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

Kim, Han Woong; Lee, Haeun; Lee, Sang‐Won; Oh, Kyeong Taek; Yun, Mijin; Yoo, Sun Kook

doi:10.1007/s00259-019-04676-y

Cited by 25 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the data source, neuroimaging data analyzed in 13 studies were mainly from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) ( Pan et al, 2018 ; Yan et al, 2018 ; Wegmayr et al, 2019 ; Islam and Zhang, 2020 ; Kim et al, 2020 ; Shin et al, 2020 ; Baydargil et al, 2021 ; Gao et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Sajjad et al, 2021 ; Zhao et al, 2021 ; Zhou X. et al, 2021 ), and some data were from the Open Access Series of Imaging Studies (OASIS) ( Han et al, 2021 ; Zhao et al, 2021 ), the Australian Imaging, Biomarker and Lifestyle Flagship Study of Aging (AIBL) and the National Alzheimer’s Coordinating Center (NACC) databases ( Figure 2B ; Zhou X. et al, 2021 ). Two studies established a test set from the collection of clinical data ( Wegmayr et al, 2019 ; Kim et al, 2020 ). Regarding the data modality, 36 percent (5/14) of studies used data from two modalities ( Figure 2C ; Pan et al, 2018 ; Yan et al, 2018 ; Shin et al, 2020 ; Gao et al, 2021 ; Lin W. et al, 2021 ).…”

Section: Resultsmentioning

confidence: 99%

“…Eleven studies focused on the application of GAN to the task of AD vs. CN classification ( Pan et al, 2018 ; Islam and Zhang, 2020 ; Kim et al, 2020 ; Shin et al, 2020 ; Baydargil et al, 2021 ; Gao et al, 2021 ; Han et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Sajjad et al, 2021 ; Zhou X. et al, 2021 ). Meta-analyses were performed on 6 studies reporting the accuracy, sensitivity, and specificity ( Pan et al, 2018 ; Kim et al, 2020 ; Gao et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Zhou X. et al, 2021 ). The results of the meta-analyses are shown in Table 2 .…”

Section: Resultsmentioning

confidence: 99%

“…Regarding the publication year, all the included articles were published between 2018 and 2021, and more than half of them (8/14) were published in 2021 ( Figure 2A ; Baydargil et al, 2021 ; Gao et al, 2021 ; Han et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Sajjad et al, 2021 ; Zhao et al, 2021 ; Zhou X. et al, 2021 ). Regarding the data source, neuroimaging data analyzed in 13 studies were mainly from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) ( Pan et al, 2018 ; Yan et al, 2018 ; Wegmayr et al, 2019 ; Islam and Zhang, 2020 ; Kim et al, 2020 ; Shin et al, 2020 ; Baydargil et al, 2021 ; Gao et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Sajjad et al, 2021 ; Zhao et al, 2021 ; Zhou X. et al, 2021 ), and some data were from the Open Access Series of Imaging Studies (OASIS) ( Han et al, 2021 ; Zhao et al, 2021 ), the Australian Imaging, Biomarker and Lifestyle Flagship Study of Aging (AIBL) and the National Alzheimer’s Coordinating Center (NACC) databases ( Figure 2B ; Zhou X. et al, 2021 ). Two studies established a test set from the collection of clinical data ( Wegmayr et al, 2019 ; Kim et al, 2020 ).…”

Section: Resultsmentioning

confidence: 99%

“…The type of GAN in the remaining studies varied. For the diagnostic task, 11 studies focused on the AD vs. CN classification ( Pan et al, 2018 ; Islam and Zhang, 2020 ; Kim et al, 2020 ; Shin et al, 2020 ; Baydargil et al, 2021 ; Gao et al, 2021 ; Han et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Sajjad et al, 2021 ; Zhou X. et al, 2021 ), and 7 studies were devoted to the pMCI vs. sMCI classification ( Figure 2D ; Pan et al, 2018 ; Yan et al, 2018 ; Wegmayr et al, 2019 ; Gao et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Zhao et al, 2021 ). For the assessment of the diagnostic performance, accuracy was reported in all studies, while sensitivity and specificity were reported in 6 studies examining the AD vs. CN classification ( Pan et al, 2018 ; Kim et al, 2020 ; Gao et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ; Zhou X. et al, 2021 ) and 4 studies examining the pMCI vs. sMCI classification ( Pan et al, 2018 ; Gao et al, 2021 ; Kang et al, 2021 ; Lin W. et al, 2021 ).…”

Section: Resultsmentioning

confidence: 99%

“…Moreover, some researchers trained the classifier based on features extracted or images processed using GAN to complete the task of pMCI vs. sMCI classification. Kim et al (2020) extracted features of two brain PET slices with the encoder-decoder D in GAN and trained an SVM classifier on these features to achieve accurate classification of AD and CN. Compared with the 2D-CNN model, the SVM classifier exhibited a 12.77% increase in accuracy, a 6.82% increase in sensitivity, and a 19.37% increase in specificity.…”

Section: Discussionmentioning

confidence: 99%

See 4 more Smart Citations

Diagnostic Performance of Generative Adversarial Network-Based Deep Learning Methods for Alzheimer’s Disease: A Systematic Review and Meta-Analysis

Zou

et al. 2022

Front. Aging Neurosci.

View full text Add to dashboard Cite

Alzheimer’s disease (AD) is the most common form of dementia. Currently, only symptomatic management is available, and early diagnosis and intervention are crucial for AD treatment. As a recent deep learning strategy, generative adversarial networks (GANs) are expected to benefit AD diagnosis, but their performance remains to be verified. This study provided a systematic review on the application of the GAN-based deep learning method in the diagnosis of AD and conducted a meta-analysis to evaluate its diagnostic performance. A search of the following electronic databases was performed by two researchers independently in August 2021: MEDLINE (PubMed), Cochrane Library, EMBASE, and Web of Science. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was applied to assess the quality of the included studies. The accuracy of the model applied in the diagnosis of AD was determined by calculating odds ratios (ORs) with 95% confidence intervals (CIs). A bivariate random-effects model was used to calculate the pooled sensitivity and specificity with their 95% CIs. Fourteen studies were included, 11 of which were included in the meta-analysis. The overall quality of the included studies was high according to the QUADAS-2 assessment. For the AD vs. cognitively normal (CN) classification, the GAN-based deep learning method exhibited better performance than the non-GAN method, with significantly higher accuracy (OR 1.425, 95% CI: 1.150–1.766, P = 0.001), pooled sensitivity (0.88 vs. 0.83), pooled specificity (0.93 vs. 0.89), and area under the curve (AUC) of the summary receiver operating characteristic curve (SROC) (0.96 vs. 0.93). For the progressing MCI (pMCI) vs. stable MCI (sMCI) classification, the GAN method exhibited no significant increase in the accuracy (OR 1.149, 95% CI: 0.878–1.505, P = 0.310) or the pooled sensitivity (0.66 vs. 0.66). The pooled specificity and AUC of the SROC in the GAN group were slightly higher than those in the non-GAN group (0.81 vs. 0.78 and 0.81 vs. 0.80, respectively). The present results suggested that the GAN-based deep learning method performed well in the task of AD vs. CN classification. However, the diagnostic performance of GAN in the task of pMCI vs. sMCI classification needs to be improved.Systematic Review Registration: [PROSPERO], Identifier: [CRD42021275294].

show abstract