Generative adversarial network constrained multiple loss autoencoder: A deep learning‐based individual atrophy detection for Alzheimer's disease and mild cognitive impairment

Exploring individual brain atrophy patterns is of great value in precision medicine for Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, the current individual brain atrophy detection models are deficient. Here, we proposed a framework called generative adversarial network...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Human brain mapping Ročník 44; číslo 3; s. 1129 - 1146
Hlavní autori: Shi, Rong, Sheng, Can, Jin, Shichen, Zhang, Qi, Zhang, Shuoyan, Zhang, Liang, Ding, Changchang, Wang, Luyao, Wang, Lei, Han, Ying, Jiang, Jiehui
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Hoboken, USA John Wiley & Sons, Inc 15.02.2023
Predmet:
Alzheimer Disease - pathology
Alzheimer's disease
Atrophy
Atrophy - diagnostic imaging
Atrophy - pathology
Automation
Brain
Brain - diagnostic imaging
Brain - pathology
Cognitive ability
Cognitive Dysfunction - diagnostic imaging
Cognitive Dysfunction - pathology
Deep Learning
Dementia
GAN
Generative adversarial networks
Humans
Image processing
Image reconstruction
Impairment
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Medical imaging
Neurodegenerative diseases
Neuroimaging
Precision medicine
Signal to noise ratio
Signs and symptoms
Subgroups
precision medicine
magnetic resonance imaging
GAN
Alzheimer's disease
ISSN:1065-9471, 1097-0193, 1097-0193
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Exploring individual brain atrophy patterns is of great value in precision medicine for Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, the current individual brain atrophy detection models are deficient. Here, we proposed a framework called generative adversarial network constrained multiple loss autoencoder (GANCMLAE) for precisely depicting individual atrophy patterns. The GANCMLAE model was trained using normal controls (NCs) from the Alzheimer's Disease Neuroimaging Initiative cohort, and the Xuanwu cohort was employed to validate the robustness of the model. The potential of the model for identifying different atrophy patterns of MCI subtypes was also assessed. Furthermore, the clinical application potential of the GANCMLAE model was investigated. The results showed that the model can achieve good image reconstruction performance on the structural similarity index measure (0.929 ± 0.003), peak signal‐to‐noise ratio (31.04 ± 0.09), and mean squared error (0.0014 ± 0.0001) with less latent loss in the Xuanwu cohort. The individual atrophy patterns extracted from this model are more precise in reflecting the clinical symptoms of MCI subtypes. The individual atrophy patterns exhibit a better discriminative power in identifying patients with AD and MCI from NCs than those of the t‐test model, with areas under the receiver operating characteristic curve of 0.867 (95%: 0.837–0.897) and 0.752 (95%: 0.71–0.790), respectively. Similar findings are also reported in the AD and MCI subgroups. In conclusion, the GANCMLAE model can serve as an effective tool for individualised atrophy detection. Our study presented a generative adversarial network constrained multiple loss autoencoder (GANCMLAE) model for the detection of individual atrophy patterns based on structural magnetic resonance imaging data. Experiments on two independent cohorts of participants showed that the residual maps from GANCMLAE model may serve as an effective tool to achieve precisely individualized atrophy detection and have potential for clinical applications.
Bibliografia:Funding information
Foundation for the National Institutes of Health, Grant/Award Number: U01 AG024904; Science and Technology Innovation 2030 Major Projects, Grant/Award Number: 2022ZD0211600; U.S. Department of Defense, Grant/Award Number: W81XWH‐12‐2‐0012; National Natural Science Foundation of China, Grant/Award Numbers: 81830059, 61603236, 82020108013, 61633018; National Key Research and Development Program of China, Grant/Award Numbers: 2018YFC1707704, 2018YFC1312000, 2016YFC1306300; 111 Project, Grant/Award Number: D20031; Shanghai Municipal Science and Technology Major Project, Grant/Award Number: 017SHZDZX01; Beijing Municipal Commission of Health and Family Planning, Grant/Award Number: PXM2020_026283_000002; National Institute of Aging and the National Institute of Biomedical Imaging and Bioengineering
Rong Shi and Can Sheng contributed equally to this work.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Funding information Foundation for the National Institutes of Health, Grant/Award Number: U01 AG024904; Science and Technology Innovation 2030 Major Projects, Grant/Award Number: 2022ZD0211600; U.S. Department of Defense, Grant/Award Number: W81XWH‐12‐2‐0012; National Natural Science Foundation of China, Grant/Award Numbers: 81830059, 61603236, 82020108013, 61633018; National Key Research and Development Program of China, Grant/Award Numbers: 2018YFC1707704, 2018YFC1312000, 2016YFC1306300; 111 Project, Grant/Award Number: D20031; Shanghai Municipal Science and Technology Major Project, Grant/Award Number: 017SHZDZX01; Beijing Municipal Commission of Health and Family Planning, Grant/Award Number: PXM2020_026283_000002; National Institute of Aging and the National Institute of Biomedical Imaging and Bioengineering
ISSN:1065-9471
1097-0193
1097-0193
DOI:10.1002/hbm.26146