Advancing diagnostic performance and clinical applicability of deep learning-driven generative adversarial networks for Alzheimer's disease

Abstract

Alzheimer's disease (AD) is a neurodegenerative disease that severely affects the activities of daily living in aged individuals, which typically needs to be diagnosed at an early stage. Generative adversarial networks (GANs) provide a new deep learning method that show good performance in image processing, while it remains to be verified whether a GAN brings benefit in AD diagnosis. The purpose of this research is to systematically review psychoradiological studies on the application of a GAN in the diagnosis of AD from the aspects of classification of AD state and AD-related image processing compared with other methods. In addition, we evaluated the research methodology and provided suggestions from the perspective of clinical application. Compared with other methods, a GAN has higher accuracy in the classification of AD state and better performance in AD-related image processing (e.g. image denoising and segmentation). Most studies used data from public databases but lacked clinical validation, and the process of quantitative assessment and comparison in these studies lacked clinicians' participation, which may have an impact on the improvement of generation effect and generalization ability of the GAN model. The application value of GANs in the classification of AD state and AD-related image processing has been confirmed in reviewed studies. Improvement methods toward better GAN architecture were also discussed in this paper. In sum, the present study demonstrated advancing diagnostic performance and clinical applicability of GAN for AD, and suggested that the future researchers should consider recruiting clinicians to compare the algorithm with clinician manual methods and evaluate the clinical effect of the algorithm.

Component-Based Software Testing Method Based on Deep Adversarial Network

“…Retrospective studies demonstrate the value of using adversarial networks in classifying AD conditions and processing AD-related images. Ultimately, this study demonstrates the improved diagnostic ability and clinical utility of deep adversarial networks for AD [3]. Virtual tissue staining using deep adversarial networks provides a realistic approach to these problems, but the use of deep learning methods remains challenging due to the very limited amount of data available for training.…”

Machine learning of brain-specific biomarkers from EEG

“…Would it then be appropriate to address the problem of disentangling brain and body signals with statistical techniques for deconfounding (Zhao et al, 2020)? A recent line of work has started studying machine learning techniques for addressing confounding in neuroscience applications (Chyzhyk et al, 2022; Qu et al, 2021). While this can lead to practically useful methods, there is an important theoretical mismatch with our perspective.…”

Embracing Deepfakes and AI-generated images in Neuroscience Research

“…In clinical neuroscience, AI can be used to synthesise neuroimaging scans (Jeong et al, 2022;Laino et al, 2022;Qu et al, 2021;Sorin et al, 2020;Wang et al, 2023;Yi et al, 2019), which can improve AI classification of neurological phenomena where examples are rare, improving diagnoses (Sims, 2022) and enhancing our understanding of brain diseases and function (Wang et al, 2023). AI can be used to convert different imaging modalities like MRI to CT (Kearney et al, 2020), helpful for diagnoses, and also comparing across different types of research.…”