Literature DB >> 34249658

THAN: task-driven hierarchical attention network for the diagnosis of mild cognitive impairment and Alzheimer's disease.

Zhehao Zhang1, Linlin Gao1, Guang Jin1, Lijun Guo1, Yudong Yao2, Li Dong1, Jinming Han3.   

Abstract

BACKGROUND: To assist doctors to diagnose mild cognitive impairment (MCI) and Alzheimer's disease (AD) early and accurately, convolutional neural networks based on structural magnetic resonance imaging (sMRI) images have been developed and shown excellent performance. However, they are still limited in their capacity in extracting discriminative features because of large sMRI image volumes yet small lesion regions and the small number of sMRI images.
METHODS: We proposed a task-driven hierarchical attention network (THAN) taking advantage of the merits of patch-based and attention-based convolutional neural networks for MCI and AD diagnosis. THAN consists of an information sub-network and a hierarchical attention sub-network. In the information sub-network, an information map extractor, a patch-assistant module, and a mutual-boosting loss function are designed to generate a task-driven information map, which automatically highlights disease-related regions and their importance for final classification. In the hierarchical attention sub-network, a visual attention module and a semantic attention module are devised based on the information map to extract discriminative features for disease diagnosis.
RESULTS: Extensive experiments were conducted for four classification tasks: MCI versus (vs.) normal controls (NC), AD vs. NC, AD vs. MCI, and AD vs. MCI vs. NC. Results demonstrated that THAN attained the accuracy of 81.6% for MCI vs. NC, 93.5% for AD vs. NC, 80.8% for AD vs. MCI, and 62.9% for AD vs. MCI vs. NC. It outperformed advanced attention-based and patch-based methods. Moreover, information maps generated by the information sub-network could highlight the potential biomarkers of MCI and AD, such as the hippocampus and ventricles. Furthermore, when the visual and semantic attention modules were combined, the performance of the four tasks was highly improved.
CONCLUSIONS: The information sub-network can automatically highlight the disease-related regions. The hierarchical attention sub-network can extract discriminative visual and semantic features. Through the two sub-networks, THAN fully exploits the visual and semantic features of disease-related regions and meanwhile considers global features of sMRI images, which finally facilitate the diagnosis of MCI and AD. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Alzheimer’s disease (AD); Mild cognitive impairment (MCI); hierarchical attention sub-network (HAS); information sub-network; structural magnetic resonance imaging (sMRI)

Year:  2021        PMID: 34249658      PMCID: PMC8249997          DOI: 10.21037/qims-21-91

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  20 in total

1.  On the momentum term in gradient descent learning algorithms.

Authors:  Ning Qian
Journal:  Neural Netw       Date:  1999-01

Review 2.  The clinical use of structural MRI in Alzheimer disease.

Authors:  Giovanni B Frisoni; Nick C Fox; Clifford R Jack; Philip Scheltens; Paul M Thompson
Journal:  Nat Rev Neurol       Date:  2010-02       Impact factor: 42.937

3.  Mid-level visual features underlie the high-level categorical organization of the ventral stream.

Authors:  Bria Long; Chen-Ping Yu; Talia Konkle
Journal:  Proc Natl Acad Sci U S A       Date:  2018-08-31       Impact factor: 11.205

4.  Joint Multi-Modal Longitudinal Regression and Classification for Alzheimer's Disease Prediction.

Authors:  Lodewijk Brand; Kai Nichols; Hua Wang; Li Shen; Heng Huang
Journal:  IEEE Trans Med Imaging       Date:  2019-12-13       Impact factor: 10.048

Review 5.  Brain imaging in the study of Alzheimer's disease.

Authors:  Eric M Reiman; William J Jagust
Journal:  Neuroimage       Date:  2011-12-07       Impact factor: 6.556

Review 6.  Classification and epidemiology of MCI.

Authors:  Rosebud Roberts; David S Knopman
Journal:  Clin Geriatr Med       Date:  2013-11       Impact factor: 3.076

7.  Non-Invasive RF Technique for Detecting Different Stages of Alzheimer's Disease and Imaging Beta-Amyloid Plaques and Tau Tangles in the Brain.

Authors:  Imran Saied; Tughrul Arslan; Siddharthan Chandran; Colin Smith; Tara Spires-Jones; Suvankar Pal
Journal:  IEEE Trans Med Imaging       Date:  2020-11-30       Impact factor: 10.048

Review 8.  Dementia in China: epidemiology, clinical management, and research advances.

Authors:  Longfei Jia; Meina Quan; Yue Fu; Tan Zhao; Yan Li; Cuibai Wei; Yi Tang; Qi Qin; Fen Wang; Yuchen Qiao; Shengliang Shi; Yan-Jiang Wang; Yifeng Du; Jiewen Zhang; Junjian Zhang; Benyan Luo; Qiumin Qu; Chunkui Zhou; Serge Gauthier; Jianping Jia
Journal:  Lancet Neurol       Date:  2019-09-04       Impact factor: 44.182

9.  Anatomical Landmark Based Deep Feature Representation for MR Images in Brain Disease Diagnosis.

Authors:  Mingxia Liu; Jun Zhang; Dong Nie; Pew-Thian Yap; Dinggang Shen
Journal:  IEEE J Biomed Health Inform       Date:  2018-01-10       Impact factor: 5.772

10.  Automatic classification of MR scans in Alzheimer's disease.

Authors:  Stefan Klöppel; Cynthia M Stonnington; Carlton Chu; Bogdan Draganski; Rachael I Scahill; Jonathan D Rohrer; Nick C Fox; Clifford R Jack; John Ashburner; Richard S J Frackowiak
Journal:  Brain       Date:  2008-01-17       Impact factor: 13.501

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.