Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/30079
Title: Deep Generative Medical Image Harmonization for Improving Cross-Site Generalization in Deep Learning Predictors.
Austin Authors: Bashyam, Vishnu M;Doshi, Jimit;Erus, Guray;Srinivasan, Dhivya;Abdulkadir, Ahmed;Singh, Ashish;Habes, Mohamad;Fan, Yong;Masters, Colin L ;Maruff, Paul;Zhuo, Chuanjun;Völzke, Henry;Johnson, Sterling C;Fripp, Jurgen;Koutsouleris, Nikolaos;Satterthwaite, Theodore D;Wolf, Daniel H;Gur, Raquel E;Gur, Ruben C;Morris, John C;Albert, Marilyn S;Grabe, Hans J;Resnick, Susan M;Bryan, Nick R;Wittfeld, Katharina;Bülow, Robin;Wolk, David A;Shou, Haochang;Nasrallah, Ilya M;Davatzikos, Christos
Affiliation: Artificial Intelligence in Biomedical Imaging Lab, University of Pennsylvania, Philadelphia, Pennsylvania, USA...
Biggs Alzheimer's Institute, University of Texas San Antonio Health Science Center, San Antonio, Texas, USA..
The Florey Institute of Neuroscience and Mental Health
Tianjin Mental Health Center, Nankai University Affiliated Tianjin Anding Hospital, Tianjin, China..
Department of Psychiatry, Tianjin Medical University, Tianjin, China..
Institute for Community Medicine, University Medicine Greifswald, Greifswald, Germany..
German Centre for Cardiovascular Research, Partner Site Greifswald, Greifswald, Germany..
Wisconsin Alzheimer's Institute, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, USA..
CSIRO Health and Biosecurity, Australian e-Health Research Centre CSIRO, Brisbane, Queensland, Australia..
Department of Psychiatry and Psychotherapy, Ludwig Maximilian University of Munich, Munich, Germany..
Department of Psychiatry, University of Pennsylvania, Philadelphia, Pennsylvania, USA..
Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, USA..
Department of Neurology, Washington University in St. Louis, St. Louis, Missouri, USA..
Department of Neurology, Johns Hopkins University School of Medicine, Baltimore, Maryland, USA..
Department of Psychiatry and Psychotherapy, University Medicine Greifswald, Greifswald, Germany..
German Center for Neurodegenerative Diseases (DZNE), Site Rostock/Greifswald, Greifswald, Germany..
Laboratory of Behavioral Neuroscience, National Institute on Aging, Baltimore, Maryland, USA..
Department of Diagnostic Medicine, University of Texas at Austin, Austin, Texas, USA..
Institute of Diagnostic Radiology and Neuroradiology, University Medicine Greifswald, Greifswald, Germany..
Department of Neurology, University of Pennsylvania, Philadelphia, Pennsylvania, USA..
Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania, Philadelphia, Pennsylvania, USA..
Issue Date: Mar-2022
Date: 2021-09-25
Publication information: Journal of Magnetic Resonance Imaging 2022; 55(3): 908-916
Abstract: In the medical imaging domain, deep learning-based methods have yet to see widespread clinical adoption, in part due to limited generalization performance across different imaging devices and acquisition protocols. The deviation between estimated brain age and biological age is an established biomarker of brain health and such models may benefit from increased cross-site generalizability. To develop and evaluate a deep learning-based image harmonization method to improve cross-site generalizability of deep learning age prediction. Retrospective. Eight thousand eight hundred and seventy-six subjects from six sites. Harmonization models were trained using all subjects. Age prediction models were trained using 2739 subjects from a single site and tested using the remaining 6137 subjects from various other sites. Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T. StarGAN v2, was used to perform a canonical mapping from diverse datasets to a reference domain to reduce site-based variation while preserving semantic information. Generalization performance of deep learning age prediction was evaluated using harmonized, histogram matched, and unharmonized data. Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model. Our results indicated a substantial improvement in age prediction in out-of-sample data, with the overall MAE improving from 15.81 (±0.21) years to 11.86 (±0.11) with histogram matching to 7.21 (±0.22) years with generative adversarial network (GAN)-based harmonization. In the multisite case, across the 5 out-of-sample sites, MAE improved from 9.78 (±6.69) years to 7.74 (±3.03) years with histogram normalization to 5.32 (±4.07) years with GAN-based harmonization. While further research is needed, GAN-based medical image harmonization appears to be a promising tool for improving cross-site deep learning generalization. 4 TECHNICAL EFFICACY: Stage 1.
URI: https://ahro.austin.org.au/austinjspui/handle/1/30079
DOI: 10.1002/jmri.27908
ORCID: 0000-0002-8460-4957
0000-0003-3072-7940
0000-0002-6947-9537
Journal: Journal of Magnetic Resonance Imaging : JMRI
PubMed URL: 34564904
PubMed URL: https://pubmed.ncbi.nlm.nih.gov/34564904/
Type: Journal Article
Subjects: StarGAN
deep learning
harmonization
Appears in Collections:Journal articles

Show full item record

Page view(s)

12
checked on Nov 1, 2024

Google ScholarTM

Check


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.