TY - GEN
T1 - Predicting Age from White Matter Diffusivity with Residual Learning
AU - The BIOCARD Study Team
AU - Gao, Chenyu
AU - Kim, Michael E.
AU - Lee, Ho Hin
AU - Yang, Qi
AU - Khairi, Nazirah Mohd
AU - Kanakaraj, Praitayini
AU - Newlin, Nancy R.
AU - Archer, Derek B.
AU - Jefferson, Angela L.
AU - Taylor, Warren D.
AU - Boyd, Brian D.
AU - Beason-Held, Lori L.
AU - Resnick, Susan M.
AU - Huo, Yuankai
AU - Van Schaik, Katherine D.
AU - Schilling, Kurt G.
AU - Moyer, Daniel
AU - Išgum, Ivana
AU - Landman, Bennett A.
AU - Albert, Marilyn
AU - Pettigrew, Corinne
AU - Rodzon, Barbara
AU - Soldan, Anja
AU - Gottesman, Rebecca F
AU - Farrington, Leonie
AU - Grega, Maura
AU - Rudow, Gay
AU - Brichko, Rostislav
AU - Rudow, Scott
AU - Giles, Jules
AU - Sacktor, Ned
AU - Miller, Michael
AU - Mori, Susumu
AU - Kolasny, Anthony
AU - Lu, Hanzhang
AU - Oishi, Kenichi
AU - Ratnanather, Tilak
AU - vanZijl, Peter
AU - Younes, Laurent
AU - Moghekar, Abhay
AU - Darrow, Jacqueline
AU - Lewis, Alexandria
AU - Ervin, Ann
AU - Wang, Mei Cheng
AU - Zhu, Yuxin
AU - Wang, Jiangxia
AU - Troncoso, Juan
AU - Pletnikova, Olga
AU - Worley, Paul
AU - Walston, Jeremy
N1 - Publisher Copyright:
© 2024 SPIE.
PY - 2024
Y1 - 2024
N2 - Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural magnetic resonance imaging (MRI) data has become an important proxy task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI’s advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest (ROIs). The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 ± 0.19 years for cognitively normal participants and MAE of 6.62 ± 0.30 years for cognitively impaired participants, while the second method achieves MAE of 4.69 ± 0.23 years for cognitively normal participants and MAE of 4.96 ± 0.28 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction.
AB - Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural magnetic resonance imaging (MRI) data has become an important proxy task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI’s advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest (ROIs). The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 ± 0.19 years for cognitively normal participants and MAE of 6.62 ± 0.30 years for cognitively impaired participants, while the second method achieves MAE of 4.69 ± 0.23 years for cognitively normal participants and MAE of 4.96 ± 0.28 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction.
KW - DTI
KW - brain age
KW - convolutional neural networks
KW - deep learning
UR - http://www.scopus.com/inward/record.url?scp=85193517060&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85193517060&partnerID=8YFLogxK
U2 - 10.1117/12.3006525
DO - 10.1117/12.3006525
M3 - Conference contribution
AN - SCOPUS:85193517060
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2024
A2 - Colliot, Olivier
A2 - Mitra, Jhimli
PB - SPIE
T2 - Medical Imaging 2024: Image Processing
Y2 - 19 February 2024 through 22 February 2024
ER -