TY - JOUR
T1 - THAN
T2 - Task-driven hierarchical attention network for the diagnosis of mild cognitive impairment and Alzheimer's disease
AU - Zhang, Zhehao
AU - Gao, Linlin
AU - Jin, Guang
AU - Guo, Lijun
AU - Yao, Yudong
AU - Dong, Li
AU - Han, Jinming
N1 - Publisher Copyright:
© 2021 AME Publishing Company. All rights reserved.
PY - 2021/7
Y1 - 2021/7
N2 - 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.
AB - 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.
KW - Alzheimer's disease (AD)
KW - Hierarchical attention sub-network (HAS)
KW - Information sub-network
KW - Mild cognitive impairment (MCI)
KW - Structural magnetic resonance imaging (sMRI)
UR - http://www.scopus.com/inward/record.url?scp=85106615231&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85106615231&partnerID=8YFLogxK
U2 - 10.21037/qims-21-91
DO - 10.21037/qims-21-91
M3 - Article
AN - SCOPUS:85106615231
SN - 2223-4292
VL - 11
SP - 3338
EP - 3354
JO - Quantitative Imaging in Medicine and Surgery
JF - Quantitative Imaging in Medicine and Surgery
IS - 7
M1 - 91
ER -