Visual and Quantitative Evaluation of Amyloid Brain PET Image Synthesis with Generative Adversarial Network
Open Access
- 10 April 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 10 (7) , 2628
Abstract
Conventional data augmentation (DA) techniques, which have been used to improve the performance of predictive models with a lack of balanced training data sets, entail an effort to define the proper repeating operation (e.g., rotation and mirroring) according to the target class distribution. Although DA using generative adversarial network (GAN) has the potential to overcome the disadvantages of conventional DA, there are not enough cases where this technique has been applied to medical images, and in particular, not enough cases where quantitative evaluation was used to determine whether the generated images had enough realism and diversity to be used for DA. In this study, we synthesized 18F-Florbetaben (FBB) images using CGAN. The generated images were evaluated using various measures, and we presented the state of the images and the similarity value of quantitative measurement that can be expected to successfully augment data from generated images for DA. The method includes (1) conditional WGAN-GP to learn the axial image distribution extracted from pre-processed 3D FBB images, (2) pre-trained DenseNet121 and model-agnostic metrics for visual and quantitative measurements of generated image distribution, and (3) a machine learning model for observing improvement in generalization performance by generated dataset. The Visual Turing test showed similarity in the descriptions of typical patterns of amyloid deposition for each of the generated images. However, differences in similarity and classification performance per axial level were observed, which did not agree with the visual evaluation. Experimental results demonstrated that quantitative measurements were able to detect the similarity between two distributions and observe mode collapse better than the Visual Turing test and t-SNE.Keywords
Funding Information
- National Research Foundation (R1A2B2008178)
This publication has 49 references indexed in Scilit:
- Quantification of 18F-florbetapir PET: comparison of two analysis methodsEuropean Journal of Nuclear Medicine and Molecular Imaging, 2015
- Brain PET in the Diagnosis of Alzheimer’s DiseaseClinical Nuclear Medicine, 2014
- Age-specific CT and MRI templates for spatial normalizationNeuroImage, 2012
- Cerebral amyloid-β PET with florbetaben (18F) in patients with Alzheimer's disease and healthy controls: a multicentre phase 2 diagnostic studyThe Lancet Neurology, 2011
- Cross-validation and bootstrapping are unreliable in small sample classificationPattern Recognition Letters, 2008
- Soluble protein oligomers in neurodegeneration: lessons from the Alzheimer's amyloid β-peptideNature Reviews Molecular Cell Biology, 2007
- Imaginem oblivionis: the prospects of neuroimaging for early detection of Alzheimer's diseaseJournal of Clinical Neuroscience, 2005
- Three‐dimensional maximum probability atlas of the human brain, with particular reference to the temporal lobeHuman Brain Mapping, 2003
- Tau Neurofibrillary Pathology and Microtubule StabilityJournal of Molecular Neuroscience, 2002
- The Fréchet distance between multivariate normal distributionsJournal of Multivariate Analysis, 1982