Deep Generative Medical Image Harmonization for Improving Cross‐Site Generalization in Deep Learning Predictors

• Published in: Journal of magnetic resonance imaging Vol. 55; no. 3; pp. 908 - 916
• Main 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
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.03.2022; Wiley Subscription Services, Inc
• Subjects: Adolescent; Age; Biomarkers; Brain; Brain - diagnostic imaging; Deep Learning; Domains; Field strength; Generative adversarial networks; harmonization; Histograms; Humans; Image Processing, Computer-Assisted - methods; Magnetic resonance imaging; Medical imaging; Medical research; Neuroimaging; Population studies; Prediction models; Research Design; Retrospective Studies; StarGAN; Statistical analysis; Statistical tests; StarGAN; deep learning; harmonization
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.27908

Background 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. Purpose To develop and evaluate a deep learning‐based image harmonization method to improve cross‐site generalizability of deep learning age prediction. Study Type Retrospective. Population 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. Field Strength/Sequence Brain imaging with magnetization prepared rapid acquisition with gradient echo or spoiled gradient echo sequences at 1.5 T and 3 T. Assessment 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. Statistical Tests Mean absolute error (MAE) and Pearson correlation between estimated age and biological age quantified the performance of the age prediction model. Results 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. Data Conclusion While further research is needed, GAN‐based medical image harmonization appears to be a promising tool for improving cross‐site deep learning generalization. Level of Evidence 4 Technical Efficacy Stage 1