Antoine Pelcat , Alice Le Berre , Wagih Ben Hassen , Clement Debacker , Sylvain Charron , Bertrand Thirion , Laurence Legrand , Guillaume Turc , Catherine Oppenheim , Joseph Benzakoun
{"title":"Generative T2*-weighted images as a substitute for true T2*-weighted images on brain MRI in patients with acute stroke","authors":"Antoine Pelcat , Alice Le Berre , Wagih Ben Hassen , Clement Debacker , Sylvain Charron , Bertrand Thirion , Laurence Legrand , Guillaume Turc , Catherine Oppenheim , Joseph Benzakoun","doi":"10.1016/j.diii.2025.03.004","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>The purpose of this study was to validate a deep learning algorithm that generates T2*-weighted images from diffusion-weighted (DW) images and to compare its performance with that of true T2*-weighted images for hemorrhage detection on MRI in patients with acute stroke.</div></div><div><h3>Materials and methods</h3><div>This single-center, retrospective study included DW- and T2*-weighted images obtained less than 48 hours after symptom onset in consecutive patients admitted for acute stroke. Datasets were divided into training (60 %), validation (20 %), and test (20 %) sets, with stratification by stroke type (hemorrhagic/ischemic). A generative adversarial network was trained to produce generative T2*-weighted images using DW images. Concordance between true T2*-weighted images and generative T2*-weighted images for hemorrhage detection was independently graded by two readers into three categories (parenchymal hematoma, hemorrhagic infarct or no hemorrhage), and discordances were resolved by consensus reading. Sensitivity, specificity and accuracy of generative T2*-weighted images were estimated using true T2*-weighted images as the standard of reference.</div></div><div><h3>Results</h3><div>A total of 1491 MRI sets from 939 patients (487 women, 452 men) with a median age of 71 years (first quartile, 57; third quartile, 81; range: 21–101) were included. In the test set (n = 300), there were no differences between true T2*-weighted images and generative T2*-weighted images for intraobserver reproducibility (κ = 0.97 [95 % CI: 0.95–0.99] vs. 0.95 [95 % CI: 0.92–0.97]; <em>P</em> = 0.27) and interobserver reproducibility (κ = 0.93 [95 % CI: 0.90–0.97] vs. 0.92 [95 % CI: 0.88–0.96]; <em>P</em> = 0.64). After consensus reading, concordance between true T2*-weighted images and generative T2*-weighted images was excellent (κ = 0.92; 95 % CI: 0.91–0.96). Generative T2*-weighted images achieved 90 % sensitivity (73/81; 95 % CI: 81–96), 97 % specificity (213/219; 95 % CI: 94–99) and 95 % accuracy (286/300; 95 % CI: 92–97) for the diagnosis of any cerebral hemorrhage (hemorrhagic infarct or parenchymal hemorrhage).</div></div><div><h3>Conclusion</h3><div>Generative T2*-weighted images and true T2*-weighted images have non-different diagnostic performances for hemorrhage detection in patients with acute stroke and may be used to shorten MRI protocols.</div></div>","PeriodicalId":48656,"journal":{"name":"Diagnostic and Interventional Imaging","volume":"106 7","pages":"Pages 264-271"},"PeriodicalIF":4.9000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Diagnostic and Interventional Imaging","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2211568425000488","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose
The purpose of this study was to validate a deep learning algorithm that generates T2*-weighted images from diffusion-weighted (DW) images and to compare its performance with that of true T2*-weighted images for hemorrhage detection on MRI in patients with acute stroke.
Materials and methods
This single-center, retrospective study included DW- and T2*-weighted images obtained less than 48 hours after symptom onset in consecutive patients admitted for acute stroke. Datasets were divided into training (60 %), validation (20 %), and test (20 %) sets, with stratification by stroke type (hemorrhagic/ischemic). A generative adversarial network was trained to produce generative T2*-weighted images using DW images. Concordance between true T2*-weighted images and generative T2*-weighted images for hemorrhage detection was independently graded by two readers into three categories (parenchymal hematoma, hemorrhagic infarct or no hemorrhage), and discordances were resolved by consensus reading. Sensitivity, specificity and accuracy of generative T2*-weighted images were estimated using true T2*-weighted images as the standard of reference.
Results
A total of 1491 MRI sets from 939 patients (487 women, 452 men) with a median age of 71 years (first quartile, 57; third quartile, 81; range: 21–101) were included. In the test set (n = 300), there were no differences between true T2*-weighted images and generative T2*-weighted images for intraobserver reproducibility (κ = 0.97 [95 % CI: 0.95–0.99] vs. 0.95 [95 % CI: 0.92–0.97]; P = 0.27) and interobserver reproducibility (κ = 0.93 [95 % CI: 0.90–0.97] vs. 0.92 [95 % CI: 0.88–0.96]; P = 0.64). After consensus reading, concordance between true T2*-weighted images and generative T2*-weighted images was excellent (κ = 0.92; 95 % CI: 0.91–0.96). Generative T2*-weighted images achieved 90 % sensitivity (73/81; 95 % CI: 81–96), 97 % specificity (213/219; 95 % CI: 94–99) and 95 % accuracy (286/300; 95 % CI: 92–97) for the diagnosis of any cerebral hemorrhage (hemorrhagic infarct or parenchymal hemorrhage).
Conclusion
Generative T2*-weighted images and true T2*-weighted images have non-different diagnostic performances for hemorrhage detection in patients with acute stroke and may be used to shorten MRI protocols.
期刊介绍:
Diagnostic and Interventional Imaging accepts publications originating from any part of the world based only on their scientific merit. The Journal focuses on illustrated articles with great iconographic topics and aims at aiding sharpening clinical decision-making skills as well as following high research topics. All articles are published in English.
Diagnostic and Interventional Imaging publishes editorials, technical notes, letters, original and review articles on abdominal, breast, cancer, cardiac, emergency, forensic medicine, head and neck, musculoskeletal, gastrointestinal, genitourinary, interventional, obstetric, pediatric, thoracic and vascular imaging, neuroradiology, nuclear medicine, as well as contrast material, computer developments, health policies and practice, and medical physics relevant to imaging.