High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis
Multimodal heterogeneous data, such as structural magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF), are effective in improving the performance of automated dementia diagnosis by providing complementary information on degenerated brain disorders, suc...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-03-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.634124/full |
| _version_ | 1818676390020513792 |
|---|---|
| author | Aimei Dong Aimei Dong Zhigang Li Mingliang Wang Dinggang Shen Dinggang Shen Dinggang Shen Mingxia Liu |
| author_facet | Aimei Dong Aimei Dong Zhigang Li Mingliang Wang Dinggang Shen Dinggang Shen Dinggang Shen Mingxia Liu |
| author_sort | Aimei Dong |
| collection | DOAJ |
| description | Multimodal heterogeneous data, such as structural magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF), are effective in improving the performance of automated dementia diagnosis by providing complementary information on degenerated brain disorders, such as Alzheimer's prodromal stage, i.e., mild cognitive impairment. Effectively integrating multimodal data has remained a challenging problem, especially when these heterogeneous data are incomplete due to poor data quality and patient dropout. Besides, multimodal data usually contain noise information caused by different scanners or imaging protocols. The existing methods usually fail to well handle these heterogeneous and noisy multimodal data for automated brain dementia diagnosis. To this end, we propose a high-order Laplacian regularized low-rank representation method for dementia diagnosis using block-wise missing multimodal data. The proposed method was evaluated on 805 subjects (with incomplete MRI, PET, and CSF data) from the real Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Experimental results suggest the effectiveness of our method in three tasks of brain disease classification, compared with the state-of-the-art methods. |
| first_indexed | 2024-12-17T08:42:42Z |
| format | Article |
| id | doaj.art-04d5b563167645839a1561ee633bebfb |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-17T08:42:42Z |
| publishDate | 2021-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-04d5b563167645839a1561ee633bebfb2022-12-21T21:56:17ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2021-03-011510.3389/fnins.2021.634124634124High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia DiagnosisAimei Dong0Aimei Dong1Zhigang Li2Mingliang Wang3Dinggang Shen4Dinggang Shen5Dinggang Shen6Mingxia Liu7School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Science), Jinan, ChinaDepartment of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, United StatesSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Science), Jinan, ChinaCollege of Computer Science and Technology, Nanjing University of Aeronautics & Astronautics, Nanjing, ChinaSchool of Biomedical Engineering, ShanghaiTech University, Shanghai, ChinaShanghai United Imaging Intelligence Co., Ltd., Shanghai, ChinaDepartment of Artificial Intelligence, Korea University, Seoul, South KoreaDepartment of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC, United StatesMultimodal heterogeneous data, such as structural magnetic resonance imaging (MRI), positron emission tomography (PET), and cerebrospinal fluid (CSF), are effective in improving the performance of automated dementia diagnosis by providing complementary information on degenerated brain disorders, such as Alzheimer's prodromal stage, i.e., mild cognitive impairment. Effectively integrating multimodal data has remained a challenging problem, especially when these heterogeneous data are incomplete due to poor data quality and patient dropout. Besides, multimodal data usually contain noise information caused by different scanners or imaging protocols. The existing methods usually fail to well handle these heterogeneous and noisy multimodal data for automated brain dementia diagnosis. To this end, we propose a high-order Laplacian regularized low-rank representation method for dementia diagnosis using block-wise missing multimodal data. The proposed method was evaluated on 805 subjects (with incomplete MRI, PET, and CSF data) from the real Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Experimental results suggest the effectiveness of our method in three tasks of brain disease classification, compared with the state-of-the-art methods.https://www.frontiersin.org/articles/10.3389/fnins.2021.634124/fullhigh-orderlow-rank representationdementiaclassificationincomplete heterogeneous data |
| spellingShingle | Aimei Dong Aimei Dong Zhigang Li Mingliang Wang Dinggang Shen Dinggang Shen Dinggang Shen Mingxia Liu High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis Frontiers in Neuroscience high-order low-rank representation dementia classification incomplete heterogeneous data |
| title | High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis |
| title_full | High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis |
| title_fullStr | High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis |
| title_full_unstemmed | High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis |
| title_short | High-Order Laplacian Regularized Low-Rank Representation for Multimodal Dementia Diagnosis |
| title_sort | high order laplacian regularized low rank representation for multimodal dementia diagnosis |
| topic | high-order low-rank representation dementia classification incomplete heterogeneous data |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.634124/full |
| work_keys_str_mv | AT aimeidong highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis AT aimeidong highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis AT zhigangli highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis AT mingliangwang highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis AT dinggangshen highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis AT dinggangshen highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis AT dinggangshen highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis AT mingxialiu highorderlaplacianregularizedlowrankrepresentationformultimodaldementiadiagnosis |