Lele Xu1, Xia Wu2, Kewei Chen3, Li Yao4. 1. College of Information Science and Technology, Beijing Normal University, Beijing 100875, China. 2. College of Information Science and Technology, Beijing Normal University, Beijing 100875, China; State Key Laboratory of Cognitive Neuroscience and Learning & IDG/McGovern Institute for Brain Research, Beijing Normal University, Beijing 100875, China. Electronic address: wuxia@bnu.edu.cn. 3. Banner Alzheimer's Institute and Banner Good Samaritan PET Center, Phoenix, AZ 85006, USA. 4. College of Information Science and Technology, Beijing Normal University, Beijing 100875, China; State Key Laboratory of Cognitive Neuroscience and Learning & IDG/McGovern Institute for Brain Research, Beijing Normal University, Beijing 100875, China.
Abstract
BACKGROUND AND OBJECTIVE: The discrimination of Alzheimer's disease (AD) and its prodromal stage known as mild cognitive impairment (MCI) from normal control (NC) is important for patients' timely treatment. The simultaneous use of multi-modality data has been demonstrated to be helpful for more accurate identification. The current study focused on extending a multi-modality algorithm and evaluating the method by identifying AD/MCI. METHODS: In this study, sparse representation-based classification (SRC), a well-developed method in pattern recognition and machine learning, was extended to a multi-modality classification framework named as weighted multi-modality SRC (wmSRC). Data including three modalities of volumetric magnetic resonance imaging (MRI), fluorodeoxyglucose (FDG) positron emission tomography (PET) and florbetapir PET from the Alzheimer's disease Neuroimaging Initiative database were adopted for AD/MCI classification (113 AD patients, 110 MCI patients and 117 NC subjects). RESULTS: Adopting wmSRC, the classification accuracy achieved 94.8% for AD vs. NC, 74.5% for MCI vs. NC, and 77.8% for progressive MCI vs. stable MCI, superior to or comparable with the results of some other state-of-the-art models in recent multi-modality researches. CONCLUSIONS: The wmSRC method is a promising tool for classification with multi-modality data. It could be effective for identifying diseases from NC with neuroimaging data, which could be helpful for the timely diagnosis and treatment of diseases.
BACKGROUND AND OBJECTIVE: The discrimination of Alzheimer's disease (AD) and its prodromal stage known as mild cognitive impairment (MCI) from normal control (NC) is important for patients' timely treatment. The simultaneous use of multi-modality data has been demonstrated to be helpful for more accurate identification. The current study focused on extending a multi-modality algorithm and evaluating the method by identifying AD/MCI. METHODS: In this study, sparse representation-based classification (SRC), a well-developed method in pattern recognition and machine learning, was extended to a multi-modality classification framework named as weighted multi-modality SRC (wmSRC). Data including three modalities of volumetric magnetic resonance imaging (MRI), fluorodeoxyglucose (FDG) positron emission tomography (PET) and florbetapir PET from the Alzheimer's disease Neuroimaging Initiative database were adopted for AD/MCI classification (113 ADpatients, 110 MCI patients and 117 NC subjects). RESULTS: Adopting wmSRC, the classification accuracy achieved 94.8% for AD vs. NC, 74.5% for MCI vs. NC, and 77.8% for progressive MCI vs. stable MCI, superior to or comparable with the results of some other state-of-the-art models in recent multi-modality researches. CONCLUSIONS: The wmSRC method is a promising tool for classification with multi-modality data. It could be effective for identifying diseases from NC with neuroimaging data, which could be helpful for the timely diagnosis and treatment of diseases.
Authors: Yiming Ding; Jae Ho Sohn; Michael G Kawczynski; Hari Trivedi; Roy Harnish; Nathaniel W Jenkins; Dmytro Lituiev; Timothy P Copeland; Mariam S Aboian; Carina Mari Aparici; Spencer C Behr; Robert R Flavell; Shih-Ying Huang; Kelly A Zalocusky; Lorenzo Nardo; Youngho Seo; Randall A Hawkins; Miguel Hernandez Pampaloni; Dexter Hadley; Benjamin L Franc Journal: Radiology Date: 2018-11-06 Impact factor: 29.146
Authors: José María Mateos-Pérez; Mahsa Dadar; María Lacalle-Aurioles; Yasser Iturria-Medina; Yashar Zeighami; Alan C Evans Journal: Neuroimage Clin Date: 2018-08-10 Impact factor: 4.881