIR images. This indicates potential for real-world thalamic volume monitoring, as well as thalamic quantification on large latent datasets without research-quality MRI.
Authors/Disclosures
Michael G. Dwyer III, MD, PhD (Buffalo Neurological Analysis Center)
PRESENTER
Dr. Dwyer has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Bristol Myers Squibb. Dr. Dwyer has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Keystone Heart, Ltd. Dr. Dwyer has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Novartis. The institution of Dr. Dwyer has received research support from Novartis. The institution of Dr. Dwyer has received research support from Keystone Heart, Ltd. The institution of Dr. Dwyer has received research support from Bristol Myers Squibb. The institution of Dr. Dwyer has received research support from Roche.
No disclosure on file
No disclosure on file
Hannah Ferrari No disclosure on file
Niels Bergsland (Buffalo Neuroimaging Analysis Center / State University of New York At Buffalo) Prof. Bergsland has nothing to disclose.
Tom Fuchs (Buffalo Neuroimaging Analysis Center) Mr. Fuchs has nothing to disclose.
Dejan Jakimovski, MD, PhD (Buffalo Neuroimaging Analysis Center, University at Buffalo) Dr. Jakimovski has nothing to disclose.
Bianca Weinstock-Guttman, MD (Department of Neurology, University At Buffalo) Dr. Weinstock-Guttman has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Biogen. Dr. Weinstock-Guttman has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Genentech. Dr. Weinstock-Guttman has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Novartis . Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving as a Consultant for EMD Serono. Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Abbvie. Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Genzyme &Sanofi. Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Janssen . Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Bayer. Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Horizon. Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Genentech. Dr. Weinstock-Guttman has received personal compensation in the range of $0-$499 for serving on a Scientific Advisory or Data Safety Monitoring board for Novartis. Dr. Weinstock-Guttman has received personal compensation in the range of $5,000-$9,999 for serving on a Speakers Bureau for Biogen. Dr. Weinstock-Guttman has received personal compensation in the range of $500-$4,999 for serving on a Speakers Bureau for Janssen. Dr. Weinstock-Guttman has received personal compensation in the range of $0-$499 for serving as a Reviewer with NIH.
Ralph H. Benedict, PhD (University At Buffalo) Dr. Benedict has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Novartis. Dr. Benedict has received personal compensation in the range of $50,000-$99,999 for serving as a Consultant for Roche. Dr. Benedict has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Sanofi. Dr. Benedict has received personal compensation in the range of $5,000-$9,999 for serving as a Consultant for Biogen. Dr. Benedict has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Bristol Meyers Squibb. Dr. Benedict has received personal compensation in the range of $50,000-$99,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Roche. Dr. Benedict has received personal compensation in the range of $10,000-$49,999 for serving on a Speakers Bureau for Biogen. Dr. Benedict has received personal compensation in the range of $500-$4,999 for serving on a Speakers Bureau for Brystal Mier Squibb. Dr. Benedict has received personal compensation in the range of $5,000-$9,999 for serving on a Speakers Bureau for EMD Serono. The institution of Dr. Benedict has received research support from Genzyme. The institution of Dr. Benedict has received research support from Biogen. The institution of Dr. Benedict has received research support from Bristol Myer Squib. Dr. Benedict has received intellectual property interests from a discovery or technology relating to health care.
Jon Riolo, PhD Dr. Riolo has received personal compensation for serving as an employee of Bristol Myers Squib.
Diego Silva (Bristol-Myers Squibb Company) Diego Silva has received personal compensation for serving as an employee of BMS. Diego Silva has received stock or an ownership interest from BMS.
Robert Zivadinov, MD, PhD, FAAN (Buffalo Neuroimaging Analysis Center) The institution of Dr. Zivadinov has received personal compensation in the range of $500-$4,999 for serving as a Consultant for BMS. The institution of Dr. Zivadinov has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Omnicuris. The institution of Dr. Zivadinov has received personal compensation in the range of $500-$4,999 for serving on a Scientific Advisory or Data Safety Monitoring board for Myrobalan. Dr. Zivadinov has received personal compensation in the range of $500-$4,999 for serving on a Speakers Bureau for Sanofi. Dr. Zivadinov has received personal compensation in the range of $10,000-$49,999 for serving on a Speakers Bureau for EMD Serono. Dr. Zivadinov has received personal compensation in the range of $5,000-$9,999 for serving on a Speakers Bureau for Bristol Myers Squibb. The institution of Dr. Zivadinov has received personal compensation in the range of $5,000-$9,999 for serving on a Speakers Bureau for Biogen.