0 49

Cited 0 times in

Slice-selective learning for Alzheimer's disease classification using a generative adversarial network: a feasibility study of external validation

Authors
 Han Woong Kim 1  ;  Ha Eun Lee 1  ;  Sangwon Lee 2  ;  Kyeong Taek Oh 1  ;  Mijin Yun 3  ;  Sun Kook Yoo 4 
Citation
 EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, Vol.47(9) : 2197-2206, 2020-08 
Journal Title
 EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING 
ISSN
 1619-7070 
Issue Date
2020-08
Keywords
Alzheimer’s disease ; External validation ; Feasibility study ; Generative Adversarial Network ; [18F] FDG PET/CT
Abstract
Purpose: The aim of this feasibility study was to use slice selective learning using a Generative Adversarial Network for external validation. We aimed to build a model less sensitive to PET imaging acquisition environment, since differences in environments negatively influence network performance. To investigate the slice performance, each slice evaluation was performed. Methods: We trained our model using a 18F-fluorodeoxyglucose ([18F]FDG) PET/CT dataset obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and tested the model with a Severance Hospital dataset. We applied slice selective learning to reduce computational cost and to extract unbiased features. We extracted features of Alzheimer's disease (AD) and normal cognitive (NC) condition using a Boundary Equilibrium Generative Adversarial Network (BEGAN) for stable convergence. Then, we utilized these features to train a support vector machine (SVM) classifier to distinguish AD from NC. Results: The slice range that covered the posterior cingulate cortex (PCC) using double slices showed the best performance. The accuracy, sensitivity, and specificity of our proposed network was 94.33%, 91.78%, and 97.06% using the Severance dataset and 94.82%, 92.11%, and 97.45% using the ADNI dataset. The performance on the two independent datasets showed no statistical difference (p > 0.05). Moreover, there was a statistical difference in the performance between using two slices and one slice as input (p < 0.05). Conclusions: Our model learned the generalized features of AD and NC for external validation when appropriate slices were selected. This study showed the feasibility of this model with consistent performance when tested using datasets acquired from a variety of image-acquisition environments.
Full Text
https://link.springer.com/article/10.1007%2Fs00259-019-04676-y
DOI
10.1007/s00259-019-04676-y
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Medical Engineering (의학공학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Nuclear Medicine (핵의학교실) > 1. Journal Papers
Yonsei Authors
Yoo, Sun Kook(유선국) ORCID logo https://orcid.org/0000-0002-6032-4686
Yun, Mi Jin(윤미진) ORCID logo https://orcid.org/0000-0002-1712-163X
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/179681
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links