TY - JOUR
T1 - Morphological Feature Visualization of Alzheimer's Disease via Multidirectional Perception GAN
AU - Yu, Wen
AU - Lei, Baiying
AU - Wang, Shuqiang
AU - Liu, Yong
AU - Feng, Zhiguang
AU - Hu, Yong
AU - Shen, Yanyan
AU - Ng, Michael K.
N1 - This work was supported in part by the National Natural Science Foundation of China under Grant 62172403 and Grant 61872351; in part by the International Science and Technology Cooperation Projects of Guangdong under Grant 2019A050510030; in part by the Distinguished Young Scholars Fund of Guangdong under Grant 2021B1515020019; in part by the Excellent Young Scholars of Shenzhen under Grant RCYX20200714114641211; in part by the Shenzhen Key Basic Research Projects under Grant JCYJ20200109115641762 and Grant JCYJ20180507182506416; and in part by the Hong Kong Research Grant Council (HKRGC) under Grant GRF 12200317, Grant 12300218, Grant 12300519, and Grant 17201020.
Publisher Copyright:
© 2022 IEEE.
PY - 2023/8
Y1 - 2023/8
N2 - The diagnosis of early stages of Alzheimer's disease (AD) is essential for timely treatment to slow further deterioration. Visualizing the morphological features for early stages of AD is of great clinical value. In this work, a novel multidirectional perception generative adversarial network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages. Specifically, by introducing a novel multidirectional mapping mechanism into the model, the proposed MP-GAN can capture the salient global features efficiently. Thus, using the class discriminative map from the generator, the proposed model can clearly delineate the subtle lesions via MR image transformations between the source domain and the predefined target domain. Besides, by integrating the adversarial loss, classification loss, cycle consistency loss, and L1 penalty, a single generator in MP-GAN can learn the class discriminative maps for multiple classes. Extensive experimental results on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that MP-GAN achieves superior performance compared with the existing methods. The lesions visualized by MP-GAN are also consistent with what clinicians observe.
AB - The diagnosis of early stages of Alzheimer's disease (AD) is essential for timely treatment to slow further deterioration. Visualizing the morphological features for early stages of AD is of great clinical value. In this work, a novel multidirectional perception generative adversarial network (MP-GAN) is proposed to visualize the morphological features indicating the severity of AD for patients of different stages. Specifically, by introducing a novel multidirectional mapping mechanism into the model, the proposed MP-GAN can capture the salient global features efficiently. Thus, using the class discriminative map from the generator, the proposed model can clearly delineate the subtle lesions via MR image transformations between the source domain and the predefined target domain. Besides, by integrating the adversarial loss, classification loss, cycle consistency loss, and L1 penalty, a single generator in MP-GAN can learn the class discriminative maps for multiple classes. Extensive experimental results on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that MP-GAN achieves superior performance compared with the existing methods. The lesions visualized by MP-GAN are also consistent with what clinicians observe.
KW - Alzheimer's disease (AD)
KW - generative adversarial networks (GANs)
KW - lesion visualization
KW - magnetic resonance (MR) images
UR - http://www.scopus.com/inward/record.url?scp=85127032767&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2021.3118369
DO - 10.1109/TNNLS.2021.3118369
M3 - Journal article
C2 - 35320106
AN - SCOPUS:85127032767
SN - 2162-237X
VL - 34
SP - 4401
EP - 4415
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 8
ER -
