Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging
Specific brain structures (gray matter regions and white matter tracts) play a dominant role in determining cognitive decline and explain the heterogeneity in cognitive aging. Identification of these structures is crucial for screening of older adults at risk of cognitive decline. Using deep learnin...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-05-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811922001495 |
| _version_ | 1818157406456119296 |
|---|---|
| author | Krishnakant V. Saboo Chang Hu Yogatheesan Varatharajah Scott A. Przybelski Robert I. Reid Christopher G. Schwarz Jonathan Graff-Radford David S. Knopman Mary M. Machulda Michelle M. Mielke Ronald C. Petersen Paul M. Arnold Gregory A. Worrell David T. Jones Clifford R. Jack Jr Ravishankar K. Iyer Prashanthi Vemuri |
| author_facet | Krishnakant V. Saboo Chang Hu Yogatheesan Varatharajah Scott A. Przybelski Robert I. Reid Christopher G. Schwarz Jonathan Graff-Radford David S. Knopman Mary M. Machulda Michelle M. Mielke Ronald C. Petersen Paul M. Arnold Gregory A. Worrell David T. Jones Clifford R. Jack Jr Ravishankar K. Iyer Prashanthi Vemuri |
| author_sort | Krishnakant V. Saboo |
| collection | DOAJ |
| description | Specific brain structures (gray matter regions and white matter tracts) play a dominant role in determining cognitive decline and explain the heterogeneity in cognitive aging. Identification of these structures is crucial for screening of older adults at risk of cognitive decline. Using deep learning models augmented with a model-interpretation technique on data from 1432 Mayo Clinic Study of Aging participants, we identified a subset of brain structures that were most predictive of individualized cognitive trajectories and indicative of cognitively resilient vs. vulnerable individuals. Specifically, these structures explained why some participants were resilient to the deleterious effects of elevated brain amyloid and poor vascular health. Of these, medial temporal lobe and fornix, reflective of age and pathology-related degeneration, and corpus callosum, reflective of inter-hemispheric disconnection, accounted for 60% of the heterogeneity explained by the most predictive structures. Our results are valuable for identifying cognitively vulnerable individuals and for developing interventions for cognitive decline. |
| first_indexed | 2024-12-11T15:13:41Z |
| format | Article |
| id | doaj.art-fc9e51d54ae345bda0e5194445952f85 |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-12-11T15:13:41Z |
| publishDate | 2022-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-fc9e51d54ae345bda0e5194445952f852022-12-22T01:00:41ZengElsevierNeuroImage1095-95722022-05-01251119020Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive agingKrishnakant V. Saboo0Chang Hu1Yogatheesan Varatharajah2Scott A. Przybelski3Robert I. Reid4Christopher G. Schwarz5Jonathan Graff-Radford6David S. Knopman7Mary M. Machulda8Michelle M. Mielke9Ronald C. Petersen10Paul M. Arnold11Gregory A. Worrell12David T. Jones13Clifford R. Jack Jr14Ravishankar K. Iyer15Prashanthi Vemuri16University of Illinois, Urbana-Champaign, IL, United States; Mayo Clinic, Rochester MN, United StatesUniversity of Illinois, Urbana-Champaign, IL, United States; Mayo Clinic, Rochester MN, United StatesUniversity of Illinois, Urbana-Champaign, IL, United States; Mayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesUniversity of Illinois, Urbana-Champaign, IL, United States; Carle Foundation Hospital, Urbana IL, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesMayo Clinic, Rochester MN, United StatesUniversity of Illinois, Urbana-Champaign, IL, United States; Corresponding authors.Mayo Clinic, Rochester MN, United States; Corresponding authors.Specific brain structures (gray matter regions and white matter tracts) play a dominant role in determining cognitive decline and explain the heterogeneity in cognitive aging. Identification of these structures is crucial for screening of older adults at risk of cognitive decline. Using deep learning models augmented with a model-interpretation technique on data from 1432 Mayo Clinic Study of Aging participants, we identified a subset of brain structures that were most predictive of individualized cognitive trajectories and indicative of cognitively resilient vs. vulnerable individuals. Specifically, these structures explained why some participants were resilient to the deleterious effects of elevated brain amyloid and poor vascular health. Of these, medial temporal lobe and fornix, reflective of age and pathology-related degeneration, and corpus callosum, reflective of inter-hemispheric disconnection, accounted for 60% of the heterogeneity explained by the most predictive structures. Our results are valuable for identifying cognitively vulnerable individuals and for developing interventions for cognitive decline.http://www.sciencedirect.com/science/article/pii/S1053811922001495Cognitive heterogeneityBrain reserveDeep learningCognitive aging |
| spellingShingle | Krishnakant V. Saboo Chang Hu Yogatheesan Varatharajah Scott A. Przybelski Robert I. Reid Christopher G. Schwarz Jonathan Graff-Radford David S. Knopman Mary M. Machulda Michelle M. Mielke Ronald C. Petersen Paul M. Arnold Gregory A. Worrell David T. Jones Clifford R. Jack Jr Ravishankar K. Iyer Prashanthi Vemuri Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging NeuroImage Cognitive heterogeneity Brain reserve Deep learning Cognitive aging |
| title | Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging |
| title_full | Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging |
| title_fullStr | Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging |
| title_full_unstemmed | Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging |
| title_short | Deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging |
| title_sort | deep learning identifies brain structures that predict cognition and explain heterogeneity in cognitive aging |
| topic | Cognitive heterogeneity Brain reserve Deep learning Cognitive aging |
| url | http://www.sciencedirect.com/science/article/pii/S1053811922001495 |
| work_keys_str_mv | AT krishnakantvsaboo deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT changhu deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT yogatheesanvaratharajah deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT scottaprzybelski deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT robertireid deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT christophergschwarz deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT jonathangraffradford deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT davidsknopman deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT marymmachulda deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT michellemmielke deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT ronaldcpetersen deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT paulmarnold deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT gregoryaworrell deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT davidtjones deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT cliffordrjackjr deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT ravishankarkiyer deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging AT prashanthivemuri deeplearningidentifiesbrainstructuresthatpredictcognitionandexplainheterogeneityincognitiveaging |