Jay Shah1,2, Fei Gao1,2, Baoxin Li1,2, Valentina Ghisays3, Ji Luo3, Yinghua Chen3, Wendy Lee3, Yuxiang Zhou4, Tammie L S Benzinger5, Eric M Reiman3, Kewei Chen3, Yi Su1,2,3, Teresa Wu1,2. 1. ASU-Mayo Center for Innovative Imaging, Arizona State University, 699 S. Mill Ave., Tempe, Arizona, 85287, USA. 2. School of Computing and Augmented Intelligence, Arizona State University, 699 S. Mill Ave., Tempe, Arizona, 85287, USA. 3. Banner Alzheimer's Institute, 901 E. Willetta Street, Phoenix, Arizona, 85006, USA. 4. Department of Radiology, Mayo Clinic at Arizona, 5777 E Mayo Blvd, Phoenix, Arizona, 85054, USA. 5. Mallinckrodt Institute of Radiology, Washington University School of Medicine in St. Louis, 510 South Kingshighway Boulevard, St. Louis, Missouri, 63110, USA.
Abstract
INTRODUCTION: Multiple positron emission tomography (PET) tracers are available for amyloid imaging, posing a significant challenge to consensus interpretation and quantitative analysis. We accordingly developed and validated a deep learning model as a harmonization strategy. METHOD: A Residual Inception Encoder-Decoder Neural Network was developed to harmonize images between amyloid PET image pairs made with Pittsburgh Compound-B and florbetapir tracers. The model was trained using a dataset with 92 subjects with 10-fold cross validation and its generalizability was further examined using an independent external dataset of 46 subjects. RESULTS: Significantly stronger between-tracer correlations (P < .001) were observed after harmonization for both global amyloid burden indices and voxel-wise measurements in the training cohort and the external testing cohort. DISCUSSION: We proposed and validated a novel encoder-decoder based deep model to harmonize amyloid PET imaging data from different tracers. Further investigation is ongoing to improve the model and apply to additional tracers.
INTRODUCTION: Multiple positron emission tomography (PET) tracers are available for amyloid imaging, posing a significant challenge to consensus interpretation and quantitative analysis. We accordingly developed and validated a deep learning model as a harmonization strategy. METHOD: A Residual Inception Encoder-Decoder Neural Network was developed to harmonize images between amyloid PET image pairs made with Pittsburgh Compound-B and florbetapir tracers. The model was trained using a dataset with 92 subjects with 10-fold cross validation and its generalizability was further examined using an independent external dataset of 46 subjects. RESULTS: Significantly stronger between-tracer correlations (P < .001) were observed after harmonization for both global amyloid burden indices and voxel-wise measurements in the training cohort and the external testing cohort. DISCUSSION: We proposed and validated a novel encoder-decoder based deep model to harmonize amyloid PET imaging data from different tracers. Further investigation is ongoing to improve the model and apply to additional tracers.
Authors: Victor L Villemagne; Kerryn E Pike; Gaël Chételat; Kathryn A Ellis; Rachel S Mulligan; Pierrick Bourgeat; Uwe Ackermann; Gareth Jones; Cassandra Szoeke; Olivier Salvado; Ralph Martins; Graeme O'Keefe; Chester A Mathis; William E Klunk; David Ames; Colin L Masters; Christopher C Rowe Journal: Ann Neurol Date: 2011-01 Impact factor: 10.422
Authors: Yi Su; Tyler M Blazey; Abraham Z Snyder; Marcus E Raichle; Daniel S Marcus; Beau M Ances; Randall J Bateman; Nigel J Cairns; Patricia Aldea; Lisa Cash; Jon J Christensen; Karl Friedrichsen; Russ C Hornbeck; Angela M Farrar; Christopher J Owen; Richard Mayeux; Adam M Brickman; William Klunk; Julie C Price; Paul M Thompson; Bernadino Ghetti; Andrew J Saykin; Reisa A Sperling; Keith A Johnson; Peter R Schofield; Virginia Buckles; John C Morris; Tammie L S Benzinger Journal: Neuroimage Date: 2014-12-05 Impact factor: 6.556
Authors: Adam S Fleisher; Kewei Chen; Yakeel T Quiroz; Laura J Jakimovich; Madelyn Gutierrez Gomez; Carolyn M Langois; Jessica B S Langbaum; Napatkamon Ayutyanont; Auttawut Roontiva; Pradeep Thiyyagura; Wendy Lee; Hua Mo; Liliana Lopez; Sonia Moreno; Natalia Acosta-Baena; Margarita Giraldo; Gloria Garcia; Rebecca A Reiman; Matthew J Huentelman; Kenneth S Kosik; Pierre N Tariot; Francisco Lopera; Eric M Reiman Journal: Lancet Neurol Date: 2012-11-06 Impact factor: 44.182
Authors: Sanka Amadoru; Vincent Doré; Catriona A McLean; Fairlie Hinton; Claire E Shepherd; Glenda M Halliday; Cristian E Leyton; Paul A Yates; John R Hodges; Colin L Masters; Victor L Villemagne; Christopher C Rowe Journal: Alzheimers Res Ther Date: 2020-03-04 Impact factor: 6.982
Authors: Yi Su; Shaney Flores; Russ C Hornbeck; Benjamin Speidel; Andrei G Vlassenko; Brian A Gordon; Robert A Koeppe; William E Klunk; Chengjie Xiong; John C Morris; Tammie L S Benzinger Journal: Neuroimage Clin Date: 2018-04-25 Impact factor: 4.881
Authors: Pierrick Bourgeat; Vincent Doré; Samantha C Burnham; Tammie Benzinger; Duygu Tosun; Shenpeng Li; Manu Goyal; Pamela LaMontagne; Liang Jin; Christopher C Rowe; Michael W Weiner; John C Morris; Colin L Masters; Jurgen Fripp; Victor L Villemagne Journal: Neuroimage Date: 2022-07-30 Impact factor: 7.400